Results 251 to 260 of about 545,718 (303)

Biomimetic Pattern Recognition for Speaker-Independent Speech Recognition

2005 International Conference on Neural Networks and Brain, 2006
In speaker-independent speech recognition, the disadvantage of the most diffused technology (hidden Markov models) is not only the need of many more training samples, but also long train time requirement. This paper describes the use of biomimetic pattern recognition (BPR) in recognizing some Mandarin speech in a speaker-independent manner.
null Hong Qin, null Shoujue Wang, null Hua Sun   +2 more
openaire   +1 more source

Speech perception as pattern recognition

The Journal of the Acoustical Society of America, 1995
This work provides theoretical and empirical arguments in favor of an approach to phonetics that is called double-weak. It is so called because it assumes relatively weak constraints both on the articulatory gestures and on the auditory patterns that map phonological elements.
openaire   +2 more sources

Dynamic speech recognition pattern switching for enhanced speech recognition accuracy

The Journal of the Acoustical Society of America, 2004
A speech recognition system and method that dynamically switches between reference patterns based on training information produced under different ambient noise levels to enhance speech recognition accuracy, is presented herein. In accordance with an embodiment of the invention, the speech recognition system includes a speech capturing device ...
openaire   +1 more source

PATTERN RECOGNITION APPROACHES FOR SPEECH-TO-SPEECH TRANSLATION

Cybernetics and Systems, 2004
We propose a statistical approach to speech-to-speech translation that uses finite-state models in all levels. Acoustic hidden Markov models (HMMs) model the pronunciation of the input-language phonemes and words, while the input–output word mapping, along with the syntax of the output language, are jointly modeled by means a large stochastic finite ...
FRANCISCO CASACUBERTA, ENRIQUE VIDAL, ALBERTO SANCHIS, JUAN-MIGUEL VILAR   +3 more
openaire   +1 more source

A MINIMUM ERROR RATE PATTERN RECOGNITION APPROACH TO SPEECH RECOGNITION

International Journal of Pattern Recognition and Artificial Intelligence, 1994
In this paper, a minimum error rate pattern recognition approach to speech recognition is studied with particular emphasis on the speech recognizer designs based on hidden Markov models (HMMs) and Viterbi decoding. This approach differs from the traditional maximum likelihood based approach in that the objective of the recognition error rate ...
W. CHOU, C.-H. LEE, B.-H. JUANG, F.K. SOONG   +3 more
openaire   +1 more source

Recognition of speech from temporal patterns

The Journal of the Acoustical Society of America, 1999
Spectrum of short segments of speech signal is accepted as one of the prime acoustic correlates of phonetic quality and it forms the basis of most current feature representations of speech. However, the short-term spectral vectors are affected by coarticulation. The coarticulation can span time intervals of several phonemes.
Sangita Sharma, Hynek Hermansky
openaire   +1 more source

Pattern Recognition Techniques for Speech Recognition

1980
This is an overview of techniques which have been developed for automatic pattern recognition, with an indication of their relevance to automatic speech recognition. The first part is concerned with data transformations, distance measures, cluster analysis and other aspects of what could be called ‘classic’ mathematical pattern recognition.
openaire   +1 more source

Research on Isolated Word Speech Recognition Based on Biomimetic Pattern Recognition

2009 International Conference on Artificial Intelligence and Computational Intelligence, 2009
In this paper, the theories of biomimetic pattern recognition and high-dimension space covering are applied into the isolated word speech recognition. And, based on Hopfield network and RBF network, a new type of neural network model is constructed to realize the coverage of different types of samples which form different geometrical shapes in high ...
Bin Lu, Jing-jing Xu
openaire   +1 more source

Study on Speech Recognition of Greeting Based on Biomimetic Pattern Recognition

2010 2nd International Workshop on Intelligent Systems and Applications, 2010
This paper presents a research method to directly recognize greeting voice without segmentation to avoid error recognition because of error segmentation. The basic principle of biomimetic pattern recognition is applied to speaker-independent and continuous speech recognition of greeting.
Hong Ye, Youzheng Zhang, Jianwei Shen
openaire   +1 more source

Syntactic Recognition of Speech Patterns

1977
Syntactic methods can be profitably used for automatically interpreting speech patterns because most of the phonetic knowledge of a language is available in terms of descriptions of spectral patterns or linguistic events.
openaire   +1 more source