paper-with-me

Papers

Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding

2024-10-29 · Bohan Li, Hankun Wang, Situo Zhang, Yiwei Guo, Kai Yu

The auto-regressive architecture, like GPTs, is widely used in modern Text-to-Speech (TTS) systems. However, it incurs substantial inference time, particularly due to the challenges in the next-token prediction posed by lengthy sequences of speech tokens. In this work, we introduce VADUSA, one of the first approaches to accelerate auto-regressive TTS through speculative decoding. Our results show that VADUSA not only significantly improves inference speed but also enhances performance by incorporating draft heads to predict future speech content auto-regressively. Furthermore, the inclusion of a tolerance mechanism during sampling accelerates inference without compromising quality. Our approach demonstrates strong generalization across large datasets and various types of speech tokens.

📄 PDF Abstract BibTeX arXiv:2410.21951

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Synthesistext-to-speechText to Speech

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

2020-06-08 · ICLR 2021 1 · Yi Ren, Chenxu Hu, Xu Tan, Tao Qin 외

Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an auto…

Knowledge DistillationSpeech Synthesistext-to-speechText to Speech+1

FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis

2022-07-08 · Yongqi Wang, Zhou Zhao

Unconstrained lip-to-speech synthesis aims to generate corresponding speeches from silent videos of talking faces with no restriction on head poses or vocabulary. Current works mainly use sequence-to-sequence models to s…

Lip to Speech SynthesisSpeech Synthesis

DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation

2023-10-11 · NeurIPS 2023 11 · Qingkai Fang, Yan Zhou, Yang Feng

Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex mul…

Decoderfr-enKnowledge DistillationSpeech-to-Speech Translation+1

Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates

2021-09-27 · Hirofumi Inaguma, Siddharth Dalmia, Brian Yan, Shinji Watanabe

The multi-decoder (MD) end-to-end speech translation model has demonstrated high translation quality by searching for better intermediate automatic speech recognition (ASR) decoder states as hidden intermediates (HI). It…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)CPUDecoder+6

Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs

2026-07-23 · Muyang Du, Shuang Yu, Junjie Lai arxiv

Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deployment in production applications that require low latency. IndexTTS-2…

Text-To-Speech Synthesis