Guardado en:
Detalles Bibliográficos
Autores principales: Ouyang, Zhicheng, Leem, Seong-Gyun, Do, Bach Viet, Wu, Haibin, Rastrow, Ariya, Liu, Yuzong, Metze, Florian
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.08709
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913020794372096
author Ouyang, Zhicheng
Leem, Seong-Gyun
Do, Bach Viet
Wu, Haibin
Rastrow, Ariya
Liu, Yuzong
Metze, Florian
author_facet Ouyang, Zhicheng
Leem, Seong-Gyun
Do, Bach Viet
Wu, Haibin
Rastrow, Ariya
Liu, Yuzong
Metze, Florian
contents Conversational AI has made significant progress, yet generating expressive and controllable text-to-speech (TTS) remains challenging. Specifically, controlling fine-grained voice styles and emotions is notoriously difficult and typically requires massive amounts of heavily annotated training data. To overcome this data bottleneck, we present a scalable, data-efficient cascaded framework that pairs textual style tokens with human-curated, high-quality audio prompts. This approach enables single-shot adaptation to fine-grained speaking styles and character voices. In the context of TTS, this audio prompting acts as In-Context Learning (ICL), guiding the model's prosody and timbre without requiring massive parameter updates or large-scale retraining. To further enhance generation quality and mitigate hallucinations, we introduce a novel ICL-based online reinforcement learning (RL) strategy. This strategy directly optimizes the autoregressive prosody model using subjective aesthetic rewards while being constrained by Connectionist Temporal Classification (CTC) alignment to preserve intelligibility. Comprehensive human perception evaluations demonstrate significant improvements in both the naturalness and expressivity of the synthesized speech, establishing the efficacy of our ICL-based online RL approach.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08709
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning
Ouyang, Zhicheng
Leem, Seong-Gyun
Do, Bach Viet
Wu, Haibin
Rastrow, Ariya
Liu, Yuzong
Metze, Florian
Audio and Speech Processing
Conversational AI has made significant progress, yet generating expressive and controllable text-to-speech (TTS) remains challenging. Specifically, controlling fine-grained voice styles and emotions is notoriously difficult and typically requires massive amounts of heavily annotated training data. To overcome this data bottleneck, we present a scalable, data-efficient cascaded framework that pairs textual style tokens with human-curated, high-quality audio prompts. This approach enables single-shot adaptation to fine-grained speaking styles and character voices. In the context of TTS, this audio prompting acts as In-Context Learning (ICL), guiding the model's prosody and timbre without requiring massive parameter updates or large-scale retraining. To further enhance generation quality and mitigate hallucinations, we introduce a novel ICL-based online reinforcement learning (RL) strategy. This strategy directly optimizes the autoregressive prosody model using subjective aesthetic rewards while being constrained by Connectionist Temporal Classification (CTC) alignment to preserve intelligibility. Comprehensive human perception evaluations demonstrate significant improvements in both the naturalness and expressivity of the synthesized speech, establishing the efficacy of our ICL-based online RL approach.
title Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning
topic Audio and Speech Processing
url https://arxiv.org/abs/2604.08709