Text-aware and Context-aware Expressive Audiobook Speech Synthesis
원문 초록
Recent advances in text-to-speech have significantly improved the expressiveness of synthetic speech. However, a major challenge remains in generating speech that captures the diverse styles exhibited by professional narrators in audiobooks without relying on manually labeled data or reference speech. To address this problem, we propose a text-aware and context-aware(TACA) style modeling approach for expressive audiobook speech synthesis. We first establish a text-aware style space to cover diverse styles via contrastive learning with the supervision of the speech style. Meanwhile, we adopt a context encoder to incorporate cross-sentence information and the style embedding obtained from text. Finally, we introduce the context encoder to two typical TTS models, VITS-based TTS and language model-based TTS. Experimental results demonstrate that our proposed approach can effectively capture diverse styles and coherent prosody, and consequently improves naturalness and expressiveness in audiobook speech synthesis.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text
V2X-REALM: Vision-Language Model-Based Robust End-to-End Cooperative Autonomous Driving with Adaptive Long-Tail Modeling
Information fusion strategy integrating pre-trained language model and contrastive learning for materials knowledge mining
Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers
DIBERT: Dependency Injected Bidirectional Encoder Representations from Transformers
A Bit of Progress in Language Modeling
토론
이 논문과 연결된 포럼 글이 아직 없습니다.