Title :
Boosting Gaussian mixtures in an LVCSR system
Author :
Zweig, Geoffrey ; Padmanabhan, Mukund
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
In this paper, we apply boosting to the problem of frame-level phone classification, and use the resulting system to perform voicemail transcription. We develop parallel, hierarchical, and restricted versions of the classic AdaBoost algorithm, which enable the technique to be used in large-scale speech recognition tasks with hundreds of thousands of Gaussians and tens of millions of training frames. We report small but consistent improvements in both frame recognition accuracy and word error rate
Keywords :
Gaussian processes; pattern classification; speech recognition; voice mail; Gaussian mixtures; LVCSR system; boosting; classic AdaBoost algorithm; frame recognition accuracy; frame-level phone classification; hierarchical algorithm; large vocabulary continuous speech recognition; large-scale speech recognition tasks; parallel algorithm; restricted algorithm; training frames; voicemail transcription; word error rate; Acoustic applications; Acoustic testing; Boosting; Error analysis; Large-scale systems; Neural networks; Probability distribution; Speech recognition; System testing; Voice mail;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
Conference_Location :
Istanbul
Print_ISBN :
0-7803-6293-4
DOI :
10.1109/ICASSP.2000.861945
