中文
相关论文

相关论文: Unifying Speech Enhancement and Separation with Gr…

200 篇论文

Recent advancements in speaker verification techniques show promise, but their performance often deteriorates significantly in challenging acoustic environments. Although speech enhancement methods can improve perceived audio quality, they…

音频与语音处理 · 电气工程与系统科学 2025-08-27 Adam Katav , Yair Moshe , Israel Cohen

The CEEMDAN algorithm is one of the modern methods used in the analysis of non-stationary signals. This research presents a study of the effectiveness of this method in audio source separation to know the limits of its work. It concluded…

声音 · 计算机科学 2024-11-19 Rawad Melhem , Riad Hamadeh , Assef Jafar

Speech enhancement using neural networks is recently receiving large attention in research and being integrated in commercial devices and applications. In this work, we investigate data augmentation techniques for supervised deep…

音频与语音处理 · 电气工程与系统科学 2020-09-25 Sebastian Braun , Ivan Tashev

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

音频与语音处理 · 电气工程与系统科学 2023-02-24 Zhepei Wang , Ritwik Giri , Devansh Shah , Jean-Marc Valin , Michael M. Goodwin , Paris Smaragdis

When dealing with overlapped speech, the performance of automatic speech recognition (ASR) systems substantially degrades as they are designed for single-talker speech. To enhance ASR performance in conversational or meeting environments,…

音频与语音处理 · 电气工程与系统科学 2023-11-16 Hassan Taherian , DeLiang Wang

The primary objective of speech enhancement is to reduce background noise while preserving the target's speech. A common dilemma occurs when a speaker is confined to a noisy environment and receives a call with high background and…

声音 · 计算机科学 2023-01-24 Amanda Shu , Hamza Khalid , Haohui Liu , Shikhar Agnihotri , Joseph Konan , Ojas Bhargave

Language model (LM)-based speech enhancement (SE) can generate natural-sounding speech, but under severe noise it often suffers from unreliable conditioning, leading to perceptually plausible yet linguistically incorrect outputs. To address…

音频与语音处理 · 电气工程与系统科学 2026-05-12 Zheng Wang , Xiaobin Rong , Hang Su , Tianyi Tan , Junnan Wu , Lichun Fan , Zhenbo Luo , Jian Luan , Jing Lu

Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks…

音频与语音处理 · 电气工程与系统科学 2019-11-05 Daniel Michelsanti , Zheng-Hua Tan

Deep learning has the potential to enhance speech signals and increase their intelligibility for users of hearing aids. Deep models suited for real-world application should feature a low computational complexity and low processing delay of…

音频与语音处理 · 电气工程与系统科学 2024-10-31 Nils L. Westhausen , Hendrik Kayser , Theresa Jansen , Bernd T. Meyer

Recent advancements in language models (LMs) have demonstrated strong capabilities in semantic understanding and contextual modeling, which have flourished in generative speech enhancement (SE). However, many LM-based SE approaches…

音频与语音处理 · 电气工程与系统科学 2025-06-11 Boyi Kang , Xinfa Zhu , Zihan Zhang , Zhen Ye , Mingshuai Liu , Ziqian Wang , Yike Zhu , Guobin Ma , Jun Chen , Longshuai Xiao , Chao Weng , Wei Xue , Lei Xie

Speech-related applications deliver inferior performance in complex noise environments. Therefore, this study primarily addresses this problem by introducing speech-enhancement (SE) systems based on deep neural networks (DNNs) applied to a…

音频与语音处理 · 电气工程与系统科学 2020-05-26 Syu-Siang Wang , Yu-You Liang , Jeih-weih Hung , Yu Tsao , Hsin-Min Wang , Shih-Hau Fang

Generative Universal Speech Enhancement (USE) methods aim to leverage generative models to improve speech quality under various types of distortions. However, existing generative speech enhancement methods often suffer from semantic…

音频与语音处理 · 电气工程与系统科学 2026-04-07 Xingchen Li , Hanke Xie , Ziqian Wang , Zihan Zhang , Longshuai Xiao , Shuai Wang , Lei Xie

Recently, audio-visual separation approaches have taken advantage of the natural synchronization between the two modalities to boost audio source separation performance. They extracted high-level semantics from visual inputs as the guidance…

声音 · 计算机科学 2024-07-08 Shentong Mo , Yapeng Tian

Blind speech separation (BSS) aims to recover multiple speech sources from multi-channel, multi-speaker mixtures under unknown array geometry and room impulse responses. In unsupervised setup where clean target speech is not available for…

声音 · 计算机科学 2025-10-13 Shulin He , Zhong-Qiu Wang

Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech…

声音 · 计算机科学 2021-03-01 Jiatong Shi , Chunlei Zhang , Chao Weng , Shinji Watanabe , Meng Yu , Dong Yu

In this study we present a Deep Mixture of Experts (DMoE) neural-network architecture for single microphone speech enhancement. By contrast to most speech enhancement algorithms that overlook the speech variability mainly caused by phoneme…

声音 · 计算机科学 2017-03-29 Shlomo E. Chazan , Jacob Goldberger , Sharon Gannot

In recent years, large language models (LLM) have made significant progress in the task of generation error correction (GER) for automatic speech recognition (ASR) post-processing. However, in complex noisy environments, they still face…

声音 · 计算机科学 2025-09-05 Yanyan Liu , Minqiang Xu , Yihao Chen , Liang He , Lei Fang , Sian Fang , Lin Liu

We propose multi-microphone complex spectral mapping, a simple way of applying deep learning for time-varying non-linear beamforming, for speaker separation in reverberant conditions. We aim at both speaker separation and dereverberation.…

声音 · 计算机科学 2021-05-25 Zhong-Qiu Wang , Peidong Wang , DeLiang Wang

The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multi-speaker speech recognition. However, up until now, state-of-the-art neural network-based time domain source…

音频与语音处理 · 电气工程与系统科学 2020-04-14 Thilo von Neumann , Keisuke Kinoshita , Lukas Drude , Christoph Boeddeker , Marc Delcroix , Tomohiro Nakatani , Reinhold Haeb-Umbach

The joint training of speech enhancement and speaker embedding networks for speaker recognition is widely adopted under noisy acoustic environments. While effective, this paradigm often fails to leverage the generalization and robustness…

音频与语音处理 · 电气工程与系统科学 2026-04-29 Chong-Xin Gan , Peter Bell , Man-Wai Mak , Zhe Li , Zezhong Jin , Zilong Huang , Kong Aik Lee