A DATA-DRIVEN RESIDUAL GAIN APPROACH FOR TWO-STAGE SPEECH ENHANCEMENT

被引：0
|
作者：
Jin, Yu Gwang [1 ]
Lee, Chul Min [1 ]
Cho, Kiho [1 ]
Kim, Nam Soo [1 ]
机构：
[1] Seoul Natl Univ, Sch Elect Engn, Seoul 151742, South Korea
来源：
2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2011年
关键词：
Speech enhancement; noise reduction; data-driven approach; residual gain estimation; SPECTRAL AMPLITUDE ESTIMATOR; SOFT DECISION; NOISE;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
In this paper, we propose a novel speech enhancement algorithm based on data-driven residual gain estimation. The system consists of two stages. A noisy input signal is processed at the first stage by a conventional speech enhancement module from which both the enhanced signal and several signal-to-noise ratio (SNR)-related parameters are obtained. At the second stage, the residual gain, which is estimated by a data-driven method, is applied to the enhanced signal to further adjust it. According to the experimental results, the proposed algorithm has been found to show better performances compared with the conventional speech enhancement technique based on soft decision as well as the data-driven approach using the SNR grid look-up table.
引用
收藏
页码：4752 / 4755
页数：4
相关论文
共 50 条
  • [1] Speech Enhancement Based on Data-Driven Residual Gain Estimation
    Jin, Yu Gwang
    Kim, Nam Soo
    Chang, Joon-Hyuk
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2011, E94D (12): : 2537 - 2540
  • [2] TWO-STAGE DATA-DRIVEN SINGLE CHANNEL SPEECH ENHANCEMENT WITH CEPSTRAL ANALYSIS PRE-PROCESSING
    Rao, Yu
    Vahanesa, Chetan
    Reddy, Chandan K. A.
    Panahi, Issa M. S.
    [J]. 2015 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP), 2015, : 702 - 706
  • [3] Data-driven two-stage scheduling of multi-energy systems for operational flexibility enhancement
    Li, Hengyi
    Qin, Boyu
    Wang, Shihan
    Ding, Tao
    Wang, Hongzhen
    [J]. INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2024, 162
  • [4] Two-stage robust energy storage planning with probabilistic guarantees: A data-driven approach
    Yan, Chao
    Geng, Xinbo
    Bie, Zhaohong
    Xie, Le
    [J]. APPLIED ENERGY, 2022, 313
  • [5] Data-driven scenario generation for two-stage stochastic programming
    Bounitsis, Georgios L.
    Papageorgiou, Lazaros G.
    Charitopoulos, Vassilis M.
    [J]. CHEMICAL ENGINEERING RESEARCH & DESIGN, 2022, 187 : 206 - 224
  • [6] A Two-Stage Bayesian Data-Driven Method to Improve Model Prediction
    Sun, Xiaozhuo
    Zeng, Xiankui
    Wu, Jichun
    Wang, Dong
    [J]. WATER RESOURCES RESEARCH, 2021, 57 (12)
  • [7] Two-Stage Trajectory Optimization for Flapping Flight with Data-Driven Models
    Hoff, Jonathan
    Kim, Joohyung
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 7686 - 7692
  • [8] Data-driven two-stage distributionally robust optimization with risk aversion
    Huang, Ripeng
    Qu, Shaojian
    Gong, Zaiwu
    Goh, Mark
    Ji, Ying
    [J]. APPLIED SOFT COMPUTING, 2020, 87
  • [9] A two-stage algorithm for enhancement of reverberant speech
    Wu, MY
    Wang, D
    [J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 1085 - 1088
  • [10] A Two-Stage Approach to Noisy Cochannel Speech Separation with Gated Residual Networks
    Tan, Ke
    Wang, DeLiang
    [J]. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 3484 - 3488
12345