Acoustic-to-Word Models with Conversational Context Information

Suyoun Kim, Florian Metze


Abstract
Conversational context information, higher-level knowledge that spans across sentences, can help to recognize a long conversation. However, existing speech recognition models are typically built at a sentence level, and thus it may not capture important conversational context information. The recent progress in end-to-end speech recognition enables integrating context with other available information (e.g., acoustic, linguistic resources) and directly recognizing words from speech. In this work, we present a direct acoustic-to-word, end-to-end speech recognition model capable of utilizing the conversational context to better process long conversations. We evaluate our proposed approach on the Switchboard conversational speech corpus and show that our system outperforms a standard end-to-end speech recognition system.
Anthology ID:
N19-1283
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2766–2771
Language:
URL:
https://aclanthology.org/N19-1283
DOI:
10.18653/v1/N19-1283
Bibkey:
Cite (ACL):
Suyoun Kim and Florian Metze. 2019. Acoustic-to-Word Models with Conversational Context Information. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2766–2771, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Acoustic-to-Word Models with Conversational Context Information (Kim & Metze, NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/N19-1283.pdf