Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretraining

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xue, Jinlong, Deng, Yayue, Gao, Yingming, Li, Ya
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911907949051904
author Xue, Jinlong
Deng, Yayue
Gao, Yingming
Li, Ya
author_facet Xue, Jinlong
Deng, Yayue
Gao, Yingming
Li, Ya
contents Recent prompt-based text-to-speech (TTS) models can clone an unseen speaker using only a short speech prompt. They leverage a strong in-context ability to mimic the speech prompts, including speaker style, prosody, and emotion. Therefore, the selection of a speech prompt greatly influences the generated speech, akin to the importance of a prompt in large language models (LLMs). However, current prompt-based TTS models choose the speech prompt manually or simply at random. Hence, in this paper, we adapt retrieval augmented generation (RAG) from LLMs to prompt-based TTS. Unlike traditional RAG methods, we additionally consider contextual information during the retrieval process and present a Context-Aware Contrastive Language-Audio Pre-training (CA-CLAP) model to extract context-aware, style-related features. The objective and subjective evaluations demonstrate that our proposed RAG method outperforms baselines, and our CA-CLAP achieves better results than text-only retrieval methods.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03714
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretraining
Xue, Jinlong
Deng, Yayue
Gao, Yingming
Li, Ya
Sound
Audio and Speech Processing
Recent prompt-based text-to-speech (TTS) models can clone an unseen speaker using only a short speech prompt. They leverage a strong in-context ability to mimic the speech prompts, including speaker style, prosody, and emotion. Therefore, the selection of a speech prompt greatly influences the generated speech, akin to the importance of a prompt in large language models (LLMs). However, current prompt-based TTS models choose the speech prompt manually or simply at random. Hence, in this paper, we adapt retrieval augmented generation (RAG) from LLMs to prompt-based TTS. Unlike traditional RAG methods, we additionally consider contextual information during the retrieval process and present a Context-Aware Contrastive Language-Audio Pre-training (CA-CLAP) model to extract context-aware, style-related features. The objective and subjective evaluations demonstrate that our proposed RAG method outperforms baselines, and our CA-CLAP achieves better results than text-only retrieval methods.
title Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretraining
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2406.03714