Home Masking and noise reduction processing of music signals in reverberant music
Article Open Access

Masking and noise reduction processing of music signals in reverberant music

  • Shenghuan Zhang EMAIL logo and Ye Cheng
Published/Copyright: April 1, 2022
Download Article (PDF)
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Journal of Intelligent Systems
From the journal Journal of Intelligent Systems Volume 31 Issue 1

Abstract

Noise will be inevitably mixed with music signals in the recording process. To improve the quality of music signals, it is necessary to reduce noise as much as possible. This article briefly introduces noise, the masking effect, and the spectral subtraction method for reducing noise in reverberant music. The spectral subtraction method was improved by the human ear masking effect to enhance its noise reduction performance. Simulation experiments were carried out on the traditional and improved spectral subtraction methods. The results showed that the improved spectral subtraction method could reduce the noise in reverberant music more effectively; under an objective evaluation criterion, the signal-to-noise ratio, the de-reverberated music signal processed by the improved spectral subtraction method had a higher signal-to-noise ratio; under a subjective evaluation criterion, mean opinion score (MOS), the de-reverberated music signal processed by the improved spectral subtraction method also had a better evaluation.

Keywords: reverberant music; musical noise; masking effect; spectral subtraction method

1 Introduction

Music will be inevitably mixed with nonmusic signal noises in the recording process [1]. These noises will have different degrees of impact on the normal music signal after mixing, and the specific size of the impact depends on the application scenario of the music signal, but regardless of the scenario, the quality of music signals will be reduced [2]. To improve the quality of music signals, they need to be processed for noise reduction [3]. Kohlberg et al. [4] evaluated the impact of noise reduction algorithms on music enjoyment and found that reducing the noise of music helped improve the music enjoyment. Deng and Han [5] proposed an adaptive denoising algorithm based on the sparsity of the first-order differential overlap group of heart sound signals. The experiments found that the algorithm performed better in denoising heart sound signals than traditional “db10,” “db5,” and “bior5.5” wavelet methods. Chen et al. [6] explored the correlation between wavelet transform and heartbeat noise performance and the adaptation of heartbeat classification using bispectral estimation. By comparing the denoising effect of four wavelets, including haar, db6, sym8, and coif6, it was found that the db6 wavelet had the best denoising effect on heartbeat signals. The aforementioned studies all focus on music noise reduction. Some of the aforementioned studies started from the improvement of music quality by noise reduction algorithms and verified and the improvement of musical experience by noise reduction algorithms; some started from the specific algorithms of noise reduction and explored the advantages of different noise reduction algorithms. All the aforementioned studies provide effective references for music signal noise reduction. In this article, noises in the reverberant music were rapidly reduced based on the simplicity of spectral subtraction, and the human ear masking effect was used to further improve the quality of music after spectral subtraction. The comparison between the traditional and improved spectral subtraction methods verified the effectiveness of the improved method. The novelty of this article lies in reducing noise in reverberant music fast by the spectral subtraction method and improving the quality of music after noise reduction by taking advantage of the insensitivity of the human ear to the phase change of music signals. This study provides an effective reference for improving the noise reduction of music signals.

2 Noise and masking effects

Objectively speaking, noise refers to all irregular signals [7], and in this article, it refers to irregular sound signals. Subjectively speaking, sounds that cause physiological and psychological discomfort and interfere with normal hearing are all noise. Even music with a regular pattern can be classified as noise if it interferes with the sound of people’s normal communication or their normal routine [8].

Influenced by different environments, noise can be divided into additive noise and nonadditive noise [9]. Additive noise includes impulse noise, broadband noise, periodic noise, and interference from other voices; nonadditive noise mainly includes reverberation, circuit noise, etc. [10]. Impulse noise is characterized by the sudden appearance of a short period of high-amplitude band spectrum; broadband noise is characterized by its overlap with pure sound signals in time and frequency domains; speech noise is characterized by the common transmission of other sound signals and pure sound signals; circuit noise is inherent to circuit operation, but can be handled after being transforming to additive noise through homomorphic conversion [11].

The ear is the human organ that receives sound. In judging the noise reduction effect of music and other sound signals, although the signal-to-noise ratio can be used to objectively judge the noise reduction effect, it ultimately depends on the subjective perception of the human ear [12]. Usually, the music sound waveform subjectively perceived by the human ear is not the same as the actual music sound waveform. In addition, the human auditory system has a good noise suppression effect when processing the reverberant sound mixed with background noise. Therefore, when noise reduction is applied to reverberant music signals, the perceptual characteristics of the human ear can also be taken into consideration to make the noise reduction effect closer to the subjective perception of the human ear [13].

The human ear can perceive sound at frequencies between 20 and 20,000 Hz, and there is a masking effect when the human ear processes the sound signal. In short, a sound is more difficult to hear by the human ear due to the presence of another sound. When strength of the masking sound can make the masked sound just audible to the human ear, then that strength is the masking threshold [14].

3 Noise reduction algorithm

In this article, the spectral subtraction method is used to remove noise from the reverberant music, i.e., to remove the background noise mixed in the music signal [15].

3.1 The traditional spectrum subtraction method

The principle of removing noise from reverberant music by spectral subtraction is to set noise in the reverberant music that is not related to the music and then to subtract the noise from the reverberant music to get the de-reverberated music signal [16]. The process of reducing noise from the reverberant music with spectral subtraction is shown in Figure 1. The basic steps are as follows.

Figure 1 The process of de-reverberation and noise reduction of reverberant music by spectral subtraction based on the masking effect.
Figure 1

The process of de-reverberation and noise reduction of reverberant music by spectral subtraction based on the masking effect.

(1) The reverberant music signal Y ( n ) is processed by fast Fourier transform (FFT) [17] to obtain Y ( ω ) .

(2) The signal frames without pure music in the reverberant music signal are counted to obtain the estimated noise signal, and Fourier transform is also performed to obtain D ˆ ( ω ) .

(3) The reverberant music signal and the estimated noise signal are subtracted to obtain the de-reverberated music signal:

(1) X ˆ ( ω ) = ∣ Y ( ω ) ∣ 2 − ∣ D ˆ ( ω ) ∣ 2 ,

where X ˆ ( ω ) is the estimated value of the music signal after de-reverberation.

(4) After adding the phase information to X ˆ ( ω ) , the inverse FFT is performed to obtain the de-reverberated music signal X ( n ) . The phase signal comes from the original reverberant music signal. The reason why the phase of reverberant music signals containing noise is directly used is that the human ear is not sensitive to changes in the phase of music signals.

As mentioned in the aforementioned steps, it is the basic process of spectral subtraction method for de-reverberation of reverberant music. The spectral subtraction method is simple and convenient when de-reverberating the reverberant music signals, but musical noise is generated in the de-reverberated music [18]. The musical noise is generated because the noise signal subtracted from the reverberant music signal in the spectral subtraction method is not the real noise in the reverberant music, but the estimated noise mean value obtained by statistics. Therefore, when the estimated noise signal is subtracted from the reverberant music signal, the real noise signal in the reverberant music signal whose real noise amplitude is lower than the estimated noise mean will be removed substantially, while the real noise signal whose real noise amplitude is higher than the mean of the estimated noise will have more residuals. These residual noise signals tend to be clearer than the original noise, affecting the de-reverberation effect of the spectral subtraction method.

3.2 The improved spectrum subtraction method

To enhance the de-reverberation effect of the spectral subtraction method on reverberant music and strengthen the de-noising performance of the method, this article improves the spectral subtraction method by using the human ear masking effect. The complete flow of the improved spectral subtraction method is shown in Figure 1. The improved spectral subtraction method for reverberant music de-reverberation and noise reduction can be divided into two stages. The first stage is consistent with the basic spectral subtraction method, i.e., subtracting the estimated noise from the reverberant music to obtain the de-reverberated music signal. The second stage is the postprocessing of the de-reverberated music signal by using the human ear masking effect [19] to eliminate the musical noise in the de-reverberated music.

The basic steps of the second stage are as follows.

(5) Both the original reverberant music Y ( n ) and the de-reverberant music X ( n ) are processed by FFT to obtain Y ( ω ) and X ( ω ) .

(6) After normalizing Y ( ω ) and X ( ω ) , the energy difference is obtained by subtracting them and is expressed as follows:

(2) diff = 0 , X N ( ω ) − Y N ( ω ) < 0 , X N ( ω ) − Y N ( ω ) , X N ( ω ) − Y N ( ω ) ≥ 0 ,

where Y N ( ω ) and X N ( ω ) are the signals obtained by normalizing Y ( ω ) , and X ( ω ) and diff is the energy difference between X N ( ω ) and Y N ( ω ) .

(7) The masking factor is calculated based on the calculated energy difference diff and used to postprocess the de-reverberated music. The corresponding formula is:

(3) Mask = 1 1 − γ ⋅ diff , X m ( ω ) = X N ( ω ) ⋅ mask,

where mask is the masking factor used to postprocess the de-reverberated music, γ is the weighting factor whose value is adjusted according to the actual situation to achieve the best masking effect, and X m ( ω ) is the postprocessed de-reverberated music signal.

4 Simulation experiments

4.1 Experimental environment

In this study, the de-reverberation performance of spectral subtraction was simulated by MATLAB software [20]. The experiments were conducted on a laboratory server with relevant configurations of the Windows 7 operating system, 32G RAM, and Core i7 processor.

4.2 Experimental methods

The audio data used were all from the music information collected in the soundproof room: the testers sang the songs, and the music information samples were collected in the soundproof room under quiet conditions. Each sample was 10 s long, and a total of 50 samples were collected, with a sampling rate of 5,000 Hz. Then, samples were added with Gaussian white noise to obtain reverberant music signal samples.

After obtaining the reverberant music samples, they were de-reverberated and noise reduced using the traditional and improved spectral reduction methods, respectively. In this article, the signal-to-noise ratio method was used to objectively evaluate the performance of the two de-reverberation noise reduction algorithms. The signal-to-noise ratio is expressed as follows:

(4) SNR = 10 lg ∑ n s 2 ( n ) ∑ n ( s ( n ) − s ˆ ( n ) ) 2 ,

where s ( n ) is the pure music signal and s ˆ ( n ) is the music signal after de-reverberation. As the ultimate goal of various noise reduction algorithms in the actual use process is to eliminate or reduce the noise in the music signal so as to improve the listening quality of the music signal, no matter how excellent the objective signal-to-noise ratio is after denoising, it ultimately depends on the subjective perception of the human ear.

Therefore, in addition to objectively evaluating the de-reverberation noise reduction performance with the signal-to-noise ratio, this article also used the mean opinion score (MOS) method. In this study, five volunteers with good hearing were selected to evaluate the noise reduction performance of the two algorithms, and the samples before and after de-reverberation were played to the volunteers one by one. The volunteers scored the de-reverberated samples for one to five points.

The MOS method divided the quality of the processed music signal into five levels: five points meant excellent, four points meant good, three points meant moderate, two points meant poor, and one point meant bad. A score of five points meant that the human ear was not aware of the noise in the music; a score of four points meant that the human ear was slightly aware of the noise; a score of three points means that the human ear was aware of the noise and slightly disgusted with it; a score of two points means that the human ear was obviously aware of the noise, disgusted with it, but is tolerable. One point meant that the human ear could not tolerate the noise.

4.3 Experimental results

Due to the limitation of space, this article only shows the time domain waveform of the relevant music signal for 1 of the 50 samples, as shown in Figure 2. It contained the pure music signal, the reverberant music after adding Gaussian white noise, and de-reverberated music signals after being processed by the two spectral subtraction methods. Figure 2 shows that after adding Gaussian white noise, the time domain waveform of the sample was significantly interfered with compared with the pure music signal; after processing by the traditional spectral subtraction, the white noise part of the time domain waveform of the de-reverberated music signal was significantly converged, but the noise still remained compared with the pure music signal; in the music signal processed by the improved spectral subtraction method, the white noise part has been further removed so that it was much closer to the pure music signal.

Figure 2 The pure music signal, the music signal added with noise, and the music signals de-reverberated by the two spectral subtraction methods.
Figure 2

The pure music signal, the music signal added with noise, and the music signals de-reverberated by the two spectral subtraction methods.

The signal-to-noise ratio was used in this study to objectively evaluate the de-reverberation effects of the two spectral subtraction methods. Average signal-to-noise ratios of the 50 samples before the noise reduction and after being processed by the two spectral subtraction methods are shown in Figure 3. Figure 3 shows that the amount of noise that was removed by the improved spectral reduction method was greater than that removed by the traditional spectral reduction method, thus making the noise-reduced music signal closer to the pure music signal, the difference between them smaller, and the signal-to-noise ratio larger.

Figure 3 The average signal-to-noise ratio of the 50 samples before noise reduction and after being processed by the two spectral subtraction methods.
Figure 3

The average signal-to-noise ratio of the 50 samples before noise reduction and after being processed by the two spectral subtraction methods.

In this study, in addition to using the signal-to-noise ratio to objectively evaluate the noise reduction performance of the two spectral reduction methods, the MOS method was also used to subjectively evaluate the performance in terms of the actual human ear perception of the noised-reduced music. The average MOS of the 50 music samples after noise reduction using the traditional and improved spectral subtraction methods is shown in Figure 4. It was seen from the comparison in Figure 4 that the human ear was perceptible to the noise in the de-reverberated music processed by the traditional spectral subtraction method and slightly disgusted with it, but could tolerate it; the human ear was occasionally perceptible to the noise in the de-reverberated music processed by the improved spectral subtraction method.

Figure 4 The average MOS of music signals processed by the two spectral subtraction methods.
Figure 4

The average MOS of music signals processed by the two spectral subtraction methods.

5 Discussion

In the process of music signal acquisition, the mixed noise signal can affect the quality of music signals to varying degrees. Depending on the use of music signals, the processing also varies; however, the general rule is to reduce noise signals in music signals as much as possible to highlight music signals. This article used the spectral subtraction method for noise reduction of reverberant music. The noise reduction principle of the spectral subtraction method is to subtract noise signals from signals. In practical application, the first few frames without music signals are counted to estimate noise signals in music signals for the subsequent spectral subtraction processing.

The ideal state for noise reduction of reverberant music using traditional spectral subtraction is that the noise signal has been known, but in practice, the noise signal is not known and should be estimated from the first few frames that do not contain the music signal, which makes the noise reduction effect unsatisfactory. Hence, this article used the human ear masking effect to improve the quality of music signals after noise reduction. Then, a comparison experiment between the traditional spectral subtraction method and the improved spectral subtraction method was also conducted, and the results have been shown earlier. The time domain waveform of the signals after processed by the improved spectral subtraction method was closer to the original signal than the signals processed by the traditional spectral subtraction method, and the comparison of the signal-to-noise ratio before and after the processing also showed that the improved spectral subtraction method had better noise reduction performance. In terms of subjective scoring, the music signals processed by the improved spectral subtraction method had a higher score.

The reason for the aforementioned results is as follows. The traditional spectral subtraction method subtracts noise signals to achieve noise reduction, but in the actual noise reduction process, the noise signal mixed in the music signal is unknown, so the noise signal needs to be estimated. The estimated noise signal is based on statistical samples, which may be statistically consistent with the actual noise, but cannot be guaranteed to be identical to the actual noise. The traditional spectral subtraction method uses the estimated noise signal for noise reduction, which may cause damages to music signals or incomplete removal of noise signals. The improved spectral subtraction method uses the human ear masking effect to further reduce noise from the music signal after noise reduction by the traditional spectral subtraction method. After noise reduction based on the human ear masking effect, the noise is masked by the music signal in the perception range of human ears to highlight the original music signal objectively and subjectively and to achieve noise reduction.

6 Conclusion

This article briefly introduces noise, masking effects, and the spectral subtraction method for reducing noise in reverberant music. The spectral subtraction method was improved using the human ear masking effect to enhance its noise reduction effect. Moreover, simulation experiments were carried out on the traditional spectral subtraction method and the improved spectral subtraction method. The research results showed that the time domain waveform of the pure music signal added with noise was significantly interfered with; the noise was significantly reduced after using the traditional spectral subtraction method and further reduced after using the improved spectral subtraction method, and the latter was closest to the pure music signal; the signal-to-noise ratio of the music de-reverberated by the improved spectral subtraction method was higher than that of the music de-reverberated by the traditional spectral subtraction method, which meant that the improved spectral subtraction method had better de-reverberation and noise reduction effects objectively; the MOS of the music de-reverberated by the improved spectral subtraction method was higher.

  1. Conflict of interest: The authors state no conflict of interest.

References

[1] Kim HJ, Lee JH, Shim HJ. Effect of digital noise reduction of hearing aids on music and speech perception. J Audiol Otol. 2020;24(4):180–90.10.7874/jao.2020.00031Search in Google Scholar PubMed PubMed Central

[2] Kohlberg GD, Mancuso DM, Griffin BM, Spitzer JB, Lalwani AK. Impact of noise reduction algorithm in cochlear implant processing on music enjoyment. Otol Neurotol. 2015;37(5):492–8.10.1097/MAO.0000000000001041Search in Google Scholar PubMed

[3] Verbanck M, Josse J, Husson F. Regularised PCA to denoise and visualise data. Stat Comput. 2015;25(2):471–86.10.1007/s11222-013-9444-ySearch in Google Scholar

[4] Kohlberg GD, Mancuso DM, Griffin BM, Spitzer JB, Lalwani AK. Impact of noise reduction algorithm in cochlear implant processing on music enjoyment. Otol Neurotol. 2016;37(5):492.10.1097/MAO.0000000000001041Search in Google Scholar

[5] Deng SQ, Han JQ. Adaptive overlapping-group sparse denoising for heart sound signals. Biomed Signal Proces. 2018;40:49–57.10.1016/j.bspc.2017.08.027Search in Google Scholar

[6] Chen T, Shao SQ, Zheng SQ. Non-invasive diagnosis methods of coronary disease based on wavelet denoising and sound analyzing. Saudi J Biol Sci. 2017;24(3):526–36.10.1016/j.sjbs.2017.01.023Search in Google Scholar PubMed PubMed Central

[7] Fatemeh A, Antoine T, Marc T. Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process. Int J Adv Manuf Tech. 2018;98:3217–27.10.1007/s00170-018-2420-0Search in Google Scholar

[8] Makary MM, Bu-Omer HM, Soliman RS, Park K, Kadah YM. Spectral subtraction denoising preprocessing block to improve slow cortical potential based brain-computer interface. J Med Biol Eng. 2017;38(1):1–12.10.1007/s40846-017-0308-3Search in Google Scholar

[9] Kompella KCD, Rao MVG, Rao RS. Bearing fault detection in a 3 phase induction motor using stator current frequency spectral subtraction with various wavelet decomposition techniques. Ain Shams Eng J. 2018;9(4):2427–39.10.1016/j.asej.2017.06.002Search in Google Scholar

[10] Iglesias-Martínez ME, de Córdoba PF, Antonino-Daviu JA, Conejero JA. Detection of nonadjacent rotor faults in induction motors via spectral subtraction and autocorrelation of stray flux signals. IEEE T Ind Appl. 2019;55(5):4585–94.10.1109/TIA.2019.2917861Search in Google Scholar

[11] Upadhyay N, Karmakar A. Speech enhancement using spectral subtraction-type algorithms: a comparison and simulation study. Proc Comput Sci. 2015;54:574–84.10.1016/j.procs.2015.06.066Search in Google Scholar

[12] Simiele E, Kapsch RP, Ankerhold U, Culberson W, DeWerd LA. Spectral characterization of plastic scintillation detector response as a function of magnetic field strength. Phys Med Biol. 2018;63(8):085001.10.1088/1361-6560/aab56cSearch in Google Scholar PubMed

[13] Kokkinakis K, Runge C, Tahmina Q, Hu Y. Evaluation of a spectral subtraction strategy to suppress reverberant energy in cochlear implant devices. J Acoust Soc Am. 2015;138(1):115–24.10.1121/1.4922331Search in Google Scholar PubMed PubMed Central

[14] Zhao F, Wang J, Wang A. An improved spectral background subtraction method based on wavelet energy. Appl Spectrosc. 2016;2016:1994–2004.10.1177/0003702816665530Search in Google Scholar PubMed

[15] Kakihana M, Okamoto M. Application of spectral subtraction technique to solid samples of HCOONa and CH3COONa with small amounts of D-variants. Appl Spectrosc. 2016;38(1):66–7.10.1366/0003702844554468Search in Google Scholar

[16] Kepes E, Porizka P, Klus J, Modlitbová P, Kaiser J. Influence of baseline subtraction on laser-induced breakdown spectroscopic data. J Anal Atomic Spectrometry. 2018;33(12):2107–15.10.1039/C8JA00209FSearch in Google Scholar

[17] Martínez MEI, de Córdoba Castellá PF, Antonino-Daviu JA, Conejero A. Detection of adjacent and non-adjacent bar breakages in induction motors based on power spectral subtraction and second order statistics of sound signals. Appl Sci. 2020;10(19):6641.10.3390/app10196641Search in Google Scholar

[18] Dash TK, Solanki SS. Speech intelligibility based enhancement system using modified deep neural network and adaptive multi-band spectral subtraction. Wireless Pers Commun. 2020;111(2):1073–87.10.1007/s11277-019-06902-0Search in Google Scholar

[19] Haider NS. Respiratory sound denoising using empirical mode decomposition, hurst analysis and spectral subtraction. Biomed Signal Proces. 2021;64:102313.10.1016/j.bspc.2020.102313Search in Google Scholar

[20] Zhang QY, Li GL, Huang YB. An efficient retrieval approach for encrypted speech based on biological hashing and spectral subtraction. Multimed Tools Appl. 2020;79(21):728–40.10.1007/s11042-020-09446-9Search in Google Scholar
Received: 2021-10-14
Revised: 2021-12-01
Accepted: 2021-12-07
Published Online: 2022-04-01

© 2022 Shenghuan Zhang and Ye Cheng, published by De Gruyter

This work is licensed under the Creative Commons Attribution 4.0 International License.

Articles in the same Issue

  1. Research Articles
  2. Construction of 3D model of knee joint motion based on MRI image registration
  3. Evaluation of several initialization methods on arithmetic optimization algorithm performance
  4. Application of visual elements in product paper packaging design: An example of the “squirrel” pattern
  5. Deep learning approach to text analysis for human emotion detection from big data
  6. Cognitive prediction of obstacle's movement for reinforcement learning pedestrian interacting model
  7. The application of neural network algorithm and embedded system in computer distance teach system
  8. Machine translation of English speech: Comparison of multiple algorithms
  9. Automatic control of computer application data processing system based on artificial intelligence
  10. A secure framework for IoT-based smart climate agriculture system: Toward blockchain and edge computing
  11. Application of mining algorithm in personalized Internet marketing strategy in massive data environment
  12. On the correction of errors in English grammar by deep learning
  13. Research on intelligent interactive music information based on visualization technology
  14. Extractive summarization of Malayalam documents using latent Dirichlet allocation: An experience
  15. Conception and realization of an IoT-enabled deep CNN decision support system for automated arrhythmia classification
  16. Masking and noise reduction processing of music signals in reverberant music
  17. Cat swarm optimization algorithm based on the information interaction of subgroup and the top-N learning strategy
  18. State feedback based on grey wolf optimizer controller for two-wheeled self-balancing robot
  19. Research on an English translation method based on an improved transformer model
  20. Short-term prediction of parking availability in an open parking lot
  21. PUC: parallel mining of high-utility itemsets with load balancing on spark
  22. Image retrieval based on weighted nearest neighbor tag prediction
  23. A comparative study of different neural networks in predicting gross domestic product
  24. A study of an intelligent algorithm combining semantic environments for the translation of complex English sentences
  25. IoT-enabled edge computing model for smart irrigation system
  26. A study on automatic correction of English grammar errors based on deep learning
  27. A novel fingerprint recognition method based on a Siamese neural network
  28. A hidden Markov optimization model for processing and recognition of English speech feature signals
  29. Crime reporting and police controlling: Mobile and web-based approach for information-sharing in Iraq
  30. Convex optimization for additive noise reduction in quantitative complex object wave retrieval using compressive off-axis digital holographic imaging
  31. CRNet: Context feature and refined network for multi-person pose estimation
  32. Improving the efficiency of intrusion detection in information systems
  33. Research on reform and breakthrough of news, film, and television media based on artificial intelligence
  34. An optimized solution to the course scheduling problem in universities under an improved genetic algorithm
  35. An adaptive RNN algorithm to detect shilling attacks for online products in hybrid recommender system
  36. Computing the inverse of cardinal direction relations between regions
  37. Human-centered artificial intelligence-based ice hockey sports classification system with web 4.0
  38. Construction of an IoT customer operation analysis system based on big data analysis and human-centered artificial intelligence for web 4.0
  39. An improved Jaya optimization algorithm with ring topology and population size reduction
  40. Review Articles
  41. A review on voice pathology: Taxonomy, diagnosis, medical procedures and detection techniques, open challenges, limitations, and recommendations for future directions
  42. An extensive review of state-of-the-art transfer learning techniques used in medical imaging: Open issues and challenges
  43. Special Issue: Explainable Artificial Intelligence and Intelligent Systems in Analysis For Complex Problems and Systems
  44. Tree-based machine learning algorithms in the Internet of Things environment for multivariate flood status prediction
  45. Evaluating OADM network simulation and an overview based metropolitan application
  46. Radiography image analysis using cat swarm optimized deep belief networks
  47. Comparative analysis of blockchain technology to support digital transformation in ports and shipping
  48. IoT network security using autoencoder deep neural network and channel access algorithm
  49. Large-scale timetabling problems with adaptive tabu search
  50. Eurasian oystercatcher optimiser: New meta-heuristic algorithm
  51. Trip generation modeling for a selected sector in Baghdad city using the artificial neural network
  52. Trainable watershed-based model for cornea endothelial cell segmentation
  53. Hessenberg factorization and firework algorithms for optimized data hiding in digital images
  54. The application of an artificial neural network for 2D coordinate transformation
  55. A novel method to find the best path in SDN using firefly algorithm
  56. Systematic review for lung cancer detection and lung nodule classification: Taxonomy, challenges, and recommendation future works
  57. Special Issue on International Conference on Computing Communication & Informatics
  58. Edge detail enhancement algorithm for high-dynamic range images
  59. Suitability evaluation method of urban and rural spatial planning based on artificial intelligence
  60. Writing assistant scoring system for English second language learners based on machine learning
  61. Dynamic evaluation of college English writing ability based on AI technology
  62. Image denoising algorithm of social network based on multifeature fusion
  63. Automatic recognition method of installation errors of metallurgical machinery parts based on neural network
  64. An FCM clustering algorithm based on the identification of accounting statement whitewashing behavior in universities
  65. Emotional information transmission of color in image oil painting
  66. College music teaching and ideological and political education integration mode based on deep learning
  67. Behavior feature extraction method of college students’ social network in sports field based on clustering algorithm
  68. Evaluation model of multimedia-aided teaching effect of physical education course based on random forest algorithm
  69. Venture financing risk assessment and risk control algorithm for small and medium-sized enterprises in the era of big data
  70. Interactive 3D reconstruction method of fuzzy static images in social media
  71. The impact of public health emergency governance based on artificial intelligence
  72. Optimal loading method of multi type railway flatcars based on improved genetic algorithm
  73. Special Issue: Evolution of Smart Cities and Societies using Emerging Technologies
  74. Data mining applications in university information management system development
  75. Implementation of network information security monitoring system based on adaptive deep detection
  76. Face recognition algorithm based on stack denoising and self-encoding LBP
  77. Research on data mining method of network security situation awareness based on cloud computing
  78. Topology optimization of computer communication network based on improved genetic algorithm
  79. Implementation of the Spark technique in a matrix distributed computing algorithm
  80. Construction of a financial default risk prediction model based on the LightGBM algorithm
  81. Application of embedded Linux in the design of Internet of Things gateway
  82. Research on computer static software defect detection system based on big data technology
  83. Study on data mining method of network security situation perception based on cloud computing
  84. Modeling and PID control of quadrotor UAV based on machine learning
  85. Simulation design of automobile automatic clutch based on mechatronics
  86. Research on the application of search algorithm in computer communication network
  87. Special Issue: Artificial Intelligence based Techniques and Applications for Intelligent IoT Systems
  88. Personalized recommendation system based on social tags in the era of Internet of Things
  89. Supervision method of indoor construction engineering quality acceptance based on cloud computing
  90. Intelligent terminal security technology of power grid sensing layer based upon information entropy data mining
  91. Deep learning technology of Internet of Things Blockchain in distribution network faults
  92. Optimization of shared bike paths considering faulty vehicle recovery during dispatch
  93. The application of graphic language in animation visual guidance system under intelligent environment
  94. Iot-based power detection equipment management and control system
  95. Estimation and application of matrix eigenvalues based on deep neural network
  96. Brand image innovation design based on the era of 5G internet of things
  97. Special Issue: Cognitive Cyber-Physical System with Artificial Intelligence for Healthcare 4.0.
  98. Auxiliary diagnosis study of integrated electronic medical record text and CT images
  99. A hybrid particle swarm optimization with multi-objective clustering for dermatologic diseases diagnosis
  100. An efficient recurrent neural network with ensemble classifier-based weighted model for disease prediction
  101. Design of metaheuristic rough set-based feature selection and rule-based medical data classification model on MapReduce framework
https://doi.org/10.1515/jisys-2022-0024
Keywords for this article
reverberant music; musical noise; masking effect; spectral subtraction method
Creative Commons
BY 4.0

Articles in the same Issue

  1. Research Articles
  2. Construction of 3D model of knee joint motion based on MRI image registration
  3. Evaluation of several initialization methods on arithmetic optimization algorithm performance
  4. Application of visual elements in product paper packaging design: An example of the “squirrel” pattern
  5. Deep learning approach to text analysis for human emotion detection from big data
  6. Cognitive prediction of obstacle's movement for reinforcement learning pedestrian interacting model
  7. The application of neural network algorithm and embedded system in computer distance teach system
  8. Machine translation of English speech: Comparison of multiple algorithms
  9. Automatic control of computer application data processing system based on artificial intelligence
  10. A secure framework for IoT-based smart climate agriculture system: Toward blockchain and edge computing
  11. Application of mining algorithm in personalized Internet marketing strategy in massive data environment
  12. On the correction of errors in English grammar by deep learning
  13. Research on intelligent interactive music information based on visualization technology
  14. Extractive summarization of Malayalam documents using latent Dirichlet allocation: An experience
  15. Conception and realization of an IoT-enabled deep CNN decision support system for automated arrhythmia classification
  16. Masking and noise reduction processing of music signals in reverberant music
  17. Cat swarm optimization algorithm based on the information interaction of subgroup and the top-N learning strategy
  18. State feedback based on grey wolf optimizer controller for two-wheeled self-balancing robot
  19. Research on an English translation method based on an improved transformer model
  20. Short-term prediction of parking availability in an open parking lot
  21. PUC: parallel mining of high-utility itemsets with load balancing on spark
  22. Image retrieval based on weighted nearest neighbor tag prediction
  23. A comparative study of different neural networks in predicting gross domestic product
  24. A study of an intelligent algorithm combining semantic environments for the translation of complex English sentences
  25. IoT-enabled edge computing model for smart irrigation system
  26. A study on automatic correction of English grammar errors based on deep learning
  27. A novel fingerprint recognition method based on a Siamese neural network
  28. A hidden Markov optimization model for processing and recognition of English speech feature signals
  29. Crime reporting and police controlling: Mobile and web-based approach for information-sharing in Iraq
  30. Convex optimization for additive noise reduction in quantitative complex object wave retrieval using compressive off-axis digital holographic imaging
  31. CRNet: Context feature and refined network for multi-person pose estimation
  32. Improving the efficiency of intrusion detection in information systems
  33. Research on reform and breakthrough of news, film, and television media based on artificial intelligence
  34. An optimized solution to the course scheduling problem in universities under an improved genetic algorithm
  35. An adaptive RNN algorithm to detect shilling attacks for online products in hybrid recommender system
  36. Computing the inverse of cardinal direction relations between regions
  37. Human-centered artificial intelligence-based ice hockey sports classification system with web 4.0
  38. Construction of an IoT customer operation analysis system based on big data analysis and human-centered artificial intelligence for web 4.0
  39. An improved Jaya optimization algorithm with ring topology and population size reduction
  40. Review Articles
  41. A review on voice pathology: Taxonomy, diagnosis, medical procedures and detection techniques, open challenges, limitations, and recommendations for future directions
  42. An extensive review of state-of-the-art transfer learning techniques used in medical imaging: Open issues and challenges
  43. Special Issue: Explainable Artificial Intelligence and Intelligent Systems in Analysis For Complex Problems and Systems
  44. Tree-based machine learning algorithms in the Internet of Things environment for multivariate flood status prediction
  45. Evaluating OADM network simulation and an overview based metropolitan application
  46. Radiography image analysis using cat swarm optimized deep belief networks
  47. Comparative analysis of blockchain technology to support digital transformation in ports and shipping
  48. IoT network security using autoencoder deep neural network and channel access algorithm
  49. Large-scale timetabling problems with adaptive tabu search
  50. Eurasian oystercatcher optimiser: New meta-heuristic algorithm
  51. Trip generation modeling for a selected sector in Baghdad city using the artificial neural network
  52. Trainable watershed-based model for cornea endothelial cell segmentation
  53. Hessenberg factorization and firework algorithms for optimized data hiding in digital images
  54. The application of an artificial neural network for 2D coordinate transformation
  55. A novel method to find the best path in SDN using firefly algorithm
  56. Systematic review for lung cancer detection and lung nodule classification: Taxonomy, challenges, and recommendation future works
  57. Special Issue on International Conference on Computing Communication & Informatics
  58. Edge detail enhancement algorithm for high-dynamic range images
  59. Suitability evaluation method of urban and rural spatial planning based on artificial intelligence
  60. Writing assistant scoring system for English second language learners based on machine learning
  61. Dynamic evaluation of college English writing ability based on AI technology
  62. Image denoising algorithm of social network based on multifeature fusion
  63. Automatic recognition method of installation errors of metallurgical machinery parts based on neural network
  64. An FCM clustering algorithm based on the identification of accounting statement whitewashing behavior in universities
  65. Emotional information transmission of color in image oil painting
  66. College music teaching and ideological and political education integration mode based on deep learning
  67. Behavior feature extraction method of college students’ social network in sports field based on clustering algorithm
  68. Evaluation model of multimedia-aided teaching effect of physical education course based on random forest algorithm
  69. Venture financing risk assessment and risk control algorithm for small and medium-sized enterprises in the era of big data
  70. Interactive 3D reconstruction method of fuzzy static images in social media
  71. The impact of public health emergency governance based on artificial intelligence
  72. Optimal loading method of multi type railway flatcars based on improved genetic algorithm
  73. Special Issue: Evolution of Smart Cities and Societies using Emerging Technologies
  74. Data mining applications in university information management system development
  75. Implementation of network information security monitoring system based on adaptive deep detection
  76. Face recognition algorithm based on stack denoising and self-encoding LBP
  77. Research on data mining method of network security situation awareness based on cloud computing
  78. Topology optimization of computer communication network based on improved genetic algorithm
  79. Implementation of the Spark technique in a matrix distributed computing algorithm
  80. Construction of a financial default risk prediction model based on the LightGBM algorithm
  81. Application of embedded Linux in the design of Internet of Things gateway
  82. Research on computer static software defect detection system based on big data technology
  83. Study on data mining method of network security situation perception based on cloud computing
  84. Modeling and PID control of quadrotor UAV based on machine learning
  85. Simulation design of automobile automatic clutch based on mechatronics
  86. Research on the application of search algorithm in computer communication network
  87. Special Issue: Artificial Intelligence based Techniques and Applications for Intelligent IoT Systems
  88. Personalized recommendation system based on social tags in the era of Internet of Things
  89. Supervision method of indoor construction engineering quality acceptance based on cloud computing
  90. Intelligent terminal security technology of power grid sensing layer based upon information entropy data mining
  91. Deep learning technology of Internet of Things Blockchain in distribution network faults
  92. Optimization of shared bike paths considering faulty vehicle recovery during dispatch
  93. The application of graphic language in animation visual guidance system under intelligent environment
  94. Iot-based power detection equipment management and control system
  95. Estimation and application of matrix eigenvalues based on deep neural network
  96. Brand image innovation design based on the era of 5G internet of things
  97. Special Issue: Cognitive Cyber-Physical System with Artificial Intelligence for Healthcare 4.0.
  98. Auxiliary diagnosis study of integrated electronic medical record text and CT images
  99. A hybrid particle swarm optimization with multi-objective clustering for dermatologic diseases diagnosis
  100. An efficient recurrent neural network with ensemble classifier-based weighted model for disease prediction
  101. Design of metaheuristic rough set-based feature selection and rule-based medical data classification model on MapReduce framework
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 13.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/jisys-2022-0024/html
Scroll to top button