DocumentCode
284773
Title
An unsupervised, sequential learning algorithm for the segmentation of speech waveforms with multiple speakers
Author
Siu, Man-Hung ; Yu, George ; Gish, Herbert
Author_Institution
BBN Systems & Technologies, Cambridge, MA, USA
Volume
2
fYear
1992
fDate
23-26 Mar 1992
Firstpage
189
Abstract
The authors present a method for segmenting speech waveforms containing several speakers into utterances, each from one individual, and then identifying each utterance as coming from a specific individual or group of individuals. The procedure is unsupervised in that there is no training set, and sequential in that information obtained in early stages of the process is utilized in later stages
Keywords
learning systems; pattern recognition; speech analysis and processing; speech recognition; multiple speakers; speech waveform segmentation; unsupervised sequential learning algorithm; utterance identification; Air traffic control; Communication system control; Detectors; Fasteners; Loudspeakers; Radio control; Speech analysis; Speech enhancement; Speech processing; Speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location
San Francisco, CA
ISSN
1520-6149
Print_ISBN
0-7803-0532-9
Type
conf
DOI
10.1109/ICASSP.1992.226088
Filename
226088
Link To Document