Time-Accurate Speech Rich Transcription with Non-Fluencies
Keywords: Non-fluency, Dysfluency, Alignment, speech transcription, clinical
Abstract: Speech is a hierarchical collection of text, prosody, emotions, dysfluencies, etc. Automatic transcription of speech that goes beyond text (words) is an underexplored problem.
We focus on transcribing speech along with non-fluencies (dysfluencies). The current state-of-the-art pipeline \citep{lian2024ssdmscalablespeechdysfluency} suffers from complex architecture design, training complexity, and significant shortcomings in the local sequence aligner, and it does not explore in-context learning capacity. In this work, we propose SSDM 2.0, which tackles those shortcomings via four main contributions:
(1) We propose a novel \textit{neural articulatory flow} to derive highly scalable speech representations.
(2) We developed a \textit{full-stack connectionist subsequence aligner} that captures all types of dysfluencies.
(3) We introduced a mispronunciation prompt pipeline and consistency learning module into LLM to leverage dysfluency \textit{in-context pronunciation learning} abilities.
(4) We curated Libri-Dys \citep{lian2024ssdmscalablespeechdysfluency} and open-sourced the current largest-scale co-dysfluency corpus, \textit{Libri-Co-Dys}, for future research endeavors.
\hl{In clinical experiments on pathological speech transcription, we tested SSDM 2.0 using nfvPPA corpus primarily characterized by \textit{articulatory dysfluencies}.}
Overall, SSDM 2.0 outperforms SSDM and all other dysfluency transcription models by a large margin. See our project demo page at \url{https://srnf2.github.io/}.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8144
Loading