https://scholars.lib.ntu.edu.tw/handle/123456789/632414
標題: | Improved Robust Speech Recognition Considering Signal Correlation Approximated by Taylor Series | 作者: | Shen J.-L Hung J.-W LIN-SHAN LEE |
公開日期: | 1998 | 來源出版物: | 5th International Conference on Spoken Language Processing, ICSLP 1998 | 摘要: | In this paper, an improved mismatch function by considering signal correlation between speech and noise is proposed to better estimate the noisy speech HMM's. A linearized model based on Taylor series expansion approach is used to approximate the proposed mismatch function. The parameters of the noisy speech HMM's can be estimated more precisely by combining the parameters of the clean speech and noise HMM's in the log-spectral domain or cepstral domain. Experimental results show that improved robustness for speech recognition in the presence of white noise as well as colored noise can be obtained. © 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-0011464161&partnerID=40&md5=727ec4a7dbfebd957dc16718898056c5 https://scholars.lib.ntu.edu.tw/handle/123456789/632414 |
SDG/關鍵字: | Speech; Speech recognition; Taylor series; Cepstral domain; Clean speech; Linearized models; Log-spectral domain; Model-based OPC; Noisy speech; Robust speech recognition; Signal correlation; Taylor's series expansion; Taylor-series; White noise |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。