Speech enhancement using a square microphone array in the presence of directional and diffuse noise

Tetsuji Ogawa, Shintaro Takada, Kenzo Akagiri, Tetsunori Kobayashi

    Research output: Contribution to journalArticle

    3 Citations (Scopus)

    Abstract

    We propose a new speech enhancement method suitable for mobile devices used in the presence of various types of noise. In order to achieve high-performance speech recognition and auditory perception in mobile devices, various types of noise have to be removed under the constraints of a space-saving microphone arrangement and few computational resources. The proposed method can reduce both the directional noise and the diffuse noise under the abovementioned constraints for mobile devices by employing a square microphone array and conducting low computational-cost processing that consists of multiple null beamforming, minimum power channel selection, and Wiener filtering. The effectiveness of the proposed method is experimentally verified in terms of speech recognition accuracy and speech quality when both the directional noise and the diffuse noise are observed simultaneously; this method reduces the number of word errors and improves the log-spectral distances as compared to conventional methods.

    Original languageEnglish
    Pages (from-to)926-935
    Number of pages10
    JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
    VolumeE93-A
    Issue number5
    DOIs
    Publication statusPublished - 2010 May

    Fingerprint

    Microphone Array
    Speech Enhancement
    Speech enhancement
    Microphones
    Mobile devices
    Speech recognition
    Mobile Devices
    Speech Recognition
    Beamforming
    Acoustic noise
    Wiener Filtering
    Null
    Computational Cost
    Processing
    Arrangement
    High Performance
    Costs
    Resources

    Keywords

    • Diffuse noise reduction
    • Directional noise reduction
    • Mobile devices
    • Speech recognition
    • Square microphone array

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Computer Graphics and Computer-Aided Design
    • Applied Mathematics
    • Signal Processing

    Cite this

    @article{4a96b29762db4f1ab4cf9b5f329695b5,
    title = "Speech enhancement using a square microphone array in the presence of directional and diffuse noise",
    abstract = "We propose a new speech enhancement method suitable for mobile devices used in the presence of various types of noise. In order to achieve high-performance speech recognition and auditory perception in mobile devices, various types of noise have to be removed under the constraints of a space-saving microphone arrangement and few computational resources. The proposed method can reduce both the directional noise and the diffuse noise under the abovementioned constraints for mobile devices by employing a square microphone array and conducting low computational-cost processing that consists of multiple null beamforming, minimum power channel selection, and Wiener filtering. The effectiveness of the proposed method is experimentally verified in terms of speech recognition accuracy and speech quality when both the directional noise and the diffuse noise are observed simultaneously; this method reduces the number of word errors and improves the log-spectral distances as compared to conventional methods.",
    keywords = "Diffuse noise reduction, Directional noise reduction, Mobile devices, Speech recognition, Square microphone array",
    author = "Tetsuji Ogawa and Shintaro Takada and Kenzo Akagiri and Tetsunori Kobayashi",
    year = "2010",
    month = "5",
    doi = "10.1587/transfun.E93.A.926",
    language = "English",
    volume = "E93-A",
    pages = "926--935",
    journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
    issn = "0916-8508",
    publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
    number = "5",

    }

    TY - JOUR

    T1 - Speech enhancement using a square microphone array in the presence of directional and diffuse noise

    AU - Ogawa, Tetsuji

    AU - Takada, Shintaro

    AU - Akagiri, Kenzo

    AU - Kobayashi, Tetsunori

    PY - 2010/5

    Y1 - 2010/5

    N2 - We propose a new speech enhancement method suitable for mobile devices used in the presence of various types of noise. In order to achieve high-performance speech recognition and auditory perception in mobile devices, various types of noise have to be removed under the constraints of a space-saving microphone arrangement and few computational resources. The proposed method can reduce both the directional noise and the diffuse noise under the abovementioned constraints for mobile devices by employing a square microphone array and conducting low computational-cost processing that consists of multiple null beamforming, minimum power channel selection, and Wiener filtering. The effectiveness of the proposed method is experimentally verified in terms of speech recognition accuracy and speech quality when both the directional noise and the diffuse noise are observed simultaneously; this method reduces the number of word errors and improves the log-spectral distances as compared to conventional methods.

    AB - We propose a new speech enhancement method suitable for mobile devices used in the presence of various types of noise. In order to achieve high-performance speech recognition and auditory perception in mobile devices, various types of noise have to be removed under the constraints of a space-saving microphone arrangement and few computational resources. The proposed method can reduce both the directional noise and the diffuse noise under the abovementioned constraints for mobile devices by employing a square microphone array and conducting low computational-cost processing that consists of multiple null beamforming, minimum power channel selection, and Wiener filtering. The effectiveness of the proposed method is experimentally verified in terms of speech recognition accuracy and speech quality when both the directional noise and the diffuse noise are observed simultaneously; this method reduces the number of word errors and improves the log-spectral distances as compared to conventional methods.

    KW - Diffuse noise reduction

    KW - Directional noise reduction

    KW - Mobile devices

    KW - Speech recognition

    KW - Square microphone array

    UR - http://www.scopus.com/inward/record.url?scp=77951955133&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77951955133&partnerID=8YFLogxK

    U2 - 10.1587/transfun.E93.A.926

    DO - 10.1587/transfun.E93.A.926

    M3 - Article

    VL - E93-A

    SP - 926

    EP - 935

    JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

    JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

    SN - 0916-8508

    IS - 5

    ER -