Rapid speech recognizer adaptation to new speakers

Author

Digalakis, Vassilis ; Collier, Heather ; Berkowitz, Sid ; Corduneanu, Adrian ; Bocchieri, Enrico ; Kannan, Ashvin ; Boulis, Costas ; Khudanpur, Sanjeev ; Byrne, William ; Sankar, Ananth

Author_Institution

Tech. Univ. of Crete, Chania, Greece

Volume

2

fYear

1999

fDate

15-19 Mar 1999

Firstpage

765

Abstract

This paper summarizes the work of the “Rapid Speech Recognizer Adaptation” team in the workshop held at Johns Hopkins University in the summer of 1998. The project addressed the modeling of dependencies between units of speech with the goal of making more effective use of small amounts of data for speaker adaptation. A variety of methods were investigated and their effectiveness in a rapid adaptation task defined on the Switchboard conversational speech corpus is reported

Keywords

adaptive signal processing; hidden Markov models; parameter estimation; speech processing; speech recognition; HMM; Johns Hopkins University; Switchboard conversational speech corpus; constrained estimation; dependencies modeling; hidden Markov models; new speakers; speaker adaptation data; speech recognizer adaptation; speech units; transform matrices; Acoustic noise; Auditory system; Gaussian processes; Hidden Markov models; Humans; Loudspeakers; Markov random fields; Maximum likelihood estimation; Maximum likelihood linear regression; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on

Conference_Location

Phoenix, AZ

ISSN

1520-6149

Print_ISBN

0-7803-5041-3

Type

conf

DOI

10.1109/ICASSP.1999.759781

Filename

759781