English
Related papers

Related papers: Attention and DCT based Global Context Modeling fo…

200 papers

In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers. Inspired by the recent success of deep neural networks (DNNs) in semantic inferencing, triplet…

Audio and Speech Processing · Electrical Eng. & Systems 2018-08-07 Huan Song , Megan Willi , Jayaraman J. Thiagarajan , Visar Berisha , Andreas Spanias

In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the selfattention mechanism. Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention…

Computer Vision and Pattern Recognition · Computer Science 2019-04-23 Jun Fu , Jing Liu , Haijie Tian , Yong Li , Yongjun Bao , Zhiwei Fang , Hanqing Lu

Properly setting up recording conditions, including microphone type and placement, room acoustics, and ambient noise, is essential to obtaining the desired acoustic characteristics of speech. In this paper, we propose Diff-R-EN-T, a…

Sound · Computer Science 2024-01-17 Jaekwon Im , Juhan Nam

In this paper, we propose Dynamic Compressive Transformer (DCT), a transformer-based framework for modeling the unbounded sequence. In contrast to the previous baselines which append every sentence representation to memory, conditionally…

Computation and Language · Computer Science 2021-10-12 Kai-Po Chang , Wei-Yun Ma

Most existing named entity recognition (NER) approaches are based on sequence labeling models, which focus on capturing the local context dependencies. However, the way of taking one sentence as input prevents the modeling of non-sequential…

Computation and Language · Computer Science 2021-06-03 Zanbo Wang , Wei Wei , Xianling Mao , Shanshan Feng , Pan Zhou , Zhiyong He , Sheng Jiang

Long-context modeling has drawn more and more attention in the area of Large Language Models (LLMs). Continual training with long-context data becomes the de-facto method to equip LLMs with the ability to process long inputs. However, it…

Computation and Language · Computer Science 2025-10-14 Jianghao Chen , Junhong Wu , Yangyifan Xu , Jiajun Zhang

Speech recognition in cocktail-party environments remains a significant challenge for state-of-the-art speech recognition systems, as it is extremely difficult to extract an acoustic signal of an individual speaker from a background of…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-17 Guan-Lin Chao , William Chan , Ian Lane

Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically…

Computation and Language · Computer Science 2022-04-20 Ziyang Luo , Yadong Xi , Jing Ma , Zhiwei Yang , Xiaoxi Mao , Changjie Fan , Rongsheng Zhang

In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models (LLMs) significantly affects their performance in tasks demanding a high degree of context awareness, such as utilizing…

Computation and Language · Computer Science 2024-06-05 Yuhan Chen , Ang Lv , Ting-En Lin , Changyu Chen , Yuchuan Wu , Fei Huang , Yongbin Li , Rui Yan

This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the conditional independence assumptions used in conventional CTC…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-21 Yosuke Higuchi , Brian Yan , Siddhant Arora , Tetsuji Ogawa , Tetsunori Kobayashi , Shinji Watanabe

Adapting speaker recognition systems to new environments is a widely-used technique to improve a well-performing model learned from large-scale data towards a task-specific small-scale data scenarios. However, previous studies focus on…

Sound · Computer Science 2022-11-21 Zhenyu Wang , John H. L. Hansen

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Computation and Language · Computer Science 2025-09-23 Asif Shahriar , Rifat Shahriyar , M Saifur Rahman

Dynamic parameterization of acoustic environments has drawn widespread attention in the field of audio processing. Precise representation of local room acoustic characteristics is crucial when designing audio filters for various audio…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-26 Chunxi Wang , Maoshen Jia , Meiran Li , Changchun Bao , Wenyu Jin

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-02 Tianchi Liu , Kong Aik Lee , Qiongqiong Wang , Haizhou Li

Comparing with traditional text-to-speech (TTS) systems, conversational TTS systems are required to synthesize speeches with proper speaking style confirming to the conversational context. However, state-of-the-art context modeling methods…

Sound · Computer Science 2022-04-01 Jingbei Li , Yi Meng , Chenyi Li , Zhiyong Wu , Helen Meng , Chao Weng , Dan Su

Recent advances in video generation can produce realistic, minute-long single-shot videos with scalable diffusion transformers. However, real-world narrative videos require multi-shot scenes with visual and dynamic consistency across shots.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Yuwei Guo , Ceyuan Yang , Ziyan Yang , Zhibei Ma , Zhijie Lin , Zhenheng Yang , Dahua Lin , Lu Jiang

This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-15 Mingyu Cui , Mengzhe Geng , Jiajun Deng , Chengxi Deng , Jiawen Kang , Shujie Hu , Guinan Li , Tianzi Wang , Zhaoqing Li , Xie Chen , Xunying Liu

Conversational agents leveraging AI, particularly deep learning, are emerging in both academic research and real-world applications. However, these applications still face challenges, including disrespecting knowledge and facts, not…

Computation and Language · Computer Science 2025-03-25 Junfeng Liu , Zhuocheng Mei , Kewen Peng , Ranga Raju Vatsavai

Recently, the application of diffusion probabilistic models has advanced speech enhancement through generative approaches. However, existing diffusion-based methods have focused on the generation process in high-dimensional waveform or…

Sound · Computer Science 2025-01-20 Shengkui Zhao , Zexu Pan , Kun Zhou , Yukun Ma , Chong Zhang , Bin Ma

Semantic communications could improve the transmission efficiency significantly by exploring the semantic information. In this paper, we make an effort to recover the transmitted speech signals in the semantic communication systems, which…

Signal Processing · Electrical Eng. & Systems 2021-09-09 Zhenzi Weng , Zhijin Qin