JOINT SINGLE-CHANNEL SPEECH SEPARATION AND SPEAKER IDENTIFICATION

被引：13
|
作者：
Mowlaee, P. [1 ]
Saeidi, R. [2 ]
Tan, Z. -H. [1 ]
Christensen, M. G. [3 ]
Franti, P. [2 ]
Jensen, S. H. [1 ]
机构：
[1] Aalborg Univ, Dept Elect Syst, Aalborg, Denmark
[2] Univ Joensuu, Dept Comp Sci & Stat, Joensuu, Finland
[3] Aalborg Univ, Dept Media, Aalborg, Denmark
来源：
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2010年
关键词：
Single-channel speech separation; speaker identification; sinusoidal mixture estimator; vector quantization; Gaussian mixture model;
D O I：
10.1109/ICASSP.2010.5495619
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
In this paper, we propose a closed loop system to improve the performance of single-channel speech separation in a speaker independent scenario. The system is composed of two interconnected blocks: a separation block and a speaker identification block. The improvement is accomplished by incorporating the speaker identities found by the speaker identification block as additional information for the separation block, which converts the speaker-independent separation problem to a speaker-dependent one where the speaker codebooks are known. Simulation results show that the closed loop system enhances the quality of the separated output signals. To assess the improvements, the results are reported in terms of PESQ for both target and masked signals.
引用
下载
收藏
页码：4430 / 4433
页数：4
相关论文
共 50 条
  • [1] A Joint Approach for Single-Channel Speaker Identification and Speech Separation
    Mowlaee, Pejman
    Saeidi, Rahim
    Christensen, Mads Grsboll
    Tan, Zheng-Hua
    Kinnunen, Tomi
    Franti, Pasi
    Jensen, Soren Holdt
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2012, 20 (09): : 2586 - 2601
  • [2] Speaker Separation Using Visual Speech Features and Single-channel Audio
    Khan, Faheem
    Milner, Ben
    14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 3263 - 3267
  • [3] Speaker Verification-Based Evaluation of Single-Channel Speech Separation
    Maciejewski, Matthew
    Watanabe, Shinji
    Khudanpur, Sanjeev
    INTERSPEECH 2021, 2021, : 3520 - 3524
  • [4] Joint identification-separation technique for single channel speech separation
    Radfar, M. H.
    Dansereau, R. M.
    Sayadiyan, A.
    2006 IEEE 12TH DIGITAL SIGNAL PROCESSING WORKSHOP & 4TH IEEE SIGNAL PROCESSING EDUCATION WORKSHOP, VOLS 1 AND 2, 2006, : 76 - 81
  • [5] Soft mask methods for single-channel speaker separation
    Reddy, Aarthi M.
    Raj, Bhiksha
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (06): : 1766 - 1776
  • [6] Assessment of Single-Channel Speech Enhancement Techniques for Speaker Identification under Mismatched Conditions
    Sadjadi, Seyed Omid
    Hansen, John H. L.
    11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4, 2010, : 2138 - 2141
  • [7] SOURCE-AWARE CONTEXT NETWORK FOR SINGLE-CHANNEL MULTI-SPEAKER SPEECH SEPARATION
    Li, Zeng-Xi
    Song, Yan
    Dai, Li-Rong
    McLoughlin, Ian
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 681 - 685
  • [8] SPEAKER AND NOISE INDEPENDENT ONLINE SINGLE-CHANNEL SPEECH ENHANCEMENT
    Germain, Francois G.
    Mysore, Gautham J.
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 71 - 75
  • [9] Speaker Counting and Separation From Single-Channel Noisy Mixtures
    Chetupalli, Srikanth Raj
    Habets, Emanuel A. P.
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2023, 31 : 1681 - 1692
  • [10] Speaker Verification Based on Single Channel Speech Separation
    Jin, Rong
    Ablimit, Mijit
    Hamdulla, Askar
    IEEE ACCESS, 2023, 11 : 112631 - 112638
12345