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

页码：186 / 190

页数：5

共 50 条

[41] A DNN-based emotional speech synthesis by speaker adaptation
Yang, Hongwu
Zhang, Weizhao
Zhi, Pengpeng
2018 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2018, : 633 - 637
[42] DNN-Based Semantic Rescoring Models for Speech Recognition
Illina, Irina
Fohr, Dominique
TEXT, SPEECH, AND DIALOGUE, TSD 2021, 2021, 12848 : 357 - 370
[43] Prediction of speech intelligibility with DNN-based performance measures
Martinez, Angel Mario Castro
Spille, Constantin
Rossbach, Jana
Kollmeier, Birger
Meyer, Bernd T.
COMPUTER SPEECH AND LANGUAGE, 2022, 74
[44] DNN-Based Speech Synthesis Using Speaker Codes
Hojo, Nobukatsu
Ijima, Yusuke
Mizuno, Hideyuki
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2018, E101D (02): : 462 - 472
[45] DNN-BASED SPEECH QUALITY ASSESSMENT FOR BINAURAL SIGNALS
Reimes, Jan
2022 INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC 2022), 2022,
[46] DNN-Based Speech Synthesis for Arabic: Modelling and Evaluation
Houidhek, Amal
Colotte, Vincent
Mnasri, Zied
Jouvet, Denis
STATISTICAL LANGUAGE AND SPEECH PROCESSING, SLSP 2018, 2018, 11171 : 9 - 20
[47] DNN-based speech watermarking resistant to desynchronization attacks
Pavlovic, Kosta
Kovacevic, Slavko
Djurovic, Igor
Wojciechowski, Adam
INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, 2023, 21 (05)
[48] A study of speaker adaptation for DNN-based speech synthesis
Wu, Zhizheng
Swietojanski, Pawel
Veaux, Christophe
Renals, Steve
King, Simon
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 879 - 883
[49] DNN-based Ultrasound-to-Speech Conversion for a Silent Speech Interface
Csapo, Temas Gabor
Grosz, Tamas
Gosztolya, Gabor
Toth, Laszlo
Marko, Alexandra
18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 3672 - 3676
[50] DNN-based Feature Enhancement using Joint Training Framework for Robust Multichannel Speech Recognition
Lee, Kang Hyun
Kang, Tae Gyoon
Kang, Woo Hyun
Kim, Nam Soo
17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 3027 - 3031

← 1 2 3 4 5 →