CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice

TL;DR

This paper presents a new approach for accent classification using large acoustic pretrained models, achieving state-of-the-art accuracy and providing an open-source recipe for multilingual accent recognition.

Contribution

It introduces a simple recipe for accent classification with pretrained models, achieving new state-of-the-art results on English and exploring phonological clustering in embeddings.

Findings

Achieved 95% accuracy on English accent classification.

Established new state-of-the-art for multilingual accent classification.

Demonstrated phonological clustering in Wav2Vec 2.0 embeddings.

Abstract

Despite the recent advancements in Automatic Speech Recognition (ASR), the recognition of accented speech still remains a dominant problem. In order to create more inclusive ASR systems, research has shown that the integration of accent information, as part of a larger ASR framework, can lead to the mitigation of accented speech errors. We address multilingual accent classification through the ECAPA-TDNN and Wav2Vec 2.0/XLSR architectures which have been proven to perform well on a variety of speech-related downstream tasks. We introduce a simple-to-follow recipe aligned to the SpeechBrain toolkit for accent classification based on Common Voice 7.0 (English) and Common Voice 11.0 (Italian, German, and Spanish). Furthermore, we establish new state-of-the-art for English accent classification with as high as 95% accuracy. We also study the internal categorization of the Wav2Vev 2.0 embeddings through t-SNE, noting that there is a level of clustering based on phonological similarity. (Our recipe is open-source in the SpeechBrain toolkit, see: https://github.com/speechbrain/speechbrain/tree/develop/recipes)