Automatic Disfluency Detection from Untranscribed Speech

TL;DR

This paper explores various language, acoustic, and multimodal methods for automatic frame-level disfluency detection from audio, highlighting the superiority of acoustic and multimodal approaches over transcript-based methods, with implications for clinical and NLP applications.

Contribution

It introduces novel acoustic and multimodal approaches for disfluency detection that outperform traditional transcript-based methods, emphasizing the importance of audio quality.

Findings

Acoustic-based disfluency detection outperforms language-based methods.

Transcript quality significantly impacts detection performance.

Multimodal architectures improve disfluency detection accuracy.

Abstract

Speech disfluencies, such as filled pauses or repetitions, are disruptions in the typical flow of speech. Stuttering is a speech disorder characterized by a high rate of disfluencies, but all individuals speak with some disfluencies and the rates of disfluencies may by increased by factors such as cognitive load. Clinically, automatic disfluency detection may help in treatment planning for individuals who stutter. Outside of the clinic, automatic disfluency detection may serve as a pre-processing step to improve natural language understanding in downstream applications. With this wide range of applications in mind, we investigate language, acoustic, and multimodal methods for frame-level automatic disfluency detection and categorization. Each of these methods relies on audio as an input. First, we evaluate several automatic speech recognition (ASR) systems in terms of their ability to transcribe disfluencies, measured using disfluency error rates. We then use these ASR transcripts as input to a language-based disfluency detection model. We find that disfluency detection performance is largely limited by the quality of transcripts and alignments. We find that an acoustic-based approach that does not require transcription as an intermediate step outperforms the ASR language approach. Finally, we present multimodal architectures which we find improve disfluency detection performance over the unimodal approaches. Ultimately, this work introduces novel approaches for automatic frame-level disfluency and categorization. In the long term, this will help researchers incorporate automatic disfluency detection into a range of applications.