DNN-based phase estimation for online speech enhancement

被引：0
|
作者：
Nguyen, Binh Thien [1 ]
Wakabayashi, Yukoh [2 ]
Geng, Yuting [1 ]
Iwai, Kenta [1 ]
Nishiura, Takanobu [1 ]
机构：
[1] Ritsumeikan Univ, 1-1-1 Noji Higashi, Kusatsu 5258577, Japan
[2] Toyohashi Univ Technol, 1-1 Hibarigaoka,Tempaku Ku, Toyohashi 4418580, Japan
来源：
ACOUSTICAL SCIENCE AND TECHNOLOGY | 2025年 / 46卷 / 02期
关键词：
Speech enhancement; Phase estimation; DNN; Convolutional recurrent network; SIGNAL ESTIMATION;
D O I：
10.1250/ast.e24.102
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This paper presents a DNN-based phase reconstruction algorithm for online speech enhancement. Although various online phase reconstruction algorithms have been proposed, many of them rely on the structure of the clean amplitude. This restricts their performance in speech enhancement applications, where only noisy observations are available. In contrast, our proposed method directly estimates the clean phase from the noisy observation. Several aspects of phase reconstruction and their effects on speech enhancement are also investigated and discussed. Experimental results confirm that our method performs better than conventional online phase reconstruction methods for speech enhancement in all experimental settings.
引用
收藏
页码：186 / 190
页数：5
相关论文
共 50 条
  • [31] Concatenated Identical DNN (CI-DNN) to Reduce Noise-Type Dependence in DNN-Based Speech Enhancement
    Xu, Ziyi
    Strake, Maximilian
    Fingscheidt, Tim
    2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2019,
  • [32] DNN-BASED SPEECH RECOGNITION FOR GLOBALPHONE LANGUAGES
    Tachbelie, Martha Yifiru
    Abulimiti, Ayimunishagu
    Abate, Solomon Teferra
    Schultz, Tanja
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 8269 - 8273
  • [33] F0 ESTIMATION FOR DNN-BASED ULTRASOUND SILENT SPEECH INTERFACES
    Grosz, Tamas
    Gosztolya, Gabor
    Toth, Laszlo
    Csapo, Tamas Gabor
    Marko, Alexandra
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 291 - 295
  • [34] SNR-Based Features and Diverse Training Data for Robust DNN-Based Speech Enhancement
    Rehr, Robert
    Gerkmann, Timo
    IEEE/ACM Transactions on Audio Speech and Language Processing, 2021, 29 : 1937 - 1949
  • [35] SNR-Based Features and Diverse Training Data for Robust DNN-Based Speech Enhancement
    Rehr, Robert
    Gerkmann, Timo
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 29 : 1937 - 1949
  • [36] Towards More Efficient DNN-Based Speech Enhancement Using Quantized Correlation Mask
    Abdullah, Salinna
    Zamani, Majid
    Demosthenous, Andreas
    IEEE ACCESS, 2021, 9 : 24350 - 24362
  • [37] A low-computational DNN-based speech enhancement for hearing aids based on element selection
    Haruta, Chiho
    Ono, Nobutaka
    29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021), 2021, : 1025 - 1029
  • [38] Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech
    Fujimura, Takuya
    Koizumi, Yuma
    Yatabe, Kohei
    Miyazaki, Ryoichi
    29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021), 2021, : 436 - 440
  • [39] Significance of Phase in DNN based speech enhancement algorithms
    Rani, P. Swetha
    Andhavarapu, Sivaganesh
    Kodukula, Sri Rama Murry
    2020 TWENTY SIXTH NATIONAL CONFERENCE ON COMMUNICATIONS (NCC 2020), 2020,
  • [40] DNN-based Amplitude and Phase Feature Enhancement for Noise Robust Speaker Identification
    Oo, Zeyan
    Kawakami, Yuta
    Wang, Longbiao
    Nakagawa, Seiichi
    Xiao, Xiong
    Iwahashi, Masahiro
    17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 2204 - 2208
12345