VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention
원문 초록
This paper proposes VARA-TTS, a non-autoregressive (non-AR) text-to-speech (TTS) model using a very deep Variational Autoencoder (VDVAE) with Residual Attention mechanism, which refines the textual-to-acoustic alignment layer-wisely. Hierarchical latent variables with different temporal resolutions from the VDVAE are used as queries for residual attention module. By leveraging the coarse global alignment from previous attention layer as an extra input, the following attention layer can produce a refined version of alignment. This amortizes the burden of learning the textual-to-acoustic alignment among multiple attention layers and outperforms the use of only a single attention layer in robustness. An utterance-level speaking speed factor is computed by a jointly-trained speaking speed predictor, which takes the mean-pooled latent variables of the coarsest layer as input, to determine number of acoustic frames at inference. Experimental results show that VARA-TTS achieves slightly inferior speech quality to an AR counterpart Tacotron 2 but an order-of-magnitude speed-up at inference; and outperforms an analogous non-AR model, BVAE-TTS, in terms of speech quality.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
MoonCast: High-Quality Zero-Shot Podcast Generation
S2ST-Omni: An Efficient and Scalable Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Streaming Speech Generation
A Novel Data Augmentation Approach for Automatic Speaking Assessment on Opinion Expressions
CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech
토론
이 논문과 연결된 포럼 글이 아직 없습니다.