English
Related papers

Related papers: MMW: Side Talk Rejection Multi-Microphone Whisper …

200 papers

Recently cross-channel attention, which better leverages multi-channel signals from microphone array, has shown promising results in the multi-party meeting scenario. Cross-channel attention focuses on either learning global correlations…

Sound · Computer Science 2022-10-12 Fan Yu , Shiliang Zhang , Pengcheng Guo , Yuhao Liang , Zhihao Du , Yuxiao Lin , Lei Xie

Speech enhancement (SE) is critical for improving speech intelligibility and quality in real-world environments, particularly for cochlear implant (CI) users who experience severe degradations in speech understanding under noisy and…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-15 Hsin-Tien Chiang , John H. L. Hansen

Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance, a phenomenon we term studio-bias. To diagnose this mismatch, we introduce Vividh-ASR, a…

Computation and Language · Computer Science 2026-05-14 Kush Juvekar , Kavya Manohar , Aditya Srinivas Menon , Arghya Bhattacharya , Kumarmanas Nethil

Fifth generation wireless systems are expected to employ multiple antenna communication at millimeter wave (mmWave) frequencies using small cells within heterogeneous cellular networks. The high path loss of mmWave as well as physical…

Information Theory · Computer Science 2015-05-19 Jiho Song , Junil Choi , Stephen G. Larew , David J. Love , Timothy A. Thomas , Amitava Ghosh

Multimodal Large Language Models (MLLMs) have played an increasingly important role in multimodal intelligence. However, the existing fine-tuning methods often ignore cross-modal heterogeneity, limiting their full potential. In this work,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Ruishu Zhu , Sida Huang , Ziheng Jiao , Hongyuan Zhang

This paper introduces a novel low-latency online beamforming (BF) algorithm, named Modified Parametric Multichannel Wiener Filter (Mod-PMWF), for enhancing speech mixtures with unknown and varying number of speakers. Although conventional…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-03 Ning Guo , Tomohiro Nakatani , Shoko Araki , Takehiro Moriya

Edge-based automatic speech recognition (ASR) technologies are increasingly prevalent in the development of intelligent and personalized assistants. However, resource-constrained ASR models face significant challenges in adaptivity,…

Computation and Language · Computer Science 2024-12-24 Amir Nassereldine , Dancheng Liu , Chenhui Xu , Ruiyang Qin , Yiyu Shi , Jinjun Xiong

The increasing number of microphone-equipped personal devices offers great flexibility and potential using them as ad-hoc microphone arrays in dynamic meeting environments. However, most existing approaches are designed for…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-23 Gene-Ping Yang , Sebastian Braun

3D object detection is critical for autonomous driving, yet it remains fundamentally challenging to simultaneously maximize computational efficiency and capture long-range spatial dependencies. We observed that Mamba-based models, with…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Longhui Zheng , Qiming Xia , Xiaolu Chen , Zhaoliang Liu , Chenglu Wen

Recent advances in large audio language models (LALMs) have primarily been assessed using a multiple-choice question answering (MCQA) framework. However, subtle changes, such as shifting the order of choices, result in substantially…

Computation and Language · Computer Science 2025-10-07 Fernando López , Santosh Kesiraju , Jordi Luque

While recent progresses in neural network approaches to single-channel speech separation, or more generally the cocktail party problem, achieved significant improvement, their performance for complex mixtures is still not satisfactory. In…

Sound · Computer Science 2018-03-30 Zhuo Chen , Jinyu Li , Xiong Xiao , Takuya Yoshioka , Huaming Wang , Zhenghao Wang , Yifan Gong

The performance of keyword spotting (KWS), measured in false alarms and false rejects, degrades significantly under the far field and noisy conditions. In this paper, we propose a multi-look neural network modeling for speech enhancement…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-22 Meng Yu , Xuan Ji , Bo Wu , Dan Su , Dong Yu

The goal of this work is to develop a meeting transcription system that can recognize speech even when utterances of different speakers are overlapped. While speech overlaps have been regarded as a major obstacle in accurately transcribing…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-10 Takuya Yoshioka , Hakan Erdogan , Zhuo Chen , Xiong Xiao , Fil Alleva

To support faster and more efficient networks, mobile operators and service providers are bringing 5G millimeter wave (mmWave) networks indoors. However, due to their high directionality, mmWave links are extremely vulnerable to blockage by…

Signal Processing · Electrical Eng. & Systems 2021-02-03 Kun Woo Cho , Mohammad Hossein Mazaheri , Jeremy Gummeson , Omid Abari , Kyle Jamieson

State Space Models (SSMs) have emerged as efficient alternatives to Transformers for sequential modeling, but their inability to leverage modality-specific features limits their performance in multi-modal pretraining. Here, we propose…

Machine Learning · Computer Science 2025-01-28 Weixin Liang , Junhong Shen , Genghan Zhang , Ning Dong , Luke Zettlemoyer , Lili Yu

Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, we obtain a speaker embedding vector by pooling single-scale features that are extracted from the last layer of a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-09 Youngmoon Jung , Seong Min Kye , Yeunju Choi , Myunghun Jung , Hoirin Kim

In real-world applications, it is challenging to build a speaker verification system that is simultaneously robust against common threats, including spoofing attacks, channel mismatch, and domain mismatch. Traditional automatic speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-11 Chang Zeng , Xiaoxiao Miao , Xin Wang , Erica Cooper , Junichi Yamagishi

Social interactions play a crucial role in shaping human behavior, relationships, and societies. It encompasses various forms of communication, such as verbal conversation, non-verbal gestures, facial expressions, and body language. In this…

Machine Learning · Computer Science 2026-05-13 Alice Zhang , Callihan Bertley , Dawei Liang , Edison Thomaz

In the scenario with reverberation, the experience of human-machine interaction will become worse. In order to solve this problem, many methods for the dereverberation have emerged. At present, how to update the parameters of the Kalman…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-29 Fengqi Tan , Changchun Bao

Deep learning has made many remarkable achievements in many fields but suffers from noisy labels in datasets. The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label by mutual-information…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Jiarun Liu , Daguang Jiang , Yukun Yang , Ruirui Li