Biomimetic pattern recognition for speaker-independent speech recognition
| Data(s) |
2005
|
|---|---|
| Resumo |
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. The vocabulary of the system consists of 15 Chinese dish's names. Neural networks based on Multi-Weight Neuron (MWN) model are used to train and recognize the speech sounds. Experimental results are presented to show that the system, which can carry out real time recognition of the persons from different provinces speaking common Chinese speech, outperforms HMMs especially in the cases of samples of a finite size. 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. The vocabulary of the system consists of 15 Chinese dish's names. Neural networks based on Multi-Weight Neuron (MWN) model are used to train and recognize the speech sounds. Experimental results are presented to show that the system, which can carry out real time recognition of the persons from different provinces speaking common Chinese speech, outperforms HMMs especially in the cases of samples of a finite size. zhangdi于2010-03-29批量导入 Made available in DSpace on 2010-03-29T06:06:19Z (GMT). No. of bitstreams: 1 2355.pdf: 1959426 bytes, checksum: cb45b96364a4953a31ba22599c6cc930 (MD5) Previous issue date: 2005 China Neural Networks Council.; IEEE Computat Intelligence Soc, Beijing Chapter.; Chinese Inst Elect.; Chinese Assoc Artificial Intelligence. Chinese Acad Sci, Inst Semicond, Lab Artificial Neural Networks, Beijing 100083, Peoples R China China Neural Networks Council.; IEEE Computat Intelligence Soc, Beijing Chapter.; Chinese Inst Elect.; Chinese Assoc Artificial Intelligence. |
| Identificador | |
| Idioma(s) |
英语 |
| Publicador |
IEEE 345 E 47TH ST, NEW YORK, NY 10017 USA |
| Fonte |
Qin, H; Wang, SJ; Sun, H .Biomimetic pattern recognition for speaker-independent speech recognition .见：IEEE .Proceedings of the 2005 International Conference on Neural Networks and Brain,345 E 47TH ST, NEW YORK, NY 10017 USA ,2005,Vols 1-3: 1290-1294 |
| Palavras-Chave | #人工智能 #speech recognition #Biomimetic Pattern Recognition #hidden Markov models #dynamic time warping |
| Tipo |
会议论文 |
