中文
相关论文

相关论文: LiSenNet: Lightweight Sub-band and Dual-Path Model…

200 篇论文

Multichannel speech enhancement (SE) aims to restore clean speech from noisy measurements by leveraging spatiotemporal signal features. In ad-hoc array conditions, microphone invariance (MI) requires systems to handle different microphone…

声音 · 计算机科学 2025-08-28 Haoyin Yan , Jie Zhang , Chengqian Jiang , Shuang Zhang

Binaural speech enhancement (BSE) aims to jointly improve the speech quality and intelligibility of noisy signals received by hearing devices and preserve the spatial cues of the target for natural listening. Existing methods often suffer…

声音 · 计算机科学 2025-01-09 Jingyuan Wang , Jie Zhang , Shihao Chen , Miao Sun

In this paper we propose a lightweight model for frequency bandwidth extension of speech signals, increasing the sampling frequency from 8kHz to 16kHz while restoring the high frequency content to a level almost indistinguishable from the…

音频与语音处理 · 电气工程与系统科学 2021-02-10 Yunpeng Li , Marco Tagliasacchi , Oleg Rybakov , Victor Ungureanu , Dominik Roblek

FullSubNet is our recently proposed real-time single-channel speech enhancement network that achieves outstanding performance on the Deep Noise Suppression (DNS) Challenge dataset. A number of variants of FullSubNet have been proposed, but…

音频与语音处理 · 电气工程与系统科学 2023-03-08 Xiang Hao , Xiaofei Li

Due to the unprecedented breakthroughs brought about by deep learning, speech enhancement (SE) techniques have been developed rapidly and play an important role prior to acoustic modeling to mitigate noise effects on speech. To increase the…

音频与语音处理 · 电气工程与系统科学 2021-09-15 Fu-An Chao , Shao-Wei Fan Jiang , Bi-Cheng Yan , Jeih-weih Hung , Berlin Chen

Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…

音频与语音处理 · 电气工程与系统科学 2024-05-28 Monisankha Pal , Arvind Ramanathan , Ted Wada , Ashutosh Pandey

Deep learning-based speech enhancement has seen huge improvements and recently also expanded to full band audio (48 kHz). However, many approaches have a rather high computational complexity and require big temporal buffers for real time…

音频与语音处理 · 电气工程与系统科学 2022-05-12 Hendrik Schröter , Alberto N. Escalante-B. , Tobias Rosenkranz , Andreas Maier

We propose Mobile Audio Streaming Networks (MASnet) for efficient low-latency speech enhancement, which is particularly suitable for mobile devices and other applications where computational capacity is a limitation. MASnet processes…

音频与语音处理 · 电气工程与系统科学 2020-08-18 Michał Romaniuk , Piotr Masztalski , Karol Piaskowski , Mateusz Matuszewski

Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio…

音频与语音处理 · 电气工程与系统科学 2024-02-19 Wangyou Zhang , Jee-weon Jung , Shinji Watanabe , Yanmin Qian

Recent advancements in automatic speech recognition (ASR) have achieved notable progress, whereas robustness in noisy environments remains challenging. While speech enhancement (SE) front-ends are widely used to mitigate noise as a…

声音 · 计算机科学 2025-09-29 Siyi Zhao , Wei Wang , Yanmin Qian

Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input. In real-world speech communication, however, noises often exist in not only speaker but also listener environments. Although SE methods can suppress…

音频与语音处理 · 电气工程与系统科学 2022-03-23 Haoyu Li , Yun Liu , Junichi Yamagishi

The deep learning-based speech enhancement (SE) methods always take the clean speech's waveform or time-frequency spectrum feature as the learning target, and train the deep neural network (DNN) by reducing the error loss between the DNN's…

音频与语音处理 · 电气工程与系统科学 2023-11-02 Yuewei Zhang , Huanbin Zou , Jie Zhu

Deep neural network based full-band speech enhancement systems face challenges of high demand of computational resources and imbalanced frequency distribution. In this paper, a light-weight full-band model is proposed with two dedicated…

音频与语音处理 · 电气工程与系统科学 2022-07-05 Qinwen Hu , Zhongshu Hou , Xiaohuai Le , Jing Lu

Despite the rapid progress in speech enhancement (SE) research, enhancing the quality of desired speech in environments with strong noise and interfering speakers remains challenging. In this paper, we extend the application of the recently…

音频与语音处理 · 电气工程与系统科学 2023-06-07 Jianwei Yu , Yi Luo , Hangting Chen , Rongzhi Gu , Chao Weng

High quality speech capture has been widely studied for both voice communication and human computer interface reasons. To improve the capture performance, we can often find multi-microphone speech enhancement techniques deployed on various…

音频与语音处理 · 电气工程与系统科学 2023-03-15 Yang Yang , Shao-Fu Shih , Hakan Erdogan , Jamie Menjay Lin , Chehung Lee , Yunpeng Li , George Sung , Matthias Grundmann

Isolating the desired speaker's voice amidst multiplespeakers in a noisy acoustic context is a challenging task. Per-sonalized speech enhancement (PSE) endeavours to achievethis by leveraging prior knowledge of the speaker's voice.Recent…

声音 · 计算机科学 2024-04-15 Thomas Serre , Mathieu Fontaine , Éric Benhaim , Geoffroy Dutour , Slim Essid

Noise suppression and echo cancellation are critical in speech enhancement and essential for smart devices and real-time communication. Deployed in voice processing front-ends and edge devices, these algorithms must ensure efficient…

声音 · 计算机科学 2023-11-28 Kaijun Tan , Benzhe Dai , Jiakui Li , Wenyu Mao

One persistent challenge in Speech Emotion Recognition (SER) is the ubiquitous environmental noise, which frequently results in deteriorating SER performance in practice. In this paper, we introduce a Two-level Refinement Network, dubbed…

声音 · 计算机科学 2024-09-04 Chengxin Chen , Pengyuan Zhang

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however…

This paper introduces a lightweight deep learning model for real-time speech enhancement, designed to operate efficiently on resource-constrained devices. The proposed model leverages a compact architecture that facilitates rapid inference…

音频与语音处理 · 电气工程与系统科学 2025-09-23 Shuubham Ojha , Felix Gervits , Carol Espy-Wilson
‹ 上一页 1 2 3 10 下一页 ›