English
Related papers

Related papers: Fast and High-Quality Auto-Regressive Speech Synth…

200 papers

The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce speaker characteristics very accurately. However, this…

Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-29 Seongyeon Park , Myungseo Song , Bohyung Kim , Tae-Hyun Oh

An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-17 Junrui Ni , Liming Wang , Heting Gao , Kaizhi Qian , Yang Zhang , Shiyu Chang , Mark Hasegawa-Johnson

Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech. Such models typically incorporate a fine-grained variational autoencoder (VAE) structure, extracting…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-11 Guangzhi Sun , Yu Zhang , Ron J. Weiss , Yuan Cao , Heiga Zen , Andrew Rosenberg , Bhuvana Ramabhadran , Yonghui Wu

Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale datasets by quantizing waveform into discrete speech tokens is making great progress to capture the diversity and expressiveness in human speech, but the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-10 Chong Zhang , Yanqing Liu , Yang Zheng , Sheng Zhao

Incremental text-to-speech, also known as streaming TTS, has been increasingly applied to online speech applications that require ultra-low response latency to provide an optimal user experience. However, most of the existing speech…

Sound · Computer Science 2022-12-06 Muyang Du , Chuan Liu , Jiaxing Qi , Junjie Lai

Regressive Text-to-Speech (TTS) system utilizes attention mechanism to generate alignment between text and acoustic feature sequence. Alignment determines synthesis robustness (e.g, the occurence of skipping, repeating, and collapse) and…

Artificial Intelligence · Computer Science 2023-06-06 Dengfeng Ke , Yayue Deng , Yukang Jia , Jinlong Xue , Qi Luo , Ya Li , Jianqing Sun , Jiaen Liang , Binghuai Lin

The performance of text-to-speech (TTS) systems heavily depends on spectrogram to waveform generation, also known as the speech reconstruction phase. The time required for the same is known as synthesis delay. In this paper, an approach to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-14 Ankit Sharma , Puneet Kumar , Vikas Maddukuri , Nagasai Madamshettib , Kishore KG , Sahit Sai Sriram Kavurub , Balasubramanian Raman , Partha Pratim Roy

This paper proposes a new "decompose-and-edit" paradigm for the text-based speech insertion task that facilitates arbitrary-length speech insertion and even full sentence generation. In the proposed paradigm, global and local factors in…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-29 Dacheng Yin , Chuanxin Tang , Yanqing Liu , Xiaoqiang Wang , Zhiyuan Zhao , Yucheng Zhao , Zhiwei Xiong , Sheng Zhao , Chong Luo

In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion…

Sound · Computer Science 2023-09-14 Zhichao Wu , Qiulin Li , Sixing Liu , Qun Yang

Speculative Decoding (SD) accelerates inference in large language models by using a smaller draft model to propose tokens, which are then verified by a larger target model. However, the throughput gains of SD are fundamentally limited by a…

Computation and Language · Computer Science 2025-10-16 Sanghyun Byun , Mohanad Odema , Jung Ick Guack , Baisub Lee , Jacob Song , Woo Seong Chung

We introduce Matcha-TTS, a new encoder-decoder architecture for speedy TTS acoustic modelling, trained using optimal-transport conditional flow matching (OT-CFM). This yields an ODE-based decoder capable of high output quality in fewer…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-11 Shivam Mehta , Ruibo Tu , Jonas Beskow , Éva Székely , Gustav Eje Henter

Voice, as input, has progressively become popular on mobiles and seems to transcend almost entirely text input. Through voice, the voice search (VS) system can provide a more natural way to meet user's information needs. However, errors…

Information Retrieval · Computer Science 2023-09-06 Yi-Cheng Wang , Tzu-Ting Yang , Hsin-Wei Wang , Bi-Cheng Yan , Berlin Chen

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of…

Computation and Language · Computer Science 2024-04-16 Mukul Gagrani , Raghavv Goel , Wonseok Jeon , Junyoung Park , Mingu Lee , Christopher Lott

Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs' significant parameter size and autoregressive (AR) decoding nature impose considerable…

Machine Learning · Computer Science 2025-09-23 Songsheng Wang , Rucheng Yu , Zhihang Yuan , Chao Yu , Feng Gao , Yu Wang , Derek F. Wong

The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the…

Sound · Computer Science 2020-08-14 Dipjyoti Paul , Muhammed PV Shifas , Yannis Pantazis , Yannis Stylianou

Semantic communication is a promising technology to improve communication efficiency by transmitting only the semantic information of the source data. However, traditional semantic communication methods primarily focus on data…

Sound · Computer Science 2024-10-07 Jiahao Zheng , Jinke Ren , Peng Xu , Zhihao Yuan , Jie Xu , Fangxin Wang , Gui Gui , Shuguang Cui

Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Although these models can generate speech with high quality and…

Sound · Computer Science 2024-08-30 Zehai Tu , Guangyan Zhang , Yiting Lu , Adaeze Adigwe , Simon King , Yiwen Guo

Traditional speech systems typically rely on separate, task-specific models for text-to-speech (TTS), automatic speech recognition (ASR), and voice conversion (VC), resulting in fragmented pipelines that limit scalability, efficiency, and…

Sound · Computer Science 2026-01-19 Runyuan Cai , Yu Lin , Yiming Wang , Chunlin Fu , Xiaodong Zeng

Speculative decoding accelerates LLM inference by using a fast draft model to generate tokens and a more accurate target model to verify them. Its performance depends on the $\textit{acceptance length}$, or number of draft tokens accepted…

Computation and Language · Computer Science 2026-05-20 Avinash Kumar , Sujay Sanghavi , Poulami Das