English
Related papers

Related papers: Vec-Tok Speech: speech vectorization and tokenizat…

200 papers

Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in response generation latency: (1) generating a spoken response…

Computation and Language · Computer Science 2024-10-04 Kentaro Mitsui , Koh Mitsuda , Toshiaki Wakatsuki , Yukiya Hono , Kei Sawada

Recently, neural vocoders have been widely used in speech synthesis tasks, including text-to-speech and voice conversion. However, when encountering data distribution mismatch between training and inference, neural vocoders trained on real…

Sound · Computer Science 2020-08-21 Po-chun Hsu , Chun-hsuan Wang , Andy T. Liu , Hung-yi Lee

The neural codec language model (CLM) has demonstrated remarkable performance in text-to-speech (TTS) synthesis. However, troubled by ``recency bias", CLM lacks sufficient attention to coarse-grained information at a higher temporal scale,…

Sound · Computer Science 2024-09-19 Haohan Guo , Fenglong Xie , Dongchao Yang , Xixin Wu , Helen Meng

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…

We propose a decoder-only language model, VoxtLM, that can perform four tasks: speech recognition, speech synthesis, text generation, and speech continuation. VoxtLM integrates text vocabulary with discrete speech tokens from…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-25 Soumi Maiti , Yifan Peng , Shukjae Choi , Jee-weon Jung , Xuankai Chang , Shinji Watanabe

Recent advances in text-to-speech (TTS) synthesis, such as Tacotron and WaveRNN, have made it possible to construct a fully neural network based TTS system, by coupling the two components together. Such a system is conceptually simple as it…

We propose \textbf{U-Codec}, an \textbf{U}ltra low frame-rate neural speech \textbf{Codec} that achieves high-fidelity reconstruction and fast speech generation at an extremely low frame-rate of 5Hz (5 frames per second). Extreme…

Sound · Computer Science 2025-10-21 Xusheng Yang , Long Zhou , Wenfu Wang , Kai Hu , Shulin Feng , Chenxing Li , Meng Yu , Dong Yu , Yuexian Zou

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

Computation and Language · Computer Science 2025-08-22 Dong Liu , Yanxuan Yu

Existing speech tokenizers typically assign a fixed number of tokens per second, regardless of the varying information density or temporal fluctuations in the speech signal. This uniform token allocation mismatches the intrinsic structure…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-14 Rui-Chen Zheng , Wenrui Liu , Hui-Peng Du , Qinglin Zhang , Chong Deng , Qian Chen , Wen Wang , Yang Ai , Zhen-Hua Ling

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization, which involves efficiently transforming input visual signals into…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Shengqiong Wu , Hao Fei , Xiangtai Li , Jiayi Ji , Hanwang Zhang , Tat-Seng Chua , Shuicheng Yan

Codec-based language models (LMs) have revolutionized text-to-speech (TTS). However, standard codecs entangle timbre and prosody, which hinders independent control in continuation-based LMs. To tackle this challenge, we propose…

Sound · Computer Science 2026-01-06 Tao Li , Wenshuo Ge , Zhichao Wang , Zihao Cui , Yong Ma , Yingying Gao , Chao Deng , Shilei Zhang , Junlan Feng

Vector representation of sentences is important for many text processing tasks that involve clustering, classifying, or ranking sentences. Recently, distributed representation of sentences learned by neural models from unlabeled data has…

Computation and Language · Computer Science 2016-10-27 Tanay Kumar Saha , Shafiq Joty , Naeemul Hassan , Mohammad Al Hasan

This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-16 Vladimir Bataev , Subhankar Ghosh , Vitaly Lavrukhin , Jason Li

While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming. Previous studies on automatic speech quality assessment address the problem by predicting human…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-12 Soumi Maiti , Yifan Peng , Takaaki Saeki , Shinji Watanabe

Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from…

In recent years, speech generation has seen remarkable progress, now achieving one-shot generation capability that is often virtually indistinguishable from real human voice. Integrating such advancements in speech generation with large…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-08 Paweł Budzianowski , Taras Sereda , Tomasz Cichy , Ivan Vulić

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

Recently, large-scale pre-trained speech encoders and Large Language Models (LLMs) have been released, which show state-of-the-art performance on a range of spoken language processing tasks including Automatic Speech Recognition (ASR). To…

Computation and Language · Computer Science 2025-05-19 Rao Ma , Tongzhou Chen , Kartik Audhkhasi , Bhuvana Ramabhadran

In real-world voice conversion applications, environmental noise in source speech and user demands for expressive output pose critical challenges. Traditional ASR-based methods ensure noise robustness but suppress prosody richness, while…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-11 Yuepeng Jiang , Ziqian Ning , Shuai Wang , Chengjia Wang , Mengxiao Bi , Pengcheng Zhu , Zhonghua Fu , Lei Xie

In voice conversion (VC), it is crucial to preserve complete semantic information while accurately modeling the target speaker's timbre and prosody. This paper proposes FabasedVC to achieve VC with enhanced similarity in timbre, prosody,…

Sound · Computer Science 2025-11-14 Wenyu Wang , Zhetao Hu , Yiquan Zhou , Jiacheng Xu , Zhiyu Wu , Chen Li , Shihao Li