Proceedings ArticleDOI
Speaker-independent isolated word recognition for telephone voice using phoneme-like templates
T. Nomura,R. Nakatsu +1 more
- Vol. 11, pp 2687-2690
Reads0
Chats0
TLDR
This paper describes a speaker-independent isolated word recognition algorithm for telephone voice and its recognition performance, which consists of dynamic time warping and statistical word discrimination.Abstract:
This paper describes a speaker-independent isolated word recognition algorithm for telephone voice and its recognition performance. The recognition algorithm consists of two processes ; dynamic time warping and statistical word discrimination. In the first process, input speech is compared with each word template using the dynamic time warping technique. Multiple word templates are used to deal with speech variations among speakers, where each word template is represented by a sequence of phoneme-like templates. To attain high recognition ability, a new technique for generating word templates is proposed. In the second process, statistical word discrimination is carried out for word candidates which have relatively low reliability in the first process. Discrimination functions are calculated based on statistics of transition tendencies of speech characteristics between adjacent frames, and the final word decision is made. The system was trained using utterances from 1305 speakers and tested with utterances from 259 speakers. The average recognition rate of 96.5% was obtained for a 16-word Japanese vocabulary set.read more
Citations
More filters
Journal ArticleDOI
Anser: an application of speech technology to the Japanese banking industry
TL;DR: A system called Anser, which combines speech recognition and synthesis to offer telephone banking services to millions of customers, is described and potential applications are indicated.
Journal ArticleDOI
Interactive voice technology development for telecommunications applications
TL;DR: A recently developed speech recognition server which includes a vocabulary-flexible recognition function is described, and a rule-based synthesis method applicable to the Japanese language is proposed, aiming to produce high quality speech.
Journal Article
Emergency Voice/Stress-Level Combined Recognition for Intelligent House Applications
Konstantinos Drosos,Andreas Floros,Kyriakos Agavanakis,Nicolas-Alexander Tatlas,Nikolaos-Grigorios Kanellopoulos +4 more
TL;DR: The implementation of a system, capable to react to common spoken words, taking into account the estimated vocal stress level, is introduced, allowing the realization of a prioritized, affective aural interaction path.
Proceedings ArticleDOI
Speaker-independent isolated-word recognition LSI
TL;DR: The architecture of a newly designed LSI for speaker-independent speech recognition based on a vector quantization technique and a dynamic time-warping technique using multiple word templates is described, which can be easily constructed on single board.
Patent
Voice recognition method using neuronal network - involves recognising pronounce words by comparison with words in reference vocabulary using sub-vocabulary for acoustic word reference
TL;DR: In this paper, a word spoken into a microphone is sent as numeric signal and transformed into acoustic wave patterns, which are then compared with data characteristic of predetermined reference words, and if the word does not fit one of the identifiers then it is retransmitted through the circuit to output (S1) of the recognition system.
References
More filters
Journal ArticleDOI
An Algorithm for Vector Quantizer Design
Y. Linde,A. Buzo,Robert M. Gray +2 more
TL;DR: An efficient and intuitive algorithm is presented for the design of vector quantizers based either on a known probabilistic model or on a long training sequence of data.
Journal ArticleDOI
Interactive clustering techniques for selecting speaker-independent reference templates for isolated word recognition
TL;DR: It is demonstrated that clustering can be a powerful tool for selecting reference templates for speaker-independent word recognition by identifying coarse structure, fine structure, overlap of, and outliers from clusters.
Proceedings ArticleDOI
Isolated word recognition using phoneme-like templates
TL;DR: New technique for use in a word recognition system where word templates are represented as sequences of descrete phoneme-like (pseudo-phoneme) templates which are automatically determined from a training set of word utterances by a clustering technique.
Journal ArticleDOI
Speaker‐independent isolated word recognition based on multiple templates using split method
TL;DR: A speaker-independent word recognition based on multiple word templates is described using the SPLIT method and the effectiveness of this system was verified via several experiments using telephone switch.
Related Papers (5)
Phoneme and word based model for tamil speech recognition using GMM-HMM
S. Karpagavalli,E. Chandra +1 more