Speaker-Independent Vowel Recognition for Malay Children Using Time-Delay Neural Network

机译：使用时延神经网络的马来儿童独立于说话人的元音识别

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper investigated the speaker independent vowel recognition for Malay children using the Time Delay Neural Network (TDNN). Due to less research done on the children speech recognition, the temporal structure of the children speech was not fully understood. This 2 hidden layers TDNN was proposed to discriminate 6 Malay vowels: /a/, /e/, /∂/, /i/, /o/ and /u/. The speech database consisted of vowel sounds from 360 children speakers. Cepstral coefficient was normalized for the input of TDNN. The frame rate of the TDNN was tested with 10ms, 20ms, and 30ms. It was found out that the 30ms frame rate produced the highest vowel recognition accuracy with 81.92%. The TDNN also showed higher speech recognition rate compared to the previous studies that used Multilayer Perceptron.

机译：本文研究了使用时延神经网络（TDNN）对马来儿童的说话人独立元音识别。由于对儿童语音识别的研究较少，因此儿童语音的时间结构尚未完全了解。建议使用这2个隐藏层TDNN来区分6个马来元音：/ a /，/ e /，/∂/，/ i /，/ o /和/ u /。语音数据库包含来自360个儿童说话者的元音。倒谱系数针对TDNN的输入进行了标准化。使用10ms，20ms和30ms测试TDNN的帧速率。结果发现，30ms的帧频产生最高的元音识别精度，为81.92％。与先前使用多层感知器的研究相比，TDNN还显示出更高的语音识别率。

著录项

来源
《5th Kuala Lumpur international conference on biomedical engineering 2011》|2011年|p.565-568|共4页
会议地点 Kuala Lumpur(MY);Kuala Lumpur(MY)
作者
B.F. Yong; H.N. Ting;
展开▼
作者单位

Department of Biomedical Engineering, Faculty of Engineering, University Malaya, Jalan Pantai Baharu, 50603 Kuala Lumpur, Malaysia;

Department of Biomedical Engineering, Faculty of Engineering, University Malaya, Jalan Pantai Baharu, 50603 Kuala Lumpur, Malaysia;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类生物工程学（生物技术）;
关键词
malay vowel recognition; time delay neural network; automatic speech recognition; children speech;

机译：马来元音识别;延时神经网络自动语音识别；儿童演讲;

相似文献

外文文献
中文文献
专利

1. A Method for Designing Neural Networks Using Nonlinear Multivariate Analysis: Application to Speaker-Independent Vowel Recognition [J] . Irino T, Kawahara H Neural computation . 1990,第3期

机译：基于非线性多元分析的神经网络设计方法：在独立于说话人的元音识别中的应用
2. Speaker-Independent Silent Speech Recognition From Flesh-Point Articulatory Movements Using an LSTM Neural Network [J] . Myungjong Kim, Beiming Cao, Ted Mau, Audio, Speech, and Language Processing, IEEE/ACM Transactions on . 2017,第12期

机译：使用LSTM神经网络从果肉关节运动中独立于说话者的沉默语音识别
3. SPEAKER-INDEPENDENT SPEECH RECOGNITION BASED ON FAST NEURAL NETWORK [J] . GUI TAG, ZHANG TAIYI International Journal of Artificial Intelligence Tools: Architectures, Languages, Algorithms . 2003,第4期

机译：基于快速神经网络的说话人独立语音识别
4. Speaker-Independent Malay Vowel Recognition of Children using Neural Networks [C] . H.N. Ting, Y.M. Lam World congress on medical physics and biomedical engineering;International congress of the IUPESM . 2011

机译：神经网络对儿童的独立于说话者的马来元音识别
5. Convolutional Neural Networks for Speaker-Independent Speech Recognition. [D] . Belilovsky, Eugene. 2011

机译：用于与说话人无关的语音识别的卷积神经网络。
6. Speaker-Independent Silent Speech Recognition from Flesh-Point Articulatory Movements Using an LSTM NeuralNetwork [O] . Myungjong Kim, Beiming Cao, Ted Mau, -1

机译：使用LSTM神经从肉点发音运动中独立于说话者的沉默语音识别网络
7. Speaker-independent Malay vowel recognition of children using multi-layer perceptron [O] . Hua Nong Ting, Yunus Jasmy 2004

机译：使用多层感知器的儿童独立于说话者的马来元音识别
8. Acoustic Signal Recognition with a Photorefractive Time-Delay Neural Network [R] . Zhou, G., Anderson, D. Z. 1994

机译：光折变时滞神经网络的声信号识别

Speaker-Independent Vowel Recognition for Malay Children Using Time-Delay Neural Network

摘要

著录项

相似文献

相关主题

期刊订阅