TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR

Shashi Kumar, Srikanth Madikeri, Juan Pablo Zuluaga Gomez, Iuliia Thorbecke, Esaú Villatoro-tello, Sergio Burdisso, Petr Motlicek, Karthik S, Aravind Ganapathiraju


Abstract
In traditional conversational intelligence from speech, a cascaded pipeline is used, involving tasks such as voice activity detection, diarization, transcription, and subsequent processing with different NLP models for tasks like semantic endpointing and named entity recognition (NER). Our paper introduces TokenVerse, a single Transducer-based model designed to handle multiple tasks. This is achieved by integrating task-specific tokens into the reference text during ASR model training, streamlining the inference and eliminating the need for separate NLP models. In addition to ASR, we conduct experiments on 3 different tasks: speaker change detection, endpointing, and NER. Our experiments on a public and a private dataset show that the proposed method improves ASR by up to 7.7% in relative WER while outperforming the cascaded pipeline approach in individual task performance. Our code is publicly available: https://github.com/idiap/tokenverse-unifying-speech-nlp
Anthology ID:
2024.emnlp-main.1167
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
20988–20995
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1167
DOI:
Bibkey:
Cite (ACL):
Shashi Kumar, Srikanth Madikeri, Juan Pablo Zuluaga Gomez, Iuliia Thorbecke, Esaú Villatoro-tello, Sergio Burdisso, Petr Motlicek, Karthik S, and Aravind Ganapathiraju. 2024. TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 20988–20995, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR (Kumar et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1167.pdf