MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Kyeongman, Joo, Seongho, Jung, Kyomin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915292720922624
author Park, Kyeongman
Joo, Seongho
Jung, Kyomin
author_facet Park, Kyeongman
Joo, Seongho
Jung, Kyomin
contents We introduce MultiActor-Audiobook, a zero-shot approach for generating audiobooks that automatically produces consistent, expressive, and speaker-appropriate prosody, including intonation and emotion. Previous audiobook systems have several limitations: they require users to manually configure the speaker's prosody, read each sentence with a monotonic tone compared to voice actors, or rely on costly training. However, our MultiActor-Audiobook addresses these issues by introducing two novel processes: (1) MSP (**Multimodal Speaker Persona Generation**) and (2) LSI (**LLM-based Script Instruction Generation**). With these two processes, MultiActor-Audiobook can generate more emotionally expressive audiobooks with a consistent speaker prosody without additional training. We compare our system with commercial products, through human and MLLM evaluations, achieving competitive results. Furthermore, we demonstrate the effectiveness of MSP and LSI through ablation studies.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13082
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers
Park, Kyeongman
Joo, Seongho
Jung, Kyomin
Sound
Artificial Intelligence
Audio and Speech Processing
We introduce MultiActor-Audiobook, a zero-shot approach for generating audiobooks that automatically produces consistent, expressive, and speaker-appropriate prosody, including intonation and emotion. Previous audiobook systems have several limitations: they require users to manually configure the speaker's prosody, read each sentence with a monotonic tone compared to voice actors, or rely on costly training. However, our MultiActor-Audiobook addresses these issues by introducing two novel processes: (1) MSP (**Multimodal Speaker Persona Generation**) and (2) LSI (**LLM-based Script Instruction Generation**). With these two processes, MultiActor-Audiobook can generate more emotionally expressive audiobooks with a consistent speaker prosody without additional training. We compare our system with commercial products, through human and MLLM evaluations, achieving competitive results. Furthermore, we demonstrate the effectiveness of MSP and LSI through ablation studies.
title MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2505.13082