Recognition of in-field frog chorusing using Bayesian nonparametric microphone array processing

Yoshiaki Bandog, Takuma Otsuka, Ikkyu Aihara, Hiromitsu Awano, Katsutoshi Itoyama, Kazuyoshi Yoshii, Hiroshi G. Okuno

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    In this paper, we exploit Bayesian nonparametric microphone array processing (BNP-MAP) for analyzing the spatio- Temporal patterns of the frog chorus. Such analysis in real environments is made more difficult due to unpredictable sound sources including calls of various species of animals. An application of conventional signal processing algorithms has been difficult because these algorithms usually require the number of sound sources in advance. BNP-MAP is developed to cope with auditory uncertainties such as reverberation or unknown number of sounds by using a unified model based on Bayesian nonparametrics. We exploit BNP-MAP for analyzing the sound data of 20 minutes captured by a 7-channel microphone array in a paddy rice field in Oki Island, Japan, and revealed that two individuals of Schlegel's green tree frog {Rhacophorus schlegelii) called alternately with anti-phase. This result is compared with the video data captured by a video camera with 18 units of sound-imaging devices called Firefly deployed along the bank of the rice field. The auditory result provides more detailed patterns of the frog chorus in higher temporal resolutions. This higher resolution enables to analyze fine temporal structures of the frog calls. For example, BNP-MAP reveals the trill-like calling pattern of R. schlegelii.

    Original languageEnglish
    Title of host publicationAAAI Workshop - Technical Report
    PublisherAI Access Foundation
    Pages2-6
    Number of pages5
    VolumeWS-15-06
    ISBN (Print)9781577357179
    Publication statusPublished - 2015
    Event29th AAAI Conference on Artificial Intelligence, AAAI 2015 - Austin, United States
    Duration: 2015 Jan 252015 Jan 30

    Other

    Other29th AAAI Conference on Artificial Intelligence, AAAI 2015
    CountryUnited States
    CityAustin
    Period15/1/2515/1/30

    Fingerprint

    Array processing
    Microphones
    Acoustic waves
    Reverberation
    Video cameras
    Signal processing
    Animals
    Imaging techniques

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Bandog, Y., Otsuka, T., Aihara, I., Awano, H., Itoyama, K., Yoshii, K., & Okuno, H. G. (2015). Recognition of in-field frog chorusing using Bayesian nonparametric microphone array processing. In AAAI Workshop - Technical Report (Vol. WS-15-06, pp. 2-6). AI Access Foundation.

    Recognition of in-field frog chorusing using Bayesian nonparametric microphone array processing. / Bandog, Yoshiaki; Otsuka, Takuma; Aihara, Ikkyu; Awano, Hiromitsu; Itoyama, Katsutoshi; Yoshii, Kazuyoshi; Okuno, Hiroshi G.

    AAAI Workshop - Technical Report. Vol. WS-15-06 AI Access Foundation, 2015. p. 2-6.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Bandog, Y, Otsuka, T, Aihara, I, Awano, H, Itoyama, K, Yoshii, K & Okuno, HG 2015, Recognition of in-field frog chorusing using Bayesian nonparametric microphone array processing. in AAAI Workshop - Technical Report. vol. WS-15-06, AI Access Foundation, pp. 2-6, 29th AAAI Conference on Artificial Intelligence, AAAI 2015, Austin, United States, 15/1/25.
    Bandog Y, Otsuka T, Aihara I, Awano H, Itoyama K, Yoshii K et al. Recognition of in-field frog chorusing using Bayesian nonparametric microphone array processing. In AAAI Workshop - Technical Report. Vol. WS-15-06. AI Access Foundation. 2015. p. 2-6
    Bandog, Yoshiaki ; Otsuka, Takuma ; Aihara, Ikkyu ; Awano, Hiromitsu ; Itoyama, Katsutoshi ; Yoshii, Kazuyoshi ; Okuno, Hiroshi G. / Recognition of in-field frog chorusing using Bayesian nonparametric microphone array processing. AAAI Workshop - Technical Report. Vol. WS-15-06 AI Access Foundation, 2015. pp. 2-6
    @inproceedings{d215d2c0a0fb4bb6bfe2b31ab3651ebd,
    title = "Recognition of in-field frog chorusing using Bayesian nonparametric microphone array processing",
    abstract = "In this paper, we exploit Bayesian nonparametric microphone array processing (BNP-MAP) for analyzing the spatio- Temporal patterns of the frog chorus. Such analysis in real environments is made more difficult due to unpredictable sound sources including calls of various species of animals. An application of conventional signal processing algorithms has been difficult because these algorithms usually require the number of sound sources in advance. BNP-MAP is developed to cope with auditory uncertainties such as reverberation or unknown number of sounds by using a unified model based on Bayesian nonparametrics. We exploit BNP-MAP for analyzing the sound data of 20 minutes captured by a 7-channel microphone array in a paddy rice field in Oki Island, Japan, and revealed that two individuals of Schlegel's green tree frog {Rhacophorus schlegelii) called alternately with anti-phase. This result is compared with the video data captured by a video camera with 18 units of sound-imaging devices called Firefly deployed along the bank of the rice field. The auditory result provides more detailed patterns of the frog chorus in higher temporal resolutions. This higher resolution enables to analyze fine temporal structures of the frog calls. For example, BNP-MAP reveals the trill-like calling pattern of R. schlegelii.",
    author = "Yoshiaki Bandog and Takuma Otsuka and Ikkyu Aihara and Hiromitsu Awano and Katsutoshi Itoyama and Kazuyoshi Yoshii and Okuno, {Hiroshi G.}",
    year = "2015",
    language = "English",
    isbn = "9781577357179",
    volume = "WS-15-06",
    pages = "2--6",
    booktitle = "AAAI Workshop - Technical Report",
    publisher = "AI Access Foundation",

    }

    TY - GEN

    T1 - Recognition of in-field frog chorusing using Bayesian nonparametric microphone array processing

    AU - Bandog, Yoshiaki

    AU - Otsuka, Takuma

    AU - Aihara, Ikkyu

    AU - Awano, Hiromitsu

    AU - Itoyama, Katsutoshi

    AU - Yoshii, Kazuyoshi

    AU - Okuno, Hiroshi G.

    PY - 2015

    Y1 - 2015

    N2 - In this paper, we exploit Bayesian nonparametric microphone array processing (BNP-MAP) for analyzing the spatio- Temporal patterns of the frog chorus. Such analysis in real environments is made more difficult due to unpredictable sound sources including calls of various species of animals. An application of conventional signal processing algorithms has been difficult because these algorithms usually require the number of sound sources in advance. BNP-MAP is developed to cope with auditory uncertainties such as reverberation or unknown number of sounds by using a unified model based on Bayesian nonparametrics. We exploit BNP-MAP for analyzing the sound data of 20 minutes captured by a 7-channel microphone array in a paddy rice field in Oki Island, Japan, and revealed that two individuals of Schlegel's green tree frog {Rhacophorus schlegelii) called alternately with anti-phase. This result is compared with the video data captured by a video camera with 18 units of sound-imaging devices called Firefly deployed along the bank of the rice field. The auditory result provides more detailed patterns of the frog chorus in higher temporal resolutions. This higher resolution enables to analyze fine temporal structures of the frog calls. For example, BNP-MAP reveals the trill-like calling pattern of R. schlegelii.

    AB - In this paper, we exploit Bayesian nonparametric microphone array processing (BNP-MAP) for analyzing the spatio- Temporal patterns of the frog chorus. Such analysis in real environments is made more difficult due to unpredictable sound sources including calls of various species of animals. An application of conventional signal processing algorithms has been difficult because these algorithms usually require the number of sound sources in advance. BNP-MAP is developed to cope with auditory uncertainties such as reverberation or unknown number of sounds by using a unified model based on Bayesian nonparametrics. We exploit BNP-MAP for analyzing the sound data of 20 minutes captured by a 7-channel microphone array in a paddy rice field in Oki Island, Japan, and revealed that two individuals of Schlegel's green tree frog {Rhacophorus schlegelii) called alternately with anti-phase. This result is compared with the video data captured by a video camera with 18 units of sound-imaging devices called Firefly deployed along the bank of the rice field. The auditory result provides more detailed patterns of the frog chorus in higher temporal resolutions. This higher resolution enables to analyze fine temporal structures of the frog calls. For example, BNP-MAP reveals the trill-like calling pattern of R. schlegelii.

    UR - http://www.scopus.com/inward/record.url?scp=84964649344&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84964649344&partnerID=8YFLogxK

    M3 - Conference contribution

    SN - 9781577357179

    VL - WS-15-06

    SP - 2

    EP - 6

    BT - AAAI Workshop - Technical Report

    PB - AI Access Foundation

    ER -