Real-time recognition of broadcast radio speech

Author

Cook, G.D. ; Christie, J.D. ; Clarkson, P.R. ; Hochberg, M.M. ; Logan, B.T. ; Robinson, A.J. ; Seymour, C.W.

Author_Institution

Dept. of Eng., Cambridge Univ., UK

Volume

1

fYear

1996

fDate

7-10 May 1996

Firstpage

141

Abstract

This paper presents a real-time speech recognition system used to transcribe broadcast radio speech. The system is based on ABBOT, the hybrid connectionist-HMM large vocabulary continuous speech recognition system developed at the Cambridge University Engineering Department. Developments designed to make the system more robust to acoustic variability and to improve performance when decoding spontaneous speech are described. Modifications necessary to increase the speed of the system so that it operates in real-time are also described. Recognition results and latency figures are presented for speech collected from broadcast news segments on BBC Radio 4

Keywords

acoustic signal processing; decoding; hidden Markov models; radio broadcasting; real-time systems; recurrent neural nets; speech processing; speech recognition; ABBOT; BBC Radio 4; Cambridge University; acoustic modelling; acoustic variability; broadcast news segments; broadcast radio speech; hybrid connectionist-HMM speech recognition; large vocabulary continuous speech recognition; latency figures; real-time speech recognition system; recognition results; recurrent neural network; spontaneous speech decoding; system performance; system speed; Acoustical engineering; Buildings; Decoding; Error analysis; Microphones; Radio broadcasting; Real time systems; Speech enhancement; Speech recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on

Conference_Location

Atlanta, GA

ISSN

1520-6149

Print_ISBN

0-7803-3192-3

Type

conf

DOI

10.1109/ICASSP.1996.540310

Filename

540310