A multifeature voiced/unvoiced decision algorithm for noisy speech

被引：10
|
作者：
Shahnaz, C. [1 ]
Zhu, W. -P. [1 ]
Ahmad, M. O. [1 ]
机构：
[1] Concordia Univ, Ctr Commun & Signal Proc, Dept Elect & Comp Engn, Montreal, PQ H3G 1M8, Canada
来源：
2006 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-11, PROCEEDINGS | 2006年
关键词：
D O I：
10.1109/ISCAS.2006.1693137
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper presents a new algorithm for the voiced/unvoiced (V/UV) decision of noise-corrupted speech. A speech periodicity-harmonic function (SPHF) is proposed to manifest distinctive characteristics between voiced and unvoiced regions. A composite feature vector is developed by combining a periodicity measure obtained from the SPHF with some energy measures such as zero-crossing rate-weighted RMS energy, Kaiser-Teager frame energy and the normalized low-frequency energy ratio. Unlike the conventional hard threshold, a signal-dependent initial-threshold (SDIT) for each feature is determined based on its statistical properties. The SDIT is exploited to develop a logical expression that returns an objective score regarding V/UV region. Additional voicing criteria are introduced to remove the artifacts that may exist due to the overlapping between decision regions. Simulation results of the proposed multifeature classification scheme, using the Keele reference database, show superior efficacy at a low SNR relative to some of the existing V/UV decision algorithms.
引用
收藏
页码：2525 / +
页数：2
相关论文
共 50 条
  • [1] A pitch determination and voiced/unvoiced decision algorithm for noisy speech
    Rouat, J
    Liu, YC
    Morissette, D
    SPEECH COMMUNICATION, 1997, 21 (03) : 191 - 207
  • [2] Voiced/Unvoiced Decision Algorithm for HMM-based Speech Synthesis
    Kang, Shiyin
    Shuang, Zhiwei
    Duan, Quansheng
    Qin, Yong
    Cai, Lianhong
    INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 420 - +
  • [3] Voiced/unvoiced classification algorithm for wideband speech
    Institute of Signal and Information Processing, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
    Shu Ju Cai Ji Yu Chu Li, 2008, 3 (288-293):
  • [4] Generalized likelihood ratio test for voiced-unvoiced decision in noisy speech using the harmonic model
    Fisher, E
    Tabrikian, J
    Dubnov, S
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (02): : 502 - 510
  • [5] Two-speaker Voiced/Unvoiced Decision for Monaural Speech
    Zeremdini, Jihen
    Ben Messaoud, Mohamed Anouar
    Bouzid, Aicha
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2020, 39 (09) : 4399 - 4415
  • [6] Significance of sonority information for voiced/unvoiced decision in speech synthesis
    Sharma, Bidisha
    Prasanna, S. R. Mahadeva
    SPEECH COMMUNICATION, 2018, 99 : 201 - 210
  • [7] Two-speaker Voiced/Unvoiced Decision for Monaural Speech
    Jihen Zeremdini
    Mohamed Anouar Ben Messaoud
    Aicha Bouzid
    Circuits, Systems, and Signal Processing, 2020, 39 : 4399 - 4415
  • [8] An approach for voiced/unvoiced decision of colored noise-corrupted speech
    Shahnaz, C.
    Zhu, W. -P.
    Ahmad, A. O.
    2007 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-11, 2007, : 3944 - 3947
  • [9] RELIABLE VOICED-UNVOICED DECISION
    KNORR, SG
    IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1979, 27 (03): : 263 - 267
  • [10] A bifeature voiced/unvoiced discrimination algorithm for speech signals in the presense of noise
    Shahnaz, C.
    Zhu, W. -P.
    Ahmad, M. O.
    2007 IEEE NORTH-EAST WORKSHOP ON CIRCUITS AND SYSTEMS, 2007, : 17 - 20
12345