Abstract
We present a novel conversational-context aware end-to-end speech recognizer based on a gated neural network that incorporates conversational-context/word/speech embeddings. Unlike conventional speech recognition models, our model learns longer conversational-context information that spans across sentences and is consequently better at recognizing long conversations. Specifically, we propose to use text-based external word and/or sentence embeddings (i.e., fastText, BERT) within an end-to-end framework, yielding significant improvement in word error rate with better conversational-context representation. We evaluated the models on the Switchboard conversational speech corpus and show that our model outperforms standard end-to-end speech recognition models.- Anthology ID:
- P19-1107
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1131–1141
- Language:
- URL:
- https://aclanthology.org/P19-1107
- DOI:
- 10.18653/v1/P19-1107
- Cite (ACL):
- Suyoun Kim, Siddharth Dalmia, and Florian Metze. 2019. Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1131–1141, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion (Kim et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/P19-1107.pdf