CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lu, Yen-Ju, Liu, Jing, Thebaud, Thomas, Moro-Velazquez, Laureano, Rastrow, Ariya, Dehak, Najim, Villalba, Jesus
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910728912371712
author Lu, Yen-Ju
Liu, Jing
Thebaud, Thomas
Moro-Velazquez, Laureano
Rastrow, Ariya
Dehak, Najim
Villalba, Jesus
author_facet Lu, Yen-Ju
Liu, Jing
Thebaud, Thomas
Moro-Velazquez, Laureano
Rastrow, Ariya
Dehak, Najim
Villalba, Jesus
contents We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream models, CA-SSLR integrates language and speaker embeddings from earlier layers, making the SSL model aware of the current language and speaker context. This approach reduces the reliance on input audio features while preserving the integrity of the base SSLR. CA-SSLR improves the model's capabilities and demonstrates its generality on unseen tasks with minimal task-specific tuning. Our method employs linear modulation to dynamically adjust internal representations, enabling fine-grained adaptability without significantly altering the original model behavior. Experiments show that CA-SSLR reduces the number of trainable parameters, mitigates overfitting, and excels in under-resourced and unseen tasks. Specifically, CA-SSLR achieves a 10% relative reduction in LID errors, a 37% improvement in ASR CER on the ML-SUPERB benchmark, and a 27% decrease in SV EER on VoxCeleb-1, demonstrating its effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04425
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
Lu, Yen-Ju
Liu, Jing
Thebaud, Thomas
Moro-Velazquez, Laureano
Rastrow, Ariya
Dehak, Najim
Villalba, Jesus
Audio and Speech Processing
Computation and Language
Machine Learning
Sound
We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream models, CA-SSLR integrates language and speaker embeddings from earlier layers, making the SSL model aware of the current language and speaker context. This approach reduces the reliance on input audio features while preserving the integrity of the base SSLR. CA-SSLR improves the model's capabilities and demonstrates its generality on unseen tasks with minimal task-specific tuning. Our method employs linear modulation to dynamically adjust internal representations, enabling fine-grained adaptability without significantly altering the original model behavior. Experiments show that CA-SSLR reduces the number of trainable parameters, mitigates overfitting, and excels in under-resourced and unseen tasks. Specifically, CA-SSLR achieves a 10% relative reduction in LID errors, a 37% improvement in ASR CER on the ML-SUPERB benchmark, and a 27% decrease in SV EER on VoxCeleb-1, demonstrating its effectiveness.
title CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
topic Audio and Speech Processing
Computation and Language
Machine Learning
Sound
url https://arxiv.org/abs/2412.04425