Home Linguistics & Semiotics Chapter 9. Cross-linguistic comparison of automatic detection of speech breaks in read and narrated speech in four languages
Chapter
Licensed
Unlicensed Requires Authentication

Chapter 9. Cross-linguistic comparison of automatic detection of speech breaks in read and narrated speech in four languages

  • Plínio A. Barbosa
View more publications by John Benjamins Publishing Company
Search
In Search of Basic Units of Spoken Language
This chapter is in the book In Search of Basic Units of Spoken Language

Abstract

This chapter tests an algorithm for the automatic detection of speech breaks in read and narrated speech in Brazilian Portuguese (BP), European Portuguese (EP), French, and German. The algorithm is independent of previous transcription or linguistic analysis (syllable, phone labeling and segmentation), requiring only the audio file. It operates in two stages: vowel onsets detection firstly, followed by V-to-V duration intervals normalization for smoothed duration z-scores. Peaks over 2.5 of the latter were considered speech breaks. Compared to human segmentation, hits for reading (70%) were higher than for narration (60%). Crosslinguistic results show EP and French having the highest proportion of hits. A test with the English Navy audio file reveals a hit proportion similar to German.

Abstract

This chapter tests an algorithm for the automatic detection of speech breaks in read and narrated speech in Brazilian Portuguese (BP), European Portuguese (EP), French, and German. The algorithm is independent of previous transcription or linguistic analysis (syllable, phone labeling and segmentation), requiring only the audio file. It operates in two stages: vowel onsets detection firstly, followed by V-to-V duration intervals normalization for smoothed duration z-scores. Peaks over 2.5 of the latter were considered speech breaks. Compared to human segmentation, hits for reading (70%) were higher than for narration (60%). Crosslinguistic results show EP and French having the highest proportion of hits. A test with the English Navy audio file reveals a hit proportion similar to German.

Chapters in this book

  1. Prelim pages i
  2. Table of contents vii
  3. Acknowledgments xi
  4. Introduction. In search of a basic unit of spoken language 1
  5. Part I
  6. Chapter 1. Russian spoken discourse 35
  7. Chapter 2. The basic unit of spoken language and the interfaces between prosody, discourse and syntax 77
  8. Chapter 3. Prosody and the organization of information in Central Pomo, a California indigenous language 107
  9. Chapter 4. Syntactic and prosodic segmentation in spoken French 127
  10. Chapter 5. Design and annotation of two-level utterance units in Japanese 155
  11. Chapter 6. The pragmatic analysis of speech and its illocutionary classification according to the Language into Act Theory 181
  12. Chapter 7. Illocution as a unit of reference for spontaneous speech 221
  13. Chapter 8. Narrative discourse segmentation in clinical linguistics 257
  14. Chapter 9. Cross-linguistic comparison of automatic detection of speech breaks in read and narrated speech in four languages 285
  15. Part II
  16. Same texts, different approaches to segmentation 303
  17. Chapter 1. Segmentation and analysis of the two English excerpts 309
  18. Chapter 2. Analysis of two English spontaneous speech examples with the dependency incremental prosodic structure model 327
  19. Chapter 3. Applying criteria of spontaneous Hebrew speech segmentation to English 337
  20. Chapter 4. Basic units of speech segmentation 349
  21. Chapter 5. Segmentation of the English texts Navy and Hearts with SUU and LUU 359
  22. Chapter 6. The Moscow approach to local discourse structure 367
  23. Chapter 7. Some notes on the Hearts and Navy excerpts according to the Language into Act Theory 383
  24. Chapter 8. Comparing annotations for the prosodic segmentation of spontaneous speech 403
  25. Index 433
https://doi.org/10.1075/scl.94.09bar

Chapters in this book

  1. Prelim pages i
  2. Table of contents vii
  3. Acknowledgments xi
  4. Introduction. In search of a basic unit of spoken language 1
  5. Part I
  6. Chapter 1. Russian spoken discourse 35
  7. Chapter 2. The basic unit of spoken language and the interfaces between prosody, discourse and syntax 77
  8. Chapter 3. Prosody and the organization of information in Central Pomo, a California indigenous language 107
  9. Chapter 4. Syntactic and prosodic segmentation in spoken French 127
  10. Chapter 5. Design and annotation of two-level utterance units in Japanese 155
  11. Chapter 6. The pragmatic analysis of speech and its illocutionary classification according to the Language into Act Theory 181
  12. Chapter 7. Illocution as a unit of reference for spontaneous speech 221
  13. Chapter 8. Narrative discourse segmentation in clinical linguistics 257
  14. Chapter 9. Cross-linguistic comparison of automatic detection of speech breaks in read and narrated speech in four languages 285
  15. Part II
  16. Same texts, different approaches to segmentation 303
  17. Chapter 1. Segmentation and analysis of the two English excerpts 309
  18. Chapter 2. Analysis of two English spontaneous speech examples with the dependency incremental prosodic structure model 327
  19. Chapter 3. Applying criteria of spontaneous Hebrew speech segmentation to English 337
  20. Chapter 4. Basic units of speech segmentation 349
  21. Chapter 5. Segmentation of the English texts Navy and Hearts with SUU and LUU 359
  22. Chapter 6. The Moscow approach to local discourse structure 367
  23. Chapter 7. Some notes on the Hearts and Navy excerpts according to the Language into Act Theory 383
  24. Chapter 8. Comparing annotations for the prosodic segmentation of spontaneous speech 403
  25. Index 433
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 10.9.2025 from https://www.degruyterbrill.com/document/doi/10.1075/scl.94.09bar/html
Scroll to top button