English
Related papers

Related papers: Generative De-Quantization for Neural Speech Codec…

200 papers

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…

Computation and Language · Computer Science 2017-09-15 Yonatan Belinkov , James Glass

Generative image codecs aim to optimize perceptual quality, producing realistic and detailed reconstructions. However, they often overlook a key property of human vision: our tendency to focus on particular aspects of a visual scene (e.g.,…

Image and Video Processing · Electrical Eng. & Systems 2026-04-02 Lucas Relic , Roberto Azevedo , Yang Zhang , Stephan Mandt , Markus Gross , Christopher Schroers

This paper introduces a discrete diffusion model (DDM) framework for text-aligned speech tokenization and reconstruction. By replacing the auto-regressive speech decoder with a discrete diffusion counterpart, our model achieves…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-25 Pin-Jui Ku , He Huang , Jean-Marie Lemercier , Subham Sekhar Sahoo , Zhehuai Chen , Ante Jukić

Semantic communication is expected to be one of the cores of next-generation AI-based communications. One of the possibilities offered by semantic communication is the capability to regenerate, at the destination side, images or videos…

Artificial Intelligence · Computer Science 2026-05-18 Eleonora Grassucci , Sergio Barbarossa , Danilo Comminiello

High-fidelity neural audio codecs in Text-to-speech (TTS) aim to compress speech signals into discrete representations for faithful reconstruction. However, prior approaches faced challenges in effectively disentangling acoustic and…

Sound · Computer Science 2025-09-23 Ruonan Zhang , Xiaoyang Hao , Yichen Han , Junjie Cao , Yue Liu , Kai Zhang

Neural speech codecs have gained great attention for their outstanding reconstruction with discrete token representations. It is a crucial component in generative tasks such as speech coding and large language models (LLM). However, most…

Sound · Computer Science 2025-07-01 Youqiang Zheng , Weiping Tu , Yueteng Kang , Jie Chen , Yike Zhang , Li Xiao , Yuhong Yang , Long Ma

Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-30 Yang Yang , Yunpeng Li , George Sung , Shao-Fu Shih , Craig Dooley , Alessio Centazzo , Ramanan Rajeswaran

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…

Computation and Language · Computer Science 2017-11-23 Dinghan Shen , Yizhe Zhang , Ricardo Henao , Qinliang Su , Lawrence Carin

Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Ivan Skorokhodov , Sharath Girish , Benran Hu , Willi Menapace , Yanyu Li , Rameen Abdal , Sergey Tulyakov , Aliaksandr Siarohin

Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-15 Tianhui Su , Tien-Ping Tan , Salima Mdhaffar , Yannick Estève , Aghilas Sini

Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-02 Wenrui Liu , Qian Chen , Wen Wang , Yafeng Chen , Jin Xu , Zhifang Guo , Guanrou Yang , Weiqin Li , Xiaoda Yang , Tao Jin , Minghui Fang , Jialong Zuo , Bai Jionghao , Zemin Liu

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Robin Rombach , Andreas Blattmann , Dominik Lorenz , Patrick Esser , Björn Ommer

Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms…

Generative models have demonstrated strong performance in conditional settings and can be viewed as a form of data compression, where the condition serves as a compact representation. However, their limited controllability and…

Machine Learning · Computer Science 2025-07-04 Xiao Li , Liangji Zhu , Anand Rangarajan , Sanjay Ranka

Spatial frequency analysis and transforms serve a central role in most engineered image and video lossy codecs, but are rarely employed in neural network (NN)-based approaches. We propose a novel NN-based image coding framework that…

Image and Video Processing · Electrical Eng. & Systems 2023-01-04 Hyomin Choi , Fabien Racape , Shahab Hamidi-Rad , Mateen Ulhaq , Simon Feltman

Neural audio codecs form the foundational building blocks for language model (LM)-based speech generation. Typically, there is a trade-off between frame rate and audio quality. This study introduces a low-frame-rate, semantically enhanced…

Sound · Computer Science 2025-10-02 Jiaqi Li , Xiaolong Lin , Zhekai Li , Shixi Huang , Yuancheng Wang , Chaoren Wang , Zhenpeng Zhan , Zhizheng Wu

In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion. We propose to first encode speech signals into a phoneme-rate latent representation with a variational autoencoder enhanced by adversarial training,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-25 Zhijun Liu , Yiwei Guo , Kai Yu

High-quality speech corpora are essential foundations for most speech applications. However, such speech data are expensive and limited since they are collected in professional recording environments. In this work, we propose an…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-11 Haoyu Li , Yang Ai , Junichi Yamagishi

While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Chuqin Zhou , Xiaoyue Ling , Yunuo Chen , Jincheng Dai , Guo Lu , Wenjun Zhang

It is a known problem that deep-learning-based end-to-end (E2E) channel coding systems depend on a known and differentiable channel model, due to the learning process and based on the gradient-descent optimization methods. This places the…

Information Theory · Computer Science 2023-11-30 Muah Kim , Rick Fritschek , Rafael F. Schaefer