An ASR-free Fluency Scoring Approach with Self-Supervised Learning

TL;DR

This paper introduces an ASR-free fluency scoring method using self-supervised learning with wav2vec2.0 features and clustering, achieving improved accuracy without relying on speech transcription or time stamps.

Contribution

The novel approach eliminates the need for ASR in fluency assessment by leveraging self-supervised features and clustering, enhancing robustness and accuracy.

Findings

Improves fluency scoring in open response scenarios

Matches state-of-the-art performance in read aloud tasks

Avoids errors caused by speech recognition systems

Abstract

A typical fluency scoring system generally relies on an automatic speech recognition (ASR) system to obtain time stamps in input speech for either the subsequent calculation of fluency-related features or directly modeling speech fluency with an end-to-end approach. This paper describes a novel ASR-free approach for automatic fluency assessment using self-supervised learning (SSL). Specifically, wav2vec2.0 is used to extract frame-level speech features, followed by K-means clustering to assign a pseudo label (cluster index) to each frame. A BLSTM-based model is trained to predict an utterance-level fluency score from frame-level SSL features and the corresponding cluster indexes. Neither speech transcription nor time stamp information is required in the proposed system. It is ASR-free and can potentially avoid the ASR errors effect in practice. Experimental results carried out on non-native English databases show that the proposed approach significantly improves the performance in the "open response" scenario as compared to previous methods and matches the recently reported performance in the "read aloud" scenario.