๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Statistical methods in multi-speaker automatic speech recognition

โœ Scribed by Boyer, A. ;Di Martino, J. ;Divoux, P. ;Haton, J. P. ;Mari, J. F. ;Smaili, K.

Publisher
John Wiley and Sons
Year
1990
Tongue
English
Weight
632 KB
Volume
6
Category
Article
ISSN
8755-0024

No coin nor oath required. For personal study only.

โœฆ Synopsis

Automatic speech recognition and understanding (ASR) plays an important role in the framework of man-machine communication. Substantial industrial developments are at present in progress in this area. Hotteker, after 40 years or so of efforts several fundamental questions remain open. This paper is concerned with a comparative study of four different methods for multi-speaker word recognition: (i) clustering of acoustic templates, (ii) comparison with a finite state automaton, (iii) dynamic programming and vector quantization, (iv) stochastic Markov sources. In order to make things comparable, the four methods were tested with the same material made up of the ten digits (0 to 9) pronounced four times by 60 different speakers (30 males and 30 females). We will distinguish in our experiments between multispeaker systems (capable of recognizing words pronounced by speakers that have been used during the training phase of the system) and speaker-independent systems (capable of recognizing words pronounced by speakers totally unknown to the system). Half of the corpus (15 male and 15 female) were used for training, and the remaining part for test. hEI \ ORDS Automatic speech recognition Multi-speaker Markov models Dynamic programming Clustering

๐Ÿ“œ SIMILAR VOLUMES

Predictive speaker adaptation in speech
Predictive speaker adaptation in speech recognition
โœ Stephen Cox ๐Ÿ“‚ Article ๐Ÿ“… 1995 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 172 KB

A major problem with most speaker adaptation schemes is that they rely on the speaker providing at least one example of each acoustic unit (word, phone, triphone, etc.) in the vocabulary in order to adapt the appropriate model. Rapid adaptation is difficult to achieve and some sounds may never be ad

Modelling error recovery and repair in a
Modelling error recovery and repair in automatic speech recognition
โœ C. Baber; K.S. Hone ๐Ÿ“‚ Article ๐Ÿ“… 1993 ๐Ÿ› Elsevier Science โš– 682 KB

While automatic speech recognition (ASR) has achieved some level of success, it often fails to live up to its hype. One of the principal reasons for this apparent failure is the prevalence of "recognition errors". This makes error correction a topic of increasing importance to ASR system development

Automatic selection of phonetically dist
Automatic selection of phonetically distributed sentence sets for speaker adaptation with application to large vocabulary Mandarin speech recognition
โœ Jia-lin Shen; Hsin-min Wang; Ren-yuan Lyu; Lin-shan Lee ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 163 KB

This paper presents an approach of automatic selection of phonetically distributed sentence sets for speaker adaptation, and applies the concept to the task of Mandarin speech recognition with very large vocabulary. This is a different approach to the adaptation data selection problem. A computer al

Comparing Multi-layer Perceptrons and Ra
Comparing Multi-layer Perceptrons and Radial Basis Functions networks in speaker recognition
โœ M.W. Mak; W.G. Allen; G.G. Sexton ๐Ÿ“‚ Article ๐Ÿ“… 1993 ๐Ÿ› Elsevier Science โš– 443 KB

We have compared the performance of Multi-layer Perceptrons networks (MLP) and Radial Basis Function networks (RBF) in the task of speaker identification. The experiments are carried out on 400 utterances ( 10 digits, in English) from 10 speakers. LPC-derived Cepstrum Coefficients are used as the sp