Learning Multiple Utterance-Level Attribute Representations with a Unified Speech Encoder

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bouziane, Maryem, Mdhaffar, Salima, Estève, Yannick
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915846420430848
author Bouziane, Maryem
Mdhaffar, Salima
Estève, Yannick
author_facet Bouziane, Maryem
Mdhaffar, Salima
Estève, Yannick
contents Speech foundation models trained with self-supervised learning produce generic speech representations that support a wide range of speech processing tasks. When further adapted with supervised learning, these models can achieve strong performance on specific downstream tasks. Recent post-training approaches, such as SAMU-XSLR and SONAR, align speech representations with utterance-level semantic representations, enabling effective multimodal (speech-text) and multilingual applications. While speech foundation models typically learn contextual embeddings at the acoustic frame level, these methods learn representations at the utterance level. In this work, we extend this paradigm to arbitrary utterance-level attributes and propose a unified post-training framework that enables a single speech foundation model to generate multiple types of utterance-level representations. We demonstrate the effectiveness of this approach by jointly learning semantic and speaker representations and evaluating them on multilingual speech retrieval and speaker recognition tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08312
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Multiple Utterance-Level Attribute Representations with a Unified Speech Encoder
Bouziane, Maryem
Mdhaffar, Salima
Estève, Yannick
Computation and Language
Speech foundation models trained with self-supervised learning produce generic speech representations that support a wide range of speech processing tasks. When further adapted with supervised learning, these models can achieve strong performance on specific downstream tasks. Recent post-training approaches, such as SAMU-XSLR and SONAR, align speech representations with utterance-level semantic representations, enabling effective multimodal (speech-text) and multilingual applications. While speech foundation models typically learn contextual embeddings at the acoustic frame level, these methods learn representations at the utterance level. In this work, we extend this paradigm to arbitrary utterance-level attributes and propose a unified post-training framework that enables a single speech foundation model to generate multiple types of utterance-level representations. We demonstrate the effectiveness of this approach by jointly learning semantic and speaker representations and evaluating them on multilingual speech retrieval and speaker recognition tasks.
title Learning Multiple Utterance-Level Attribute Representations with a Unified Speech Encoder
topic Computation and Language
url https://arxiv.org/abs/2603.08312