3. Assessment and intelligibility modification for dysarthric speech
-
P. Vijayalakshmi
Abstract
Dysarthria is a motor speech disorder that is often associated with irregular phonation and amplitude, incoordination and restricted movement of articulators. This condition is caused by cerebral palsy, degenerative neurological disease and so on. The pattern of speech impairment can be determined by the amount of compromise detected in the muscle groups. That is, the dysarthrias have global effect rather than focal effects on speech production systems of phonation, articulation and resonance. Clinically, assessment of dysarthria is carried out using perceptual judgment by experienced listeners. One of the limitations of perceptual assessment is that it can be difficult even for highly trained listeners to differentiate the multiple dimensions of dysarthric speech, as dysarthria has multisystem dysregulation. Although many researchers are involved in developing assistive devices, acoustic analyses are carried out on each of the subsystems independent of each other. As dysarthria affects the speech system globally, a multidimensional approach is required for the assessment and an associated intelligibility improvement system to develop an assistive device. This chapter will describe the significance and methods to develop a detection and assessment system by analyzing the problems related to laryngeal, velopharyngeal and articulatory subsystems for dysarthric speakers, using a speech recognition system and relevant signal-processing-based techniques. The observations from the assessment system are used to correct and resynthesize the dysarthric speech, conserving the speaker’s identity, thereby improving the intelligibility. The complete system can detect the multisystem dysregulation in dysarthria, correct the text and resynthesize the speech, thus improving the lifestyle of the dysarthric speaker by giving them the freedom to communicate easily with the society without any human assistance.
Abstract
Dysarthria is a motor speech disorder that is often associated with irregular phonation and amplitude, incoordination and restricted movement of articulators. This condition is caused by cerebral palsy, degenerative neurological disease and so on. The pattern of speech impairment can be determined by the amount of compromise detected in the muscle groups. That is, the dysarthrias have global effect rather than focal effects on speech production systems of phonation, articulation and resonance. Clinically, assessment of dysarthria is carried out using perceptual judgment by experienced listeners. One of the limitations of perceptual assessment is that it can be difficult even for highly trained listeners to differentiate the multiple dimensions of dysarthric speech, as dysarthria has multisystem dysregulation. Although many researchers are involved in developing assistive devices, acoustic analyses are carried out on each of the subsystems independent of each other. As dysarthria affects the speech system globally, a multidimensional approach is required for the assessment and an associated intelligibility improvement system to develop an assistive device. This chapter will describe the significance and methods to develop a detection and assessment system by analyzing the problems related to laryngeal, velopharyngeal and articulatory subsystems for dysarthric speakers, using a speech recognition system and relevant signal-processing-based techniques. The observations from the assessment system are used to correct and resynthesize the dysarthric speech, conserving the speaker’s identity, thereby improving the intelligibility. The complete system can detect the multisystem dysregulation in dysarthria, correct the text and resynthesize the speech, thus improving the lifestyle of the dysarthric speaker by giving them the freedom to communicate easily with the society without any human assistance.
Chapters in this book
- Frontmatter I
- Foreword V
- Acknowledgments IX
- Contents XI
- List of contributors XIII
- Introduction 1
-
Part I: Comparative analysis of methods for speaker identification, speech recognition, and intelligibility modification in the dysarthric speaker population
- 1. State-of-the-art speaker recognition methods applied to speakers with dysarthria 7
- 2. Enhancement of continuous dysarthric speech 35
- 3. Assessment and intelligibility modification for dysarthric speech 67
-
Part II: New approaches to speech reconstruction and enhancement via conversion of non-acoustic signals
- 4. Analysis and quality conversion of nonacoustic signals: the physiological microphone (PMIC) 97
- 5. Non-audible murmur to audible speech conversion 125
-
Part III: Use of novel speech diagnostic and therapeutic intervention software for speech enhancement and rehabilitation
- 6. Application of speech signal processing for assessment and treatment of voice and speech disorders 153
- 7. A mobile phone-based platform for asynchronous speech therapy 195
Chapters in this book
- Frontmatter I
- Foreword V
- Acknowledgments IX
- Contents XI
- List of contributors XIII
- Introduction 1
-
Part I: Comparative analysis of methods for speaker identification, speech recognition, and intelligibility modification in the dysarthric speaker population
- 1. State-of-the-art speaker recognition methods applied to speakers with dysarthria 7
- 2. Enhancement of continuous dysarthric speech 35
- 3. Assessment and intelligibility modification for dysarthric speech 67
-
Part II: New approaches to speech reconstruction and enhancement via conversion of non-acoustic signals
- 4. Analysis and quality conversion of nonacoustic signals: the physiological microphone (PMIC) 97
- 5. Non-audible murmur to audible speech conversion 125
-
Part III: Use of novel speech diagnostic and therapeutic intervention software for speech enhancement and rehabilitation
- 6. Application of speech signal processing for assessment and treatment of voice and speech disorders 153
- 7. A mobile phone-based platform for asynchronous speech therapy 195
