Saved in:
Bibliographic Details
Main Authors: Liu, Min, Yin, JingJing, Zhang, Xiang, Hao, Siyu, Hu, Yanni, Lin, Bin, Feng, Yuan, Zhou, Hongbin, Ye, Jianhao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.17516
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911168268861440
author Liu, Min
Yin, JingJing
Zhang, Xiang
Hao, Siyu
Hu, Yanni
Lin, Bin
Feng, Yuan
Zhou, Hongbin
Ye, Jianhao
author_facet Liu, Min
Yin, JingJing
Zhang, Xiang
Hao, Siyu
Hu, Yanni
Lin, Bin
Feng, Yuan
Zhou, Hongbin
Ye, Jianhao
contents Existing text-to-speech systems predominantly focus on single-sentence synthesis and lack adequate contextual modeling as well as fine-grained performance control capabilities for generating coherent multicast audiobooks. To address these limitations, we propose a context-aware and emotion controllable speech synthesis framework specifically engineered for multicast audiobooks with three key innovations: a context mechanism for contextual consistency, a disentanglement paradigm to decouple style control from speech prompts for semantic consistency, and self-distillation to boost emotional expressiveness and instruction controllability. Experimental results show superior performance across the generation of narration, dialogue, and the whole chapter, significantly outperforming existing baselines. Ablation studies are conducted to validate the effectiveness of our proposed methods. Demo samples can be found in https://everest-ai.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Audiobook-CC: Controllable Long-context Speech Generation for Multicast Audiobook
Liu, Min
Yin, JingJing
Zhang, Xiang
Hao, Siyu
Hu, Yanni
Lin, Bin
Feng, Yuan
Zhou, Hongbin
Ye, Jianhao
Audio and Speech Processing
Existing text-to-speech systems predominantly focus on single-sentence synthesis and lack adequate contextual modeling as well as fine-grained performance control capabilities for generating coherent multicast audiobooks. To address these limitations, we propose a context-aware and emotion controllable speech synthesis framework specifically engineered for multicast audiobooks with three key innovations: a context mechanism for contextual consistency, a disentanglement paradigm to decouple style control from speech prompts for semantic consistency, and self-distillation to boost emotional expressiveness and instruction controllability. Experimental results show superior performance across the generation of narration, dialogue, and the whole chapter, significantly outperforming existing baselines. Ablation studies are conducted to validate the effectiveness of our proposed methods. Demo samples can be found in https://everest-ai.github.io/.
title Audiobook-CC: Controllable Long-context Speech Generation for Multicast Audiobook
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.17516