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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tits, Noé, Bhatnagar, Prernna, Dutoit, Thierry
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917656386338816
author Tits, Noé
Bhatnagar, Prernna
Dutoit, Thierry
author_facet Tits, Noé
Bhatnagar, Prernna
Dutoit, Thierry
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_02124
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TIPAA-SSL: Text Independent Phone-to-Audio Alignment based on Self-Supervised Learning and Knowledge Transfer
Tits, Noé
Bhatnagar, Prernna
Dutoit, Thierry
Audio and Speech Processing
Artificial Intelligence
Computation and Language
Machine Learning
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.
title TIPAA-SSL: Text Independent Phone-to-Audio Alignment based on Self-Supervised Learning and Knowledge Transfer
topic Audio and Speech Processing
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2405.02124