A TAG-based noisy channel model of speech repairs
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Developments in continuous speech dictation using the 1995 ARPA NAB news task
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Analysis and processing of lecture audio data: preliminary investigations
SpeechIR '04 Proceedings of the Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004
Simultaneous translation of lectures and speeches
Machine Translation
Hi-index | 0.00 |
The main goal of this work is to provide automatic transcriptions of classroom lectures for e-learning and e-inclusion applications. The first experiments using a recognition system trained for Broadcast News resulted in word error rates near 60%, clearly confirming the need for adaptation to the specific topic of the lectures, on one hand, and for better strategies for handling spontaneous speech. This paper describes the different domain adaptation steps that lowered the error rate to 45%, with very little transcribed adaptation material. It also includes a qualitative analysis of the different types of error, focusing on the ones related to a very high rate of disfluencies.