MULTI-STAGE TRAINING FOR CROSS-DOMAIN FULL-BAND AUDIO PACKET LOSS CONCEALMENT

被引：0
|
作者：
Li, Nan [1 ]
Yu, Guochen [1 ]
Zhang, Chen [1 ]
Zhou, Chao [1 ]
Huang, Qi [1 ]
Yu, Bing [1 ]
机构：
[1] Kuaishou Technol, Beijing, Peoples R China
来源：
2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW 2024 | 2024年
关键词：
packet loss concealment; multi-stage training; cross-domain;
D O I：
10.1109/ICASSPW62465.2024.10626444
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This paper introduces a multi-stage full-band packet loss concealment (PLC) method that incorporates both time-domain and frequency-domain learning. Specifically, the time-domain model is elaborately designed to generate the missing packets, while the frequency-domain model aims to remove discontinuity and noise. The proposed system achieved the 1st place ranking in the ICASSP 2024 PLC Challenge, demonstrating superior performance with a mere 20ms algorithm latency.
引用
收藏
页码：35 / 36
页数：2
相关论文
共 24 条
  • [1] Multi-Stage Packet Loss Concealment Using ADMM-GLA Phase Reconstruction
    Patadiya, Chirag Nileshbhai
    Gangan, Siddhesh Chandrashekhar
    Shah, Bhavin
    Gundur, Siva Prasad
    10TH INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTING AND COMMUNICATION TECHNOLOGIES, CONECCT 2024, 2024,
  • [2] A TIME-FREQUENCY BAND-SPLIT NEURAL NETWORK FOR REAL-TIME FULL-BAND PACKET LOSS CONCEALMENT
    Dai, Lingling
    Ke, Yuxuan
    Zhang, Huiyong
    Hao, Fengyuan
    Luo, Xiaoxue
    Li, Xiaodong
    Zheng, Chengshi
    2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW 2024, 2024, : 77 - 78
  • [3] Audio packet loss concealment in a combined MDCT-MDST domain
    Ofir, Hadas
    Malah, David
    Cohen, Israel
    IEEE SIGNAL PROCESSING LETTERS, 2007, 14 (12) : 1032 - 1035
  • [4] ENHANCED TIME DOMAIN PACKET LOSS CONCEALMENT IN SWITCHED SPEECH/AUDIO CODEC
    Lecomte, Jeremie
    Tomasek, Adrian
    Markovic, Goran
    Schnabel, Michael
    Tsutsumi, Kimitaka
    Kikuiri, Kei
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 5922 - 5926
  • [5] Streaming Audio Packet Loss Concealment Based on Sinusoidal Frequency Estimation in MDCT Domain
    Zhu, Meng-Yao
    Zhang, Ming
    Yu, Xiao-Qing
    Wan, Wang-Gen
    IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2010, 56 (02) : 811 - 819
  • [6] DELAY-LESS FREQUENCY DOMAIN PACKET-LOSS CONCEALMENT FOR TONAL AUDIO SIGNALS
    Sperschneider, Ralph
    Sukowski, Janine
    Markovic, Goran
    2015 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP), 2015, : 766 - 770
  • [7] End-to-End Multi-Loss Training for Low Delay Packet Loss Concealment
    Li, Nan
    Zheng, Xiguang
    Zhang, Chen
    Guo, Liang
    Yu, Bing
    INTERSPEECH 2022, 2022, : 585 - 589
  • [8] A clustering multi-stage training transfer learning framework for cross simulation domain and experimental domain fault diagnosis
    Yu, Shubo
    Liu, Zhansheng
    Zhao, Chen
    Lv, Dongfang
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (06)
  • [9] MULTI-CHANNEL NARROW-BAND DEEP SPEECH SEPARATION WITH FULL-BAND PERMUTATION INVARIANT TRAINING
    Quan, Changsheng
    Li, Xiaofei
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 541 - 545
  • [10] A Cross-Domain Exploration of Audio and Textual Data for Multi-Modal Emotion Detection
    Haque, Mohd Ariful
    George, Roy
    Rifat, Rakib Hossain
    Uddin, Md Shihab
    Kamal, Marufa
    Gupta, Kishor Datta
    17TH ACM INTERNATIONAL CONFERENCE ON PERVASIVE TECHNOLOGIES RELATED TO ASSISTIVE ENVIRONMENTS, PETRA 2024, 2024, : 375 - 381
123