Feasibility of single channel speaker separation based on modulation frequency analysis

被引：0
|
作者：
Schimmel, Steven M. [1 ]
Atlas, Les E. [1 ]
Nie, Kaibao [2 ]
机构：
[1] Univ Washington, Dept Elect Engn, Seattle, WA 98195 USA
[2] Univ Washington, VM Bloedel Hearing Res Ctr, Seattle, WA USA
来源：
2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3 | 2007年
关键词：
speech enhancement; separation; modulation; spectral analysis; time-varying filters;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
We explore the use of the modulation frequency domain for single channel speaker separation. We discuss features of the modulation spectrogram of speech signals that suggest that multiple speakers are highly separable in this space. In a preliminary experiment, we separate a target speaker from an interfering speaker by manually masking out modulation spectral features of the interferer. We extend this experiment into a new automatic speaker separation algorithm, and show that it achieves an acceptable level of separation. The new algorithm only needs a rough estimate of the target speaker's pitch range.
引用
收藏
页码：605 / +
页数：2
相关论文
共 50 条
  • [1] Single-channel speech separation based on modulation frequency
    Gu, Lingyun
    Stern, Richard M.
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 25 - 28
  • [2] Speaker Verification Based on Single Channel Speech Separation
    Jin, Rong
    Ablimit, Mijit
    Hamdulla, Askar
    [J]. IEEE ACCESS, 2023, 11 : 112631 - 112638
  • [3] CASA BASED SUPERVISED SINGLE CHANNEL SPEAKER INDEPENDENT SPEECH SEPARATION
    Rehman, M. Fazal Ur
    Saleem, Nasir
    Nawaz, Asif
    Jan, Sadeeq
    Najam, Zeeshan
    Khattak, M. Irfan
    Ahmed, Sheeraz
    [J]. JOURNAL OF MECHANICS OF CONTINUA AND MATHEMATICAL SCIENCES, 2019, 14 (06): : 973 - 984
  • [4] Speaker Verification-Based Evaluation of Single-Channel Speech Separation
    Maciejewski, Matthew
    Watanabe, Shinji
    Khudanpur, Sanjeev
    [J]. INTERSPEECH 2021, 2021, : 3520 - 3524
  • [5] Speaker-independent model-based single channel speech separation
    Radfar, M. H.
    Dansereau, R. M.
    Sayadiyan, A.
    [J]. NEUROCOMPUTING, 2008, 72 (1-3) : 71 - 78
  • [6] Sparse overcomplete decomposition for single channel speaker separation
    Shashanka, Madhusudana V. S.
    Raj, Bhiksha
    Smaragdis, Paris
    [J]. 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PTS 1-3, 2007, : 641 - +
  • [7] Latent dirichlet decomposition for single channel speaker separation
    Raj, Bhiksha
    Shashanka, Madhusudana V. S.
    Smaragdis, Paris
    [J]. 2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13, 2006, : 5679 - 5682
  • [8] Single channel speech separation in modulation frequency domain based on a novel pitch range estimation method
    Mahmoodzadeh, Azar
    Abutalebi, Hamid Reza
    Soltanian-Zadeh, Hamid
    Sheikhzadeh, Hamid
    [J]. EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2012,
  • [9] Single channel speech separation in modulation frequency domain based on a novel pitch range estimation method
    Azar Mahmoodzadeh
    Hamid Reza Abutalebi
    Hamid Soltanian-Zadeh
    Hamid Sheikhzadeh
    [J]. EURASIP Journal on Advances in Signal Processing, 2012
  • [10] Soft mask methods for single-channel speaker separation
    Reddy, Aarthi M.
    Raj, Bhiksha
    [J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (06): : 1766 - 1776
12345