A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

被引：31

作者：

Valin, Jean-Marc ^{[1
]}

Isik, Umut ^{[2
]}

Phansalkar, Neerad ^{[2
]}

Giri, Ritwik ^{[2
]}

Helwani, Karim ^{[2
]}

Krishnaswamy, Arvindh ^{[2
]}

机构：

[1] Amazon Web Serv, Toronto, ON, Canada

[2] Amazon Web Serv, Seattle, WA USA

来源：

INTERSPEECH 2020 | 2020年

关键词：

speech enhancement; pitch filtering; postfilter; MASKING; NOISE;

D O I：

10.21437/Interspeech.2020-2730

中图分类号：

R36 [病理学]; R76 [耳鼻咽喉科学];

学科分类号：

100104 ; 100213 ;

摘要：

Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of these new techniques operate directly in the the short-time Fourier transform (STFT) domain, resulting in a high computational complexity. In this work, we propose PercepNet, an efficient approach that relies on human perception of speech by focusing on the spectral envelope and on the periodicity of the speech. We demonstrate high-quality, real-time enhancement of fullband (48 kHz) speech with less than 5% of a CPU core.

引用

页码：2482 / 2486

页数：5

共 50 条

[31] A real-time kepstrum approach to speech enhancement and noise cancellation
Jeong, J.
Moir, T. J.
[J]. NEUROCOMPUTING, 2008, 71 (13-15) : 2635 - 2649
[32] Real-Time Demonstration of Low-Complexity Time-Domain Chromatic Dispersion Equalization
Martins, Celestino S.
Amado, Sofia B.
Ferreira, Ricardo M.
Shahpari, Ali
Teixeira, Antonio L.
Guiomar, Fernando P.
Pinto, Armando N.
[J]. 2017 19TH INTERNATIONAL CONFERENCE ON TRANSPARENT OPTICAL NETWORKS (ICTON), 2017,
[33] Real-Time Low-Complexity Automatic Modulation Classifier for Pulsed Radar Signals
Iglesias, Victor
Grajal, Jesus
Royer, Pablo
Sanchez, Miguel A.
Lopez-Vallejo, Marisa
Yeste-Ojeda, Omar A.
[J]. IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2015, 51 (01) : 108 - 126
[34] A Low-Complexity Vision-Based System for Real-Time Traffic Monitoring
Isaac Engel, Juan
Martin, Juan
Barco, Raquel
[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2017, 18 (05) : 1279 - 1288
[35] Adaptive Block Compressive Sensing: Toward a Real-Time and Low-Complexity Implementation
Zammit, Joseph
Wassell, Ian J.
[J]. IEEE ACCESS, 2020, 8 : 120999 - 121013
[36] A Modular Low-Complexity ECG Delineation Algorithm for Real-Time Embedded Systems
Bote, Jose Manuel
Recas, Joaquin
Rincon, Francisco
Atienza, David
Hermida, Roman
[J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2018, 22 (02) : 429 - 441
[37] Low-Complexity Image Processing for Real-Time Detection of Neonatal Clonic Seizures
Ntonfo, Guy Mathurin Kouamou
Ferrari, Gianluigi
Raheli, Riccardo
Pisani, Francesco
[J]. IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 2012, 16 (03): : 375 - 382
[38] A Novel Approach to Noise Reduction and Real-Time Enhancement of Speech Synthesis
Rafieee, M. Saadeq
Khazaei, Ali Akbar
[J]. 2010 SECOND INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, COMMUNICATION SYSTEMS AND NETWORKS (CICSYN), 2010, : 250 - 255
[39] Divide and Conquer: A Low-complexity Neural Network for Monophonic Speech Enhancement
Fang, Bingxiao
Liu, Liang
[J]. PROCEEDINGS OF 2022 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2022, : 944 - 949
[40] Low-Complexity Compressive Spectrum Sensing for Large-Scale Real-Time Processing
Zhang, Xingjian
Ma, Yuan
Qi, Haoran
Gao, Yue
[J]. IEEE WIRELESS COMMUNICATIONS LETTERS, 2018, 7 (04) : 674 - 677

← 1 2 3 4 5 →