We present a novel trigger-based language model adaptation method oriented to the transcription of meetings. In meetings, the topic is focused and consistent throughout the whole session, therefore keywords can be correlated over long distances. The trigger-based language model is designed to capture such long-distance dependencies, but it is typically constructed from a large corpus, which is usually too general to derive task-dependent trigger pairs. In the proposed method, we make use of the initial speech recognition results to extract task-dependent trigger pairs and to estimate their statistics. Moreover, we introduce a back-off scheme that also exploits the statistics estimated from a large corpus. The proposed model reduced the test-set perplexity considerably more than the typical trigger-based language model constructed from a large corpus, and achieved a remarkable perplexity reduction of 44% over the baseline when combined with an adapted trigram language model. In addition, a reduction in word error rate was obtained when using the proposed language model to rescore word graphs.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Carlos TRONCOSO, Tatsuya KAWAHARA, "Trigger-Based Language Model Adaptation for Automatic Transcription of Panel Discussions" in IEICE TRANSACTIONS on Information,
vol. E89-D, no. 3, pp. 1024-1031, March 2006, doi: 10.1093/ietisy/e89-d.3.1024.
Abstract: We present a novel trigger-based language model adaptation method oriented to the transcription of meetings. In meetings, the topic is focused and consistent throughout the whole session, therefore keywords can be correlated over long distances. The trigger-based language model is designed to capture such long-distance dependencies, but it is typically constructed from a large corpus, which is usually too general to derive task-dependent trigger pairs. In the proposed method, we make use of the initial speech recognition results to extract task-dependent trigger pairs and to estimate their statistics. Moreover, we introduce a back-off scheme that also exploits the statistics estimated from a large corpus. The proposed model reduced the test-set perplexity considerably more than the typical trigger-based language model constructed from a large corpus, and achieved a remarkable perplexity reduction of 44% over the baseline when combined with an adapted trigram language model. In addition, a reduction in word error rate was obtained when using the proposed language model to rescore word graphs.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.3.1024/_p
Copy
@ARTICLE{e89-d_3_1024,
author={Carlos TRONCOSO, Tatsuya KAWAHARA, },
journal={IEICE TRANSACTIONS on Information},
title={Trigger-Based Language Model Adaptation for Automatic Transcription of Panel Discussions},
year={2006},
volume={E89-D},
number={3},
pages={1024-1031},
abstract={We present a novel trigger-based language model adaptation method oriented to the transcription of meetings. In meetings, the topic is focused and consistent throughout the whole session, therefore keywords can be correlated over long distances. The trigger-based language model is designed to capture such long-distance dependencies, but it is typically constructed from a large corpus, which is usually too general to derive task-dependent trigger pairs. In the proposed method, we make use of the initial speech recognition results to extract task-dependent trigger pairs and to estimate their statistics. Moreover, we introduce a back-off scheme that also exploits the statistics estimated from a large corpus. The proposed model reduced the test-set perplexity considerably more than the typical trigger-based language model constructed from a large corpus, and achieved a remarkable perplexity reduction of 44% over the baseline when combined with an adapted trigram language model. In addition, a reduction in word error rate was obtained when using the proposed language model to rescore word graphs.},
keywords={},
doi={10.1093/ietisy/e89-d.3.1024},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Trigger-Based Language Model Adaptation for Automatic Transcription of Panel Discussions
T2 - IEICE TRANSACTIONS on Information
SP - 1024
EP - 1031
AU - Carlos TRONCOSO
AU - Tatsuya KAWAHARA
PY - 2006
DO - 10.1093/ietisy/e89-d.3.1024
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2006
AB - We present a novel trigger-based language model adaptation method oriented to the transcription of meetings. In meetings, the topic is focused and consistent throughout the whole session, therefore keywords can be correlated over long distances. The trigger-based language model is designed to capture such long-distance dependencies, but it is typically constructed from a large corpus, which is usually too general to derive task-dependent trigger pairs. In the proposed method, we make use of the initial speech recognition results to extract task-dependent trigger pairs and to estimate their statistics. Moreover, we introduce a back-off scheme that also exploits the statistics estimated from a large corpus. The proposed model reduced the test-set perplexity considerably more than the typical trigger-based language model constructed from a large corpus, and achieved a remarkable perplexity reduction of 44% over the baseline when combined with an adapted trigram language model. In addition, a reduction in word error rate was obtained when using the proposed language model to rescore word graphs.
ER -