English
Related papers

Related papers: SNAC: Multi-Scale Neural Audio Codec

200 papers

We present STFTCodec, a novel spectral-based neural audio codec that efficiently compresses audio using Short-Time Fourier Transform (STFT). Unlike waveform-based approaches that require large model capacity and substantial memory…

Sound · Computer Science 2025-03-24 Tao Feng , Zhiyuan Zhao , Yifan Xie , Yuqi Ye , Xiangyang Luo , Xun Guan , Yu Li

In the development of spatial audio technologies, reliable and shared methods for evaluating audio quality are essential. Listening tests are currently the standard but remain costly in terms of time and resources. Several models predicting…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-21 Adrien Llave , Emma Granier , Grégory Pallone

A learning-based framework for representation of domain-specific images is proposed where joint compression and denoising can be done using a VQ-based multi-layer network. While it learns to compress the images from a training set, the…

Computer Vision and Pattern Recognition · Computer Science 2017-07-10 Sohrab Ferdowsi , Slava Voloshynovskiy , Dimche Kostadinov

Modern speaker verification (SV) systems typically demand expensive storage and computing resources, thereby hindering their deployment on mobile devices. In this paper, we explore adaptive neural network quantization for lightweight…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-03 Bei Liu , Haoyu Wang , Yanmin Qian

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

Neural speech codecs have recently emerged as a focal point in the fields of speech compression and generation. Despite this progress, achieving high-quality speech reconstruction under low-bitrate scenarios remains a significant challenge.…

Sound · Computer Science 2024-11-22 Yu Pan , Xiang Zhang , Yuguang Yang , Jixun Yao , Yanni Hu , Jianhao Ye , Hongbin Zhou , Lei Ma , Jianjun Zhao

Spectral sub-bands do not portray the same perceptual relevance. In audio coding, it is therefore desirable to have independent control over each of the constituent bands so that bitrate assignment and signal reconstruction can be achieved…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-15 Darius Petermann , Inseon Jang , Minje Kim

In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network. A challenging problem as such results in unwelcome complexity increase and inferior…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-16 Haici Yang , Inseon Jang , Minje Kim

Neural speech codecs excel in reconstructing clean speech signals; however, their efficacy in complex acoustic environments and downstream signal processing tasks remains underexplored. In this study, we introduce a novel benchmark named…

Sound · Computer Science 2025-05-29 Haoran Wang , Guanyu Chen , Bohan Li , Hankun Wang , Yiwei Guo , Zhihan Li , Xie Chen , Kai Yu

We introduce a practical real-time neural video codec (NVC) designed to deliver high compression ratio, low latency and broad versatility. In practice, the coding speed of NVCs depends on 1) computational costs, and 2) non-computational…

Image and Video Processing · Electrical Eng. & Systems 2025-03-19 Zhaoyang Jia , Bin Li , Jiahao Li , Wenxuan Xie , Linfeng Qi , Houqiang Li , Yan Lu

Latent representation learning has been an active field of study for decades in numerous applications. Inspired among others by the tokenization from Natural Language Processing and motivated by the research of a simple data representation,…

Signal Processing · Electrical Eng. & Systems 2024-09-26 Benoît Giniès , Xiaoyu Bie , Olivier Fercoq , Gaël Richard

Neural audio codec tokens serve as the fundamental building blocks for speech language model (SLM)-based speech generation. However, there is no systematic understanding on how the codec system affects the speech generation performance of…

In neural-based audio feature extraction, ensuring that representations capture disentangled information is crucial for model interpretability. However, existing disentanglement methods often rely on assumptions that are highly dependent on…

Sound · Computer Science 2025-10-07 Benoit Ginies , Xiaoyu Bie , Olivier Fercoq , Gaël Richard

Recent advances in spatially selective active noise control (SSANC) using multiple microphones have enabled hearables to suppress undesired noise while preserving desired speech from a specific direction. Aiming to achieve minimal speech…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-18 Tong Xiao , Reinhild Roden , Matthias Blau , Simon Doclo

In this paper, we propose an image re-sampling compression method by learning virtual codec network (VCN) to resolve the non-differentiable problem of quantization function for image compression. Here, the image re-sampling not only refers…

Image and Video Processing · Electrical Eng. & Systems 2018-07-11 Lijun Zhao , Huihui Bai , Anhong Wang , Yao Zhao

While neural-based models have led to significant advancements in audio feature extraction, the interpretability of the learned representations remains a critical challenge. To address this, disentanglement techniques have been integrated…

Sound · Computer Science 2025-10-07 Benoît Giniès , Xiaoyu Bie , Olivier Fercoq , Gaël Richard

Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio…

Most neural speech codecs achieve bitrate adjustment through intra-frame mechanisms, such as codebook dropout, at a Constant Frame Rate (CFR). However, speech segments inherently have time-varying information density (e.g., silent intervals…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-09 Hanglei Zhang , Yiwei Guo , Zhihan Li , Xiang Hao , Xie Chen , Kai Yu

Discrete audio tokenizers are fundamental to empowering large language models with native audio processing and generation capabilities. Despite recent progress, existing approaches often rely on pretrained encoders, semantic distillation,…

For a large number of tasks, quantum computing demonstrates the potential for exponential acceleration over classical computing. In the NISQ era, variable-component subcircuits enable applications of quantum computing. To reduce the…

Quantum Physics · Physics 2022-12-12 Junhan Qin
‹ Prev 1 8 9 10 Next ›