✦ LIBER ✦

Predictor codebook for speaker-independent speech recognition

✍ Scribed by Takeshi Kawabata

Book ID: 104591609
Publisher: John Wiley and Sons
Year: 1994
Tongue: English
Weight: 752 KB
Volume: 25
Category: Article
ISSN: 0882-1666
DOI: 10.1002/scj.4690250103

No coin nor oath required. For personal study only.

✦ Synopsis

Abstract

This paper discusses a method to handle the diversified dynamic features of speech by representing the dynamic features of speech by spectrum predictors and constructing the codebook containing predictors as the elements. The effectiveness of the method for speaker‐independent speech recognition is examined. Three kinds of predictor structures, i.e., the forward predictor, the backward predictor and the interpolator, are examined. The predictor codebook is constructed by the predictor quantization procedure, which is a small modification of the LBG algorithm. For the evaluation of the phoneme recognition level, two kinds statistical evaluation quantities and the phoneme recognition rate have been considered. It is seen as a result that the predictor codebook can realize a high phoneme separation capability and the robustness against the speaker variation. By combining the process actually into the phrase recognition system, the performance at the continuous speech recognition level is evaluated. In either case, the codebook with the backward predictor as the elements exhibited the highest performance.

📜 SIMILAR VOLUMES

Speaker-independent speech recognition b

Speaker-independent speech recognition based on tree-structured speaker clustering

✍ Tetsuo Kosaka; Shoichi Matsunaga; Shigeki Sagayama 📂 Article 📅 1996 🏛 Elsevier Science 🌐 English ⚖ 231 KB

We have already proposed the application of tree-structured speaker clustering to supervised speaker adaptation. This paper proposes its application to unsupervised speaker adaptation and speakerindependent (SI) speech recognition. This clustering involves the selection of a speaker cluster from amo

On large-vocabulary speaker-independent

On large-vocabulary speaker-independent continuous speech recognition

✍ Kai-Fu Lee 📂 Article 📅 1988 🏛 Elsevier Science 🌐 English ⚖ 470 KB

A speaker-independent word recognition b

A speaker-independent word recognition based on HMM using orthogonalized phonetic segment codebook

✍ Hiroshi Matsuura; Tsuneo Nitta 📂 Article 📅 1994 🏛 John Wiley and Sons 🌐 English ⚖ 833 KB

## Abstract Matrix quantization (MQ) is a method which directly quantizes the spectrum‐time pattern. However, it has a problem in that the quantization error is relatively large compared to the vector quantization (VQ), since the dimension is large and the pattern variation is less. From such a vi

A new approach for text-independent spea

A new approach for text-independent speaker recognition

✍ Shung-Yung Lung; Chih-Chien Thomas Chen 📂 Article 📅 2000 🏛 Elsevier Science 🌐 English ⚖ 76 KB

Speaker adaptation techniques for speech

Speaker adaptation techniques for speech recognition using probabilistic models

✍ Koichi Shinoda 📂 Article 📅 2005 🏛 John Wiley and Sons 🌐 English ⚖ 353 KB

N-Best-based unsupervised speaker adapta

N-Best-based unsupervised speaker adaptation for speech recognition

✍ Tomoko Matsui; Sadaoki Furui 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 251 KB

This paper proposes an instantaneous speaker adaptation method that uses N-best decoding for continuous mixture-density hidden-Markovmodel-based speech-recognition systems. This method is effective even for speakers whose decoding using speaker-independent (SI) models are error-prone and for whom sp