Streaming Joint Speech Recognition and Disfluency Detection

Futami, Hayato; Tsunoo, Emiru; Shibata, Kentaro; Kashiwagi, Yosuke; Okuda, Takuo; Arora, Siddhant; Watanabe, Shinji

doi:10.1109/icassp49357.2023.10094620

Cited by 2 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study of disfluencies has been prevalent in computational linguistics, largely aimed at enhancing recognition of spontaneous speech (Futami et al, 2023;Chen et al, 2022;Hough, 2021, 2020). Traditionally, the approach has been to "clean" disfluent content for easier processing.…”

Section: Introductionmentioning

confidence: 99%

Disfluent Cues for Enhanced Speech Understanding in Large Language Models

Rohanian,

Nooralahzadeh,

Rohanian

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

In computational linguistics, the common practice is to "clean" disfluent content from spontaneous speech. However, we hypothesize that these disfluencies might serve as more than mere noise, potentially acting as informative cues. We use a range of pre-trained models for a reading comprehension task involving disfluent queries, specifically featuring different types of speech repairs. The findings indicate that certain disfluencies can indeed improve model performance, particularly those stemming from context-based adjustments. However, large-scale language models struggle to handle repairs involving decision-making or the correction of lexical or syntactic errors, suggesting a crucial area for potential improvement. This paper thus highlights the importance of a nuanced approach to disfluencies, advocating for their potential utility in enhancing model performance rather than their removal.

show abstract

Section: Introductionmentioning

confidence: 99%