PROSODY MODELS FOR CONVERSATIONAL SPEECH RECOGNITION

作者： Mari Ostendorf , Rebecca Bates , Izhak Shafran

DOI:

关键词:

摘要: This paper describes a formal model for incorporating prosody in the speech recognition process, both improving word directly and jointly recognizing words underlying structure. The includes possibility of using an intermediate symbolic representation as well direct conditioning on acoustic correlates. Alternatives feature extraction are described, together with implications statistical modeling. Examples spontaneous include clustering dynamic pronunciation

暂无可下载资源，当前可以选择系统获取到有开放资源时通知我或者直接发起求助文献求助

参考文章(49)

Mari Ostendorf, Richard Wright, Izhak Shafran, Prosody and phonetic variability: Lessons learned from acoustic model clustering ,(2003)

Leah H. Jamieson, Michael T. Johnson, Temporal Features for Broadcast News Segmentation ,(2001)

Andreas Stolcke, Dilek Zeynep Hakkani, Madelaine Plauché, Elizabeth Shriberg, Mari Ostendorf, Rebecca A. Bates, Gökhan Tür, Yu Lu, Automatic detection of sentence boundaries and disfluencies based on recognized words. conference of the international speech communication association. ,(1998)

Sadaoki Furui, Koji Iwano, Takahiro Seki, Noise robust speech recognition using F0 contour extracted by hough transform. conference of the international speech communication association. ,(2002)

Christine H. Nakatani, Julia Hirschberg, Acoustic indicators of topic segmentation. conference of the international speech communication association. ,(1998)

Jan Buckow, Volker Warnke, Elmar Nöth, Heinrich Niemann, Richard Huber, Anton Batliner, Whence and Whither Prosody in Automatic Speech Understanding: A Case Study ,(2002)

Jie Zhang, Richard Wright, Patricia Keating, Word-level asymmetries in consonant articulation ,(2001)

James R. Glass, Jane W. Chang, Segmentation and modeling in segment-based recognition. conference of the international speech communication association. ,(1997)

Julia Hirschberg, Marc Swerts, Diane Litman, Detecting Misrecognitions and Corrections in Spoken Dialogue Systems from ‘Aware’ Sites ,(2003)

10.

Michael Finke, Alex Waibel, Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition. conference of the international speech communication association. ,(1997)

PROSODY MODELS FOR CONVERSATIONAL SPEECH RECOGNITION

来源期刊

我的账户

PROSODY MODELS FOR CONVERSATIONAL SPEECH RECOGNITION

来源期刊

相似文章 10

我的账户