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
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;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0532-9
DOI :
10.1109/ICASSP.1992.226088
