English
Related papers

Related papers: Cross-Scale Vector Quantization for Scalable Neura…

200 papers

Quantization in SSL speech models (e.g., HuBERT) improves compression and performance in tasks like language modeling, resynthesis, and text-to-speech but often discards prosodic and paralinguistic information (e.g., emotion, prominence).…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-22 Nicholas Sanders , Yuanchao Li , Korin Richmond , Simon King

High-quality singing annotations are fundamental to modern Singing Voice Synthesis (SVS) systems. However, obtaining these annotations at scale through manual labeling is unrealistic due to the substantial labor and musical expertise…

Sound · Computer Science 2026-05-07 Yukun Chen , Tianrui Wang , Zhaoxi Mu , Xinyu Yang , EngSiong Chng

This paper proposes a novel vision-integrated neural speech codec (VNSC), which aims to enhance speech coding quality by leveraging visual modality information. In VNSC, the image analysis-synthesis module extracts visual features from lip…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-30 Yao Guo , Yang Ai , Rui-Chen Zheng , Hui-Peng Du , Xiao-Hang Jiang , Zhen-Hua Ling

Neural audio codec (NAC) is essential for reconstructing high-quality speech signals and generating discrete representations for downstream speech language models. However, ensuring accurate semantic modeling while maintaining high-fidelity…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-03 Yanzhou Ren , Noboru Harada , Daiki Takeuchi , Siyu Chen , Wei Liu , Xiao Zhang , Liyuan Zhang , Takehiro Moriya , Shoji Makino

Recently end-to-end neural audio/speech coding has shown its great potential to outperform traditional signal analysis based audio codecs. This is mostly achieved by following the VQ-VAE paradigm where blind features are learned,…

Sound · Computer Science 2023-02-28 Xue Jiang , Xiulian Peng , Yuan Zhang , Yan Lu

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Lianli Gao , Xiaosu Zhu , Jingkuan Song , Zhou Zhao , Heng Tao Shen

Speech super-resolution (SR) is a task to increase speech sampling rate by generating high-frequency components. Existing speech SR methods are trained in constrained experimental settings, such as a fixed upsampling ratio. These strong…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-10 Haohe Liu , Woosung Choi , Xubo Liu , Qiuqiang Kong , Qiao Tian , DeLiang Wang

In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with…

Sound · Computer Science 2026-05-20 Junyi Wang , Chi Zhang , Jing Qian , Haifeng Luo , Hao Wang , Zengrui Jin , Chao Zhang

Neural audio coding has been shown to outperform classical audio coding at extremely low bitrates. However, the practical application of neural audio codecs is still limited by their elevated complexity. To address this challenge, we have…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-20 Jiawei Jiang , Linping Xu , Dejun Zhang , Qingbo Huang , Xianjun Xia , Yijian Xiao

Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data. Recently, self-supervised learning of speech representation…

Sound · Computer Science 2022-02-14 Trung Dang , Dung Tran , Peter Chin , Kazuhito Koishida

The data representation in a machine-learning model strongly influences its performance. This becomes even more important for quantum machine learning models implemented on noisy intermediate scale quantum (NISQ) devices. Encoding high…

Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription accuracy. However, the biasing mechanism is typically based on a cross-attention module between the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-05 Nikolaos Flemotomos , Roger Hsiao , Pawel Swietojanski , Takaaki Hori , Dogan Can , Xiaodan Zhuang

The continuous quadratures of a single mode of the light field present a promising avenue to encode quantum information. By virtue of the infinite dimensionality of the associated Hilbert space, quantum states of these continuous variables…

Quantum Physics · Physics 2023-01-24 Ian Tillman , Thirupathaiah Vasantam , Kaushik P. Seshadreesan

Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. While post-training quantization (PTQ) has successfully…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Shubhang Bhatnagar , Andy Xu , Kar-Han Tan , Narendra Ahuja

Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded audio signals. For neural audio codecs, however, the…

Sound · Computer Science 2021-01-05 Kai Zhen , Mi Suk Lee , Jongmo Sung , Seungkwon Beack , Minje Kim

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

Straight-through estimator (STE), which enables the gradient flow over the non-differentiable function via approximation, has been favored in studies related to quantization-aware training (QAT). However, STE incurs unstable convergence…

Machine Learning · Computer Science 2023-07-04 Juncheol Shin , Junhyuk So , Sein Park , Seungyeop Kang , Sungjoo Yoo , Eunhyeok Park

Language mismatch is among the most common and challenging domain mismatches in deploying speaker verification (SV) systems. Adversarial reprogramming has shown promising results in cross-language adaptation for SV. The reprogramming is…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-09 Jingyu Li , Aemon Yat Fei Chiu , Tan Lee

Quantum sensing is an important application of emerging quantum technologies. We explore whether a hybrid system of quantum sensors and quantum circuits can surpass the classical limit of sensing. In particular, we use optimization…

Neural audio codecs have recently enabled high-fidelity reconstruction at high compression rates, especially for speech. However, speech and non-speech audio exhibit fundamentally different spectral characteristics: speech energy…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-11 Haoran Wang , Jiatong Shi , Jinchuan Tian , Bohan Li , Kai Yu , Shinji Watanabe