English
Related papers

Related papers: SoCodec: A Semantic-Ordered Multi-Stream Speech Co…

200 papers

Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-12 Xuan Shi , Chang Zeng , Tiantian Feng , Shih-Heng Wang , Jianbo Ma , Shrikanth Narayanan

This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based sequence-to-sequence acoustic model and the LPCNet vocoder…

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Thai-Son Nguyen , Ngoc-Quan Pham , Sebastian Stueker , Alex Waibel

The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexible trade-offs between speed and quality during inference…

Recent years have witnessed a trend that large language model (LLM) based text-to-speech (TTS) emerges into the mainstream due to their high naturalness and zero-shot capacity. In this paradigm, speech signals are discretized into token…

Current text-to-speech (TTS) models face a persistent limitation: autoregressive (AR) models suffer from low generation efficiency, while modern non-autoregressive (NAR) models experience high latency due to their unordered temporal nature.…

Sound · Computer Science 2026-03-17 Zhengyan Sheng , Zhihao Du , Shiliang Zhang , Zhijie Yan , Liping Chen

Language models require tokenized inputs. However, tokenization strategies for continuous data like audio and vision are often based on simple heuristics such as fixed sized convolutions or discrete clustering, which do not necessarily…

Computation and Language · Computer Science 2024-10-08 Alan Baade , Puyuan Peng , David Harwath

We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-24 Hyeongju Kim , Jinhyeok Yang , Yechan Yu , Seunghun Ji , Jacob Morton , Frederik Bous , Joon Byun , Juheon Lee

While existing speech audio codecs designed for compression exploit limited forms of temporal redundancy and allow for multi-scale representations, they tend to represent all features of audio in the same way. In contrast, generative voice…

Sound · Computer Science 2025-09-22 Ryan Collette , Ross Greenwood , Serena Nicoll

Modern sequence to sequence neural TTS systems provide close to natural speech quality. Such systems usually comprise a network converting linguistic/phonetic features sequence to an acoustic features sequence, cascaded with a neural…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-26 Slava Shechtman , Alex Sorin

With the rapid advancement of large language models (LLMs), discrete speech representations have become crucial for integrating speech into LLMs. Existing methods for speech representation discretization rely on a predefined codebook size…

Sound · Computer Science 2025-01-03 Linqin Wang , Yaping Liu , Zhengtao Yu , Shengxiang Gao , Cunli Mao , Yuxin Huang , Wenjun Wang , Ling Dong

Although text-to-speech (TTS) systems have significantly improved, most TTS systems still have limitations in synthesizing speech with appropriate phrasing. For natural speech synthesis, it is important to synthesize the speech with a…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-14 Ji-Sang Hwang , Sang-Hoon Lee , Seong-Whan Lee

Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio. High-quality spectrum models usually…

Sound · Computer Science 2021-04-05 Qing He , Zhiping Xiu , Thilo Koehler , Jilong Wu

Large language models (LLMs) have demonstrated remarkable capabilities in tasks requiring reasoning and multi-step problem-solving through the use of chain-of-thought (CoT) prompting. However, generating the full CoT process results in…

Computation and Language · Computer Science 2024-09-16 Tianqiao Liu , Zui Chen , Zitao Liu , Mi Tian , Weiqi Luo

Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low…

Sound · Computer Science 2022-02-16 Xue Jiang , Xiulian Peng , Chengyu Zheng , Huaying Xue , Yuan Zhang , Yan Lu

Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In this paper, we propose…

Computation and Language · Computer Science 2018-08-31 Yu-An Chung , Yuxuan Wang , Wei-Ning Hsu , Yu Zhang , RJ Skerry-Ryan

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-05 Tao Tu , Yuan-Jui Chen , Alexander H. Liu , Hung-yi Lee

Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-annotated transcripts and translations. However, the…

Computation and Language · Computer Science 2024-10-28 Peter Polák , Ondřej Bojar

Although discrete speech tokens have exhibited strong potential for language model-based speech generation, their high bitrates and redundant timbre information restrict the development of such models. In this work, we propose LSCodec, a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-22 Yiwei Guo , Zhihan Li , Chenpeng Du , Hankun Wang , Xie Chen , Kai Yu

Discrete speech tokenization is a fundamental component in speech codecs. However, in large-scale speech-to-speech systems, the complexity of parallel streams from multiple quantizers and the computational cost of high-time-dimensional…

Sound · Computer Science 2025-07-28 Rongkun Xue , Yazhe Niu , Shuai Hu , Zixin Yin , Yongqiang Yao , Jing Yang