GENERALIZED MINIMAL DISTORTION SEGMENTATION FOR ANN-BASED SPEECH RECOGNITION

標題:	GENERALIZED MINIMAL DISTORTION SEGMENTATION FOR ANN-BASED SPEECH RECOGNITION
作者:	CHEN, SH CHEN, WY 交大名義發表電信工程研究所 National Chiao Tung University Institute of Communications Engineering
公開日期:	1-三月-1995
摘要:	A generalized minimal distortion segmentation algorithm is proposed to solve the time alignment problem for ANN-based speech recognition. By modeling dynamics of spectral information of an acoustic segment with smooth curves obtained by orthonormal polynomial expansion, a speech signal is optimally divided into segments and then recognized by an MLP recognizer. Experimental results showed that the proposed method outperforms the standard CDHMM method.
URI:	http://dx.doi.org/10.1109/89.366545 http://hdl.handle.net/11536/2021
ISSN:	1063-6676
DOI:	10.1109/89.366545
期刊:	IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING
Volume:	3
Issue:	2
起始頁:	141
結束頁:	145
顯示於類別：	期刊論文

文件中的檔案：

若為 zip 檔案，請下載檔案解壓縮後，用瀏覽器開啟資料夾中的 index.html 瀏覽全文。