Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Zhengdong, Shimizu, Shuichiro, Yu, Yahan, Chu, Chenhui
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2502.19548
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915484904980480
author Yang, Zhengdong
Shimizu, Shuichiro
Yu, Yahan
Chu, Chenhui
author_facet Yang, Zhengdong
Shimizu, Shuichiro
Yu, Yahan
Chu, Chenhui
contents Recent advancements in large language models (LLMs) have spurred interest in expanding their application beyond text-based tasks. A large number of studies have explored integrating other modalities with LLMs, notably speech modality, which is naturally related to text. This paper surveys the integration of speech with LLMs, categorizing the methodologies into three primary approaches: text-based, latent-representation-based, and audio-token-based integration. We also demonstrate how these methods are applied across various speech-related applications and highlight the challenges in this field to offer inspiration for
format Preprint
id arxiv_https___arxiv_org_abs_2502_19548
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Large Language Models Meet Speech: A Survey on Integration Approaches
Yang, Zhengdong
Shimizu, Shuichiro
Yu, Yahan
Chu, Chenhui
Computation and Language
Sound
Audio and Speech Processing
Recent advancements in large language models (LLMs) have spurred interest in expanding their application beyond text-based tasks. A large number of studies have explored integrating other modalities with LLMs, notably speech modality, which is naturally related to text. This paper surveys the integration of speech with LLMs, categorizing the methodologies into three primary approaches: text-based, latent-representation-based, and audio-token-based integration. We also demonstrate how these methods are applied across various speech-related applications and highlight the challenges in this field to offer inspiration for
title When Large Language Models Meet Speech: A Survey on Integration Approaches
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2502.19548