English
Related papers

Related papers: Dynamic Chunk Convolution for Unified Streaming an…

200 papers

Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored for modern deep neural network end-to-end model…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-15 Timo Lohrenz , Zhengyang Li , Tim Fingscheidt

Large-batch Contrastive Learning (CL), the foundation of modern representation learning, is fundamentally incompatible with the volatile resource constraints of edge devices. This conflict creates a dilemma: small on-device batches degrade…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-27 Minh K. Quan , Pubudu N. Pathirana

Contextual biasing (CB) improves automatic speech recognition for rare and unseen phrases. Recent studies have introduced dynamic vocabulary, which represents context phrases as expandable tokens in autoregressive (AR) models. This method…

Computation and Language · Computer Science 2025-06-04 Yui Sudo , Yosuke Fukumoto , Muhammad Shakeel , Yifan Peng , Chyi-Jiunn Lin , Shinji Watanabe

Audio-visual recognition (AVR) has been considered as a solution for speech recognition tasks when the audio is corrupted, as well as a visual recognition method used for speaker verification in multi-speaker scenarios. The approach of AVR…

Computer Vision and Pattern Recognition · Computer Science 2017-11-01 Amirsina Torfi , Seyed Mehdi Iranmanesh , Nasser M. Nasrabadi , Jeremy Dawson

Dynamic Adaptive Streaming over HTTP (DASH) has emerged as an increasingly popular paradigm for video streaming [13], in which a video is segmented into many chunks delivered to users by HTTP request/response over Transmission Control…

Multimedia · Computer Science 2016-07-06 Wen Hu , Zhi Wang , Lifeng Sun

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

Sound · Computer Science 2023-08-16 Tianyi Xu , Zhanheng Yang , Kaixun Huang , Pengcheng Guo , Ao Zhang , Biao Li , Changru Chen , Chao Li , Lei Xie

It is difficult for an E2E ASR system to recognize words such as entities appearing infrequently in the training data. A widely used method to mitigate this issue is feeding contextual information into the acoustic model. Previous works…

Sound · Computer Science 2023-06-09 Zhanheng Yang , Sining Sun , Xiong Wang , Yike Zhang , Long Ma , Lei Xie

Conformer, combining convolution and self-attention sequentially to capture both local and global information, has shown remarkable performance and is currently regarded as the state-of-the-art for automatic speech recognition (ASR).…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-18 Kwangyoun Kim , Felix Wu , Yifan Peng , Jing Pan , Prashant Sridhar , Kyu J. Han , Shinji Watanabe

Federated learning (FL) scenarios inherently generate a large communication overhead by frequently transmitting neural network updates between clients and server. To minimize the communication cost, introducing sparsity in conjunction with…

Machine Learning · Computer Science 2022-04-12 Daniel Becking , Heiner Kirchhoffer , Gerhard Tech , Paul Haase , Karsten Müller , Heiko Schwarz , Wojciech Samek

Current continuous sign language recognition (CSLR) methods struggle with handling diverse samples. Although dynamic convolutions are ideal for this task, they mainly focus on spatial modeling and fail to capture the temporal dynamics and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Sheng Liu , Yiheng Yu , Yuan Feng , Min Xu , Zhelun Jin , Yining Jiang , Tiantian Yuan

Recent works have shown that prompting large language models with audio encodings can unlock speech recognition capabilities. However, existing techniques do not scale efficiently, especially while handling long form streaming audio inputs…

The dual-stream transformer architecture-based joint audio-video generation method has become the dominant paradigm in current research. By incorporating pre-trained video diffusion models and audio diffusion models, along with a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Bingqi Ma , Linlong Lang , Ming Zhang , Dailan He , Xingtong Ge , Yi Zhang , Guanglu Song , Yu Liu

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within this framework remains a challenge. In this work, we propose…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-02 Genshun Wan , Wenhui Zhang , Jing-Xuan Zhang , Shifu Xiong , Jianqing Gao , Zhongfu Ye

Recently, the cascaded two-pass architecture has emerged as a strong contender for on-device automatic speech recognition (ASR). A cascade of causal and shallow non-causal encoders coupled with a shared decoder enables operation in both…

Online 3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage. Although causal variants of VGGT address this challenge through a key-value (KV) cache mechanism, the cache grows…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Runze Wang , Yuxuan Song , Youcheng Cai , Ligang Liu

Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear in symmetric and rigid kernels by the conventional CNN…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-19 Jiamin Xie , John H. L. Hansen

In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework. In particular, we derive new context vectors using time…

Computation and Language · Computer Science 2018-03-16 Amit Das , Jinyu Li , Rui Zhao , Yifan Gong

Real-time streaming joint audio-video generation for character animation requires a generator to speak the requested transcript, maintain visual identity across chunks, and run within a strict playback budget. These requirements are…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Linrui Tian , Qi Wang , Bang Zhang

Current multichannel speech enhancement algorithms typically assume a stationary sound source, a common mismatch with reality that limits their performance in real-world scenarios. This paper focuses on attention-driven spatial filtering…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-19 Yuzhu Wang , Archontis Politis , Tuomas Virtanen

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-27 Mingyu Cui , Jiawen Kang , Jiajun Deng , Xi Yin , Yutao Xie , Xie Chen , Xunying Liu