TIPAA-SSL: Text Independent Phone-to-Audio Alignment based on Self-Supervised Learning and Knowledge Transfer

TL;DR

This paper introduces TIPAA-SSL, a self-supervised learning approach for text-independent phone-to-audio alignment that leverages phoneme recognition and knowledge transfer to achieve high accuracy with minimal additional training.

Contribution

The paper proposes a novel multi-lingual phonetic representation method using self-supervised learning and knowledge transfer, requiring minimal extra training for effective phone-to-audio alignment.

Findings

Outperforms state-of-the-art in statistical metrics

Effective on synthetic native data from TIMIT and SCRIBE datasets

Easily adaptable to multiple languages

Abstract

In this paper, we present a novel approach for text independent phone-to-audio alignment based on phoneme recognition, representation learning and knowledge transfer. Our method leverages a self-supervised model (wav2vec2) fine-tuned for phoneme recognition using a Connectionist Temporal Classification (CTC) loss, a dimension reduction model and a frame-level phoneme classifier trained thanks to forced-alignment labels (using Montreal Forced Aligner) to produce multi-lingual phonetic representations, thus requiring minimal additional training. We evaluate our model using synthetic native data from the TIMIT dataset and the SCRIBE dataset for American and British English, respectively. Our proposed model outperforms the state-of-the-art (charsiu) in statistical metrics and has applications in language learning and speech processing systems. We leave experiments on other languages for future work but the design of the system makes it easily adaptable to other languages.