Selective Gammatone Filterbank Feature for Robust Sound Event Recognition

被引：0
|
作者：
Leng, Yi Ren [1 ]
Huy Dat Tran [1 ]
Kitaoka, Norihide [2 ]
Li, Haizhou [1 ]
机构：
[1] ASTAR, Inst Infocomm Res, Human Language Technol Dept, Singapore 138632, Singapore
[2] Nagoya Univ, Nagoya, Aichi 4648601, Japan
来源：
11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4 | 2010年
关键词：
gammatone filterbank; Hidden Markov Model; robust recognition; sound event recognition;
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 introduces a novel feature based on the raw output of the garnmatone filterbank. Channel selection is used to enhance robustness over a range of signal-to-noise ratios (SNR) of additive noise. The recognition accuracy of the proposed feature is tested on a sound event database using a Hidden Markov Model (HMM) recogniser. A comparison with a series of similar features and the conventional Mel-Frequency Cepstral Coefficients (MFCC) shows that the proposed feature offers significant improvement in low SNR conditions.
引用
收藏
页码：2246 / +
页数：2
相关论文
共 50 条
  • [41] Improved MFCC feature extraction by PCA-optimized filterbank for speech recognition
    Lee, SM
    Fang, SH
    Hung, JW
    Lee, LS
    ASRU 2001: IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, CONFERENCE PROCEEDINGS, 2001, : 49 - 52
  • [42] Gammatone filterbank and symbiotic combination of amplitude and phase-based spectra for robust speaker verification under noisy conditions and compression artifacts
    M. Fedila
    M. Bengherabi
    A. Amrouche
    Multimedia Tools and Applications, 2018, 77 : 16721 - 16739
  • [43] Gammatone filterbank and symbiotic combination of amplitude and phase-based spectra for robust speaker verification under noisy conditions and compression artifacts
    Fedila, M.
    Bengherabi, M.
    Amrouche, A.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (13) : 16721 - 16739
  • [44] Sound Event Recognition in Smart Environments
    Pop, Gheorghe
    Caranica, Alexandru
    Cucu, Horia
    Burileanu, Dragos
    2015 INTERNATIONAL CONFERENCE ON SPEECH TECHNOLOGY AND HUMAN-COMPUTER DIALOGUE (SPED), 2015,
  • [45] On Feature Selection in Environmental Sound Recognition
    Mitrovic, Dalibor
    Zeppelzauer, Matthias
    Eidenberger, Horst
    PROCEEDINGS ELMAR-2009, 2009, : 201 - 204
  • [46] Feature Extraction and Recognition of Heart Sound
    Zhou, Jing
    He, Wei
    Dan, Chunmei
    Que, Xiaosheng
    2008 WORLD AUTOMATION CONGRESS PROCEEDINGS, VOLS 1-3, 2008, : 1820 - +
  • [47] Robust scream sound detection via sound event partitioning
    Baiying Lei
    Man-Wai Mak
    Multimedia Tools and Applications, 2016, 75 : 6071 - 6089
  • [48] Robust scream sound detection via sound event partitioning
    Lei, Baiying
    Mak, Man-Wai
    MULTIMEDIA TOOLS AND APPLICATIONS, 2016, 75 (11) : 6071 - 6089
  • [49] Robust Sound Recognition: A Neuromorphic Approach
    Wu, Jibin
    Pan, Zihan
    Zhang, Malu
    Das, Rohan Kumar
    Chua, Yansong
    Li, Haizhou
    INTERSPEECH 2019, 2019, : 3667 - 3668
  • [50] Towards joint sound scene and polyphonic sound event recognition
    Bear, Helen L.
    Nolasco, Ines
    Benetos, Emmanouil
    INTERSPEECH 2019, 2019, : 4594 - 4598
12345