Proceedings ArticleDOI
Isolated word recognition based on finite-state vector quantization
Reads0
Chats0
TLDR
An isolated word recognition system based on the finite-state vector quantization (FSVQ) method is proposed that requires far less search time, and needs no segmentation of input speech, yet yields comparable recognition accuracies.Abstract:
In this paper, we propose an isolated word recognition system based on the finite-state vector quantization (FSVQ) method. The recognition system can be viewed as a finite state machine composed of a codebook and next-state functions. As compared to an isolated word recognition system that uses the conventional memoryless vector quantization, the proposed system requires far less search time, and needs no segmentation of input speech, yet yields comparable recognition accuracies. For the design of next-state functions, two techniques, that is, the conditional histogram and omniscient design methods, are used, and their performances are compared in recognition of the ten Korean digits.read more
Citations
More filters
Journal ArticleDOI
A combined self-organizing feature map and multilayer perceptron for isolated word recognition
TL;DR: A neural network system which combines a self-organizing feature map and multilayer perception for the problem of isolated word speech recognition is presented, and an efficient adaptive nearby-search coding method based on the 'locality' of theSelf-organization is designed.
Journal ArticleDOI
Spellmode recognition based on vector quantization
Shan-shan Huang,Robert M. Gray +1 more
TL;DR: A Markov-modelling Spellmode recognizer is described which uses LPC-VQ as a front-end for analog to digital conversion and data compression and it suffers from high computational cost.
Proceedings ArticleDOI
Conditional histogram vector quantization for spellmode recognizer
Shan-shan Huang,Robert M. Gray +1 more
TL;DR: A conditional histogram technique is described which incorporates temporal information by considering the relative likelihoods that certain codewords follow others and produces better decoding results than the simple VQ algorithm with similar complexity.
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 Article
Vector quantization
TL;DR: During the past few years several design algorithms have been developed for a variety of vector quantizers and the performance of these codes has been studied for speech waveforms, speech linear predictive parameter vectors, images, and several simulated random processes.
Journal ArticleDOI
Distortion measures for speech processing
TL;DR: It is argued that the Itakura-Saito and related distortions are well-suited computationally, mathematically, and intuitively for such applications.
Journal ArticleDOI
On the application of vector quantization and hidden Markov models to speaker-independent, isolated word recognition
TL;DR: This paper presents an approach to speaker-independent, isolated word recognition in which the well-known techniques of vector quantization and hidden Markov modeling are combined with a linear predictive coding analysis front end in the framework of a standard statistical pattern recognition model.
Journal ArticleDOI
Algorithm for determining the endpoints of isolated utterances
Lawrence R. Rabiner,M. Sambur +1 more
TL;DR: In this article, the authors proposed an algorithm for locating the endpoints of an utterance based on two measures of the signal, namely, zero crossing rate and energy, which is inherently capable of performing correctly in any reasonable acoustic environment where the signalto-noise ratio is on the order of 30 Db or better.
Related Papers (5)
Segmentation in isolated word recognition using vector quantization
M. Bush,G. Kopec,N. Lauritzen +2 more
Speaker-independent isolated word recognition using label histograms
Osaaki Watanuki,T. Kaneko +1 more