Modern Methods of Speech Processing

ISBN-13: 9781461359623 / Angielski / Miękka / 2012 / 470 str.

Ravi P. Ramachandran; Richard Mammone

Opis

The term speech processing refers to the scientific discipline concerned with the analysis and processing of speech signals for getting the best benefit in various practical scenarios. These different practical scenarios correspond to a large variety of applications of speech processing research. Examples of some applications include enhancement, coding, synthesis, recognition and speaker recognition. A very rapid growth, particularly during the past ten years, has resulted due to the efforts of many leading scientists. The ideal aim is to develop algorithms for a certain task that maximize performance, are computationally feasible and are robust to a wide class of conditions. The purpose of this book is to provide a cohesive collection of articles that describe recent advances in various branches of speech processing. The main focus is in describing specific research directions through a detailed analysis and review of both the theoretical and practical settings. The intended audience includes graduate students who are embarking on speech research as well as the experienced researcher already working in the field. For graduate students taking a course, this book serves as a supplement to the course material. As the student focuses on a particular topic, the corresponding set of articles in this book will serve as an initiation through exposure to research issues and by providing an extensive reference list to commence a literature survey. Expe- rienced researchers can utilize this book as a reference guide and can expand their horizons in this rather broad area.

Spis treści

Contributors. Preface. Part 1: Speech Coding. 1. The use of pitch prediction in speech coding; R.P. Ramachandran. 2. Vector quantization of linear predictor coefficients; J.S. Collura. 3. Linear predictive analysis by synthesis coding; P. Kroon, W.B. Kleijn. 4. Waveform interpolation; J. Haggen, W.B. Kleijn. 5. Variable rate speech coding; V. Cuperman, P. Lupini. Part 2: Speech Recognition. 6. Word spotting; J.R. Rohlicek. 7. Speech recognition using neural networks; S.V. Kosonocky. 8. Current methods in continuous speech recognition; P.S. Gopalakrishnan. 9. Large vocabulary isolated word recognition; V. Gupta, M. Lennig. 10. Recent developments in robust speech recognition; B.H. Juang. 11. How do humans process and recognize speech? J.B. Allen. Part 3: Speaker Recognition. 12. Data fusion techniques for speaker recognition; K.R. Farrell, R.J. Mammone. 13. Speaker recognition over telephone channels; Y.-H. Kao, et al. Part 4: Text to speech synthesis. 14. Approaches to improve automatic speech synthesis; D. O'Shaughnessy. Part 5: Applications of Models. 15. Microphone array for hands-free voice communication in a car; S. Oh, V. Viswanathan. 16. The pitch mode modulation model and its application in speech processing; O. Ghitza. 17. Auditory models and human performance in tasks related to speech coding and speech recognition; O. Ghitza. 18. Applications of wavelets to speech processing: a case study of a Celp coder; J. Ooi, V. Viswanathan. Index.