Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition
International Journal on Natural Language Computing · 30.12.2022 · 11 (6) · 01-13
DOI: 10.5121/ijnlc.2022.11601 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal on Natural Language Computing, online erschienen am 30.12.2022. Verfasst von Piyush Behre und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting from irregular pausing patterns or slow speakers. Transformer sequence tagging models are effective at capturing long bi-directional context, which is crucial for automatic punctuation. Automatic Speech Recognition (ASR) production systems, however, are constrained by real-time requirements, making it hard to incorporate the right context when making punctuation decisions. Context within the segments produced by ASR decoders can be helpful but limiting in overall punctuation performance for a continuous speech session. In this paper, we propose a streaming approach for punctuation or re-punctuation of ASR output using dynamic decoding windows and measure its impact on punctuation and segmentation accuracy across scenarios. The new system tackles over-segmentation issues, improving segmentation F0.5-score by 13.9%. Streaming punctuation achieves an average BLEUscore improvement of 0.66 for the downstream task of Machine Translation (MT).
Zitieren
APA
Behre, P., Tan, S., Varadharajan, P., & Chang, S. (2022). Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition. International Journal on Natural Language Computing, 11(6), 01-13. https://doi.org/10.5121/ijnlc.2022.11601
Vancouver
Behre P, Tan S, Varadharajan P, Chang S. Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition. International Journal on Natural Language Computing. 2022;11(6):01-13. doi:10.5121/ijnlc.2022.11601
BibTeX
@article{Behre2022,
author = {Behre, Piyush and Tan, Sharman and Varadharajan, Padma and Chang, Shuangyu},
title = {Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition},
journal = {International Journal on Natural Language Computing},
year = {2022},
volume = {11},
number = {6},
pages = {01--13},
doi = {10.5121/ijnlc.2022.11601}
}
EUVIMED