Enhancement of Noisy Speech using Sub-band Harmonic Regeneration and Speech Presence Uncertainty Estimator

被引：0
|
作者：
Kumar, Ravi [1 ]
Subbaiah, P. V. [2 ]
机构：
[1] Lakireddy Balireddy Coll Engn, Dept Elect & Commun Engn, Mylavaram, Vijayawada, India
[2] VR Siddhartha Engn Coll, Dept Elect & Commun Engn, Vijayawada, India
来源：
2016 IEEE INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ELECTRONICS, INFORMATION & COMMUNICATION TECHNOLOGY (RTEICT) | 2016年
关键词：
Speech enhancement; Harmonic regeneratio; speech presence uncertainty estimation; wavelet packet transform;
D O I：
暂无
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
This paper presents a noise reduction technique based on sub-band harmonic regeneration with Speech Presence Uncertainty (SPU). Harmonic Regeneration (HRNR) overcomes the harmonic distortion, which is significant at low SNR values by preserving harmonics. For further noise suppression at low SNRs, Sub-band modification of HRNR gain with weights calculated using speech presence uncertainty is proposed. Objective (SNR, SegSNR, LLR, WSS) performance measures show that the proposed method provides superiority in noise reduction and measures like SNR and SegSNR shows better speech preservation at high SNRs, better noise suppression at low SNRs.
引用
收藏
页码：456 / 460
页数：5
相关论文
共 50 条
  • [41] A Replay Speech Detection Algorithm Based on Sub-band Analysis
    Lang Lin
    Wang, Rangding
    Yan Diqun
    INTELLIGENT INFORMATION PROCESSING IX, 2018, 538 : 337 - 345
  • [42] Maximum likelihood sub-band adaptation for robust speech recognition
    Zhu, DL
    Nakamura, S
    Paliwal, KK
    Wang, RH
    SPEECH COMMUNICATION, 2005, 47 (03) : 243 - 264
  • [43] SIMULATION ON SUB-BAND CODING OF SPEECH WITH NOVEL ADPCM.
    Pei, Soo-Chang
    Yu, Gong-San
    A.M.S.E. review, 1988, 7 (01): : 39 - 51
  • [44] Sub-band Modulation Spectrum Compensation for Robust Speech Recognition
    Tu, Wen-hsiang
    Huang, Sheng-Yuan
    Hung, Jeih-weih
    2009 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION & UNDERSTANDING (ASRU 2009), 2009, : 261 - 265
  • [45] A Hybrid Text-to-Speech Based on Sub-Band Approach
    Inoue, Takuma
    Hara, Sunao
    Abe, Masanobu
    2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014,
  • [46] Mel Sub-Band Filtering and Compression for Robust Speech Recognition
    Nasersharif, Babak
    Akbari, Ahmad
    Homayounpour, Mohammad Mehdi
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 105 - +
  • [47] Minima Controlled Speech Presence Uncertainty Tracking Method for Speech Enhancement
    Lee, Woojung
    Chang, Joon-Hyuk
    JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2009, 28 (07): : 668 - 673
  • [48] On speech enhancement under signal presence uncertainty
    Cohen, I
    2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING, 2001, : 661 - 664
  • [49] A method for the reconstruction of missing speech frames using linear prediction and sub-band excitation
    Cluver, K
    FREQUENZ, 1996, 50 (9-10) : 211 - 215
  • [50] HMM-based speech synthesis using sub-band basis spectrum model
    Ohtani, Yamato
    Tamura, Masatsune
    Morita, Masahiro
    Kagoshima, Takehiko
    Akamine, Masami
    13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 1438 - 1441
12345