DSpace Repository

Speech Recognition of a Moving Talker Based on 3-D Viterbi Search Using a Microphone Array

Show simple item record

dc.contributor.author Takeshi Yamada en
dc.contributor.author Satoshi Nakamura en
dc.contributor.author Kiyohiro Shikano en
dc.date.accessioned 2012-08-22T07:58:53Z en
dc.date.available 2012-08-22T07:58:53Z en
dc.date.issued 1997-08 en
dc.identifier.uri http://hdl.handle.net/10061/8126 en
dc.description IJCAI 1997: the 15th International Joint Conference on Artificial Intelligence, August 23-29, 1997, Nagoya, Japan. en
dc.description.abstract This paper describes a new speech recognition algorithm to recognize speech from sound mixtures observed by a microphone array. The proposed algorithm extracts spatial information about sound sources using a microphone array, then performs Viterbi search on 3-D trellis space composed of talker directions, input frames, and HMM states. To evaluate the performance of the proposed algorithm, speech recognition experiments are carried out. These results show that the proposed algorithm works well by using a weight function based on pitch harmonics. en
dc.language.iso en en
dc.title Speech Recognition of a Moving Talker Based on 3-D Viterbi Search Using a Microphone Array en
dc.type.nii Conference Paper en
dc.textversion Publisher en
dc.identifier.spage 113 en
dc.identifier.epage 116 en
dc.identifier.NAIST-ID 73296626 en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account