INFORMATION

15/04/2021
New!　Our paper has been accepted to IJCNN2021 (2021/7/18~2021/7/22)
  • D. Niizumi, D. Takeuchi, Y. Ohishi, N. Harada, K. Kashino, "BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation,"

    • 10/10/2020
    Our paper has been accepted to ICPR2020 (2021/1/10~2021/1/15)
  • Y. Ohishi, Y. Tanaka, K. Kashino, "Unsupervised Co-Segmentation for Athlete Movements and Live Commentaries Using Crossmodal Temporal Proximity,"

    • 10/9/2020
    Our paper has been accepted to DCASE2020 Workshop (2020/11/2~2020/11/3)
  • D. Takeuchi, Y. Koizumi, Y. Ohishi, N. Harada, K. Kashino, "Effects of Word-Frequency based Pre- and Post- Processings for Audio Captioning,"

    • 25/7/2020
    Our paper has been accepted to Interspeech2020 (2020/10/25~2020/10/29)
  • Y. Ohishi, A. Kimura, T. Kawanishi, K. Kashino, D. Harwath, and J. Glass, "Pair Expansion for Learning Multilingual Semantic Embeddings using Disjoint Visually-grounded Speech Audio Datasets,"

  • M. Yasuda, Y. Ohishi, Y. Koizumi, and N. Harada, "Crossmodal Sound Retrieval based on Specific Target Co-occurrence Denoted with Weak Labels,"

  • H. Takeuchi, K. Kashino, Y. Ohishi, and H. Saruwatari, "Harmonic Lowering for Accelerating Harmonic Convolution for Audio Signals,"
    • 1/7/2020
    NTT team ranked the first place in automated audio captioning (Task6) of this year's Detection and Classification of Acoustic Scenes and Events (DCASE2020) competition
  • Y. Koizumi, D. Takeuchi, Y. Ohishi, N. Harada, K. Kashino, "The NTT DCASE2020 Challenge Task 6 System: Automated Audio Captioning with Keywords and Sentence Length Estimation (Technical Repor)," in Proc. DCASE 2020 - the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE).

    • Also see NTT Topics!
    4~8/5/2020
    Present our research at oral session of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2020@Barcelona, Spain
    Y. Ohishi, A. Kimura, T. Kawanishi, K. Kashino, D. Harwath, and J. Glass,
    "Trilingual Semantic Embeddings of Visually Grounded Speech with Self-attention Mechanisms," 'Signal Processing for Multimedia Applications I'
    5/10/2017
    Back to NTT CSL
    Activities 2014
    5/9/2014
    Transfer to NTT DATA
    It's a pleasure doing business with you!
    5/9/2014
    Received 36th Awaya Kiyoshi Science Promotion Award from Acoustical Society of Japan (ASJ)
    15/7/2014
    Gave a special lecture on audio content-based music retrieval at Graduate School of Information Science, Nagoya University
    Please check the papers here.
    5,6/6/2014
    NTT Communication Science Labs. OPEN HOUSE 2014
    Date: 5/6/2014 THU. 12:00-17:30, 5/6/2014 FRI. 9:30-16:00
    Place: NTT Keihanna Building, No Admission Charge, No Pre-registration Required
    http://www.kecl.ntt.co.jp/openhouse/2014/
    25/5/2014
    24,25/5/2014
    Presented our research at a poster session of the Ongaku Symposium 2014
    Yasunori Ohishi, Daichi Mochihashi, Hirokazu Kameoka, Kunio Kashino,
    "Prediction of Vocal F0 Contour and Singing Style Conversion based on Mixture of Gaussian Process Experts"
    4~9/5/2014
    Presented our researches at oral and poster sessions of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2014@Florence, Italy
    Yasunori Ohishi, Daichi Mochihashi, Hirokazu Kameoka, Kunio Kashino,
    "Mixture of Gaussian process experts for predicting sung melodic contour with expressive dynamic fluctuations"
    Masahiro Nakano, Yasunori Ohishi, Hirokazu Kameoka, Ryo Mukai, Kunio Kashino,
    "Mondrian hidden Markov model for music signal processing"
    Please check the papers here.

    PROFILE

    Japanese cherry

    1981.12 Born in Aichi Prefecture, Japan
    2000.03 Graduated from Aichi prefectual Okazaki high school
    2004.03 Graduated from Department of Electrical and Electoronic Engineering and Information Engineering, Nagoya University
    2009.03 Received Ph.D. from Nagoya University.
    Currently, Yasunori Ohishi is with NTT Communication Science Laboratories, Media Information Laboratory.


    Research Interests

    Publications

    Ph.D. Thesis

    Journals

    1. K. Imoto, Y. Ohishi, H. Uematsu, H. Omuro, N. Ono, "Online acoustic scene analysis with sequentially obtained acoustic event sequence," Journal of the Acoustival Society of Japan, 72(6) pp. 293-305, 2016.

    2. H. Kameoka, K. Yoshizato, T. Ishihara, K. Kadowaki, Y. Ohishi, and K. Kashino, "Generative Modeling of Voice Fundamental Frequency Contours," IEEE/ACM Trans. Audio, Speech and Language Processing, Vol. 23, No. 6, pp. 1042–1053, 2015.

    3. Yasunori Ohishi, Masataka Goto, Katunobu Itou, and Kazuya Takeda. "Sung Melodic Contour Characterized in Phase Plane: Estimation of Target Note Sequence from the Melodic Contour and Its Application for Query-by-humming," IPSJ Journal, vol.49, no.11, pp.3789-3797, Nov. 2008, (in Japanese).

    4. Yasunori Ohishi, Masataka Goto, Katunobu Itou, and Kazuya Takeda. "Discrimination between Singing and Speaking Voices Using a Spectral Envelope and a Fundamental Frequency Derivative," IPSJ Journal, vol.47, no.6, pp.1822-1830, June 2006, (in Japanese).

    Letter

    1. Yasunori Ohishi, Katunobu Itou, Kazuya Takeda, Atsushi Fujii, and Fumitada Itakura. "Statistical Analysis for the hierarchy Using an Encyclopedic Corpus," Information Technology Letters, FIT2004, LF-001, Sept. 2004. (in Japanese).

    Conference Papers

    1. Yasunori Ohishi, Daichi Mochihashi, Hirokazu Kameoka, Kunio Kashino, "Mixture of Gaussian process experts for predicting sung melodic contour with expressive dynamic fluctuations," In Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP2014), pp.3742-3746, May 2014.  (PDF) (Oral)

    2. Masahiro Nakano, Yasunori Ohishi, Hirokazu Kameoka, Ryo Mukai, Kunio Kashino, "Mondrian hidden Markov model for music signal processing," In Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP2014), pp.2424-2428, May 2014.

    3. Keisuke Imoto, Yasunori Ohishi, Hisashi Uematsu, Hitoshi Ohmuro, "Acoustic Scene Analysis Based On Latent Acoustic Topic And Event Allocation," In Proc. International Workshop on Machine Learning for Signal Processing (MLSP 2013), Sep. 2013.

    4. Hirokazu Kameoka, Kota Yoshizato, Tatsuma Ishihara, Yasunori Ohishi, Kunio Kashino and Shigeki Sagayama, "Generative modeling of speech F0 contours," In Proc. International Conference on Spoken Language Processing (INTERSPEECH 2013), Aug. 2013.  (PDF)

    5. Yasunori Ohishi, Daichi Mochihashi, Tomoko Matsui, Masahiro Nakano, Hirokazu Kameoka, Tomonori Izumitani, Kunio Kashino, "Bayesian Semi-supervised Audio Event Transcription based on Markov Indian buffet Process," In Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP2013), June 2013.  (PDF) (Oral)

    6. Yasunori Ohishi, Hirokazu Kameoka, Daichi Mochihashi, Kunio Kashino, "A Stochastic Model of Singing Voice F0 Contours for Characterizing Expressive Dynamic Components," In Proc. International Conference on Spoken Language Processing (INTERSPEECH 2012), Sep. 2012.  (PDF) (Poster)

    7. Masahiro Nakano, Yasunori Ohishi, Hirokazu Kameoka, Ryo Mukai, Kunio Kashino, "Bayesian Nonparametric Music Parser," In Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP2012), pp. 461-464, Mar. 2012. (PDF) (Poster)

    8. Jun Takagi, Yasunori Ohishi, Akisato Kimura, Masashi Sugiyama, Makoto Yamada, Hirokazu Kameoka, "Automatic Audio Tag Classification via Semi-supervised Canonical Density Estimation," In Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP2011), pp. 2232-2235, May 2011. (PDF) (Poster)

    9. Yasunori Ohishi, Hirokazu Kameoka, Daichi Mochihashi, Hidehisa Nagano, Kunio Kashino, "Statistical Modeling of F0 Dynamics in Singing Voices Based on Gaussian Processes with Multiple Oscillation Bases," In Proc. International Conference on Spoken Language Processing (INTERSPEECH 2010), pp. 2598-2601, Sept. 2010. (PDF) (Oral)

    10. Hirokazu Kameoka, Jonathan Le Roux, Yasunori Ohishi, "A statistical model of speech F0 contours," ISCA Tutorial and Research Workshop on Statistical And Perceptual Audition (SAPA 2010), pp. 43-48, Sept. 2010. (PDF)

    11. Tatsuya Kako, Yasunori Ohishi, Hirokazu Kameoka, Kunio Kashino and Kazuya Takeda, "Automatic Identification for Singing Style Based on Sung Melodic Contour Characterized in Phase Plane," In Proc. International Conference on Music Information Retrieval, (ISMIR 2009), pp. 393-397, Oct. 2009. (PDF) (Poster)

    12. Yasunori Ohishi, Hirokazu Kameoka, Kunio Kashino, and Kazuya Takeda, "Parameter Estimation Method of F0 Control Model for Singing Voices," In Proc. International Conference on Spoken Language Processing (INTERSPEECH 2008), pp. 139-142, Sept. 2008. (PDF) (Poster)

    13. Ryoei Takahashi, Yasunori Ohishi, Norihide Kitaoka, and Kazuya Takeda, "Building and Combining Document and Music Spaces for Music Query-By-Webpage System," In Proc. International Conference on Spoken Language Processing (INTERSPEECH 2008), pp. 2020-2023, Sept. 2008. (PDF) (Oral)

    14. Ryoei Takahashi, Yasunori Ohishi, and Kazuya Takeda, "Associating document and acoustic spaces for a WEB-BGM system," In Proc. International Conference on Music Communication Science (ICoMCS 2007), Dec. 2007.

    15. Yasunori Ohishi, Masataka Goto, Katunobu Itou, and Kazuya Takeda, "A Stochastic Representation of the Dynamics of Sung Melody," In Proc. International Conference on Music Information Retrieval (ISMIR 2007), pp. 371-372, Sept. 2007. (PDF) (Poster)

    16. Yasunori Ohishi, Masataka Goto, Katunobu Itou, and Kazuya Takeda, "Automatic Discrimination between Singing and Speaking Voices for Flexible Music Retrieval System," The 152th Meeting of the Acoustical Society of America (ASA) / 4th Joint Meeting of the Acoustical Society of America and the Acoustical Society of Japan, Dec. 2006. (Oral)

    17. Yasunori Ohishi, Masataka Goto, Katunobu Itou, and Kazuya Takeda, "On the human capability and acoustic cues for discriminating the singing and the speaking voices," In Proc. International Conference on Music Perception and Cognition (ICMPC 2006), pp. 1831-1837, Aug. 2006. (PDF) (Oral)

    18. Yasunori Ohishi, Katunobu Itou, Kazuya Takeda, and Atsushi Fuji, "Statistical Analysis for Thesaurus Construction using an Encyclopedic Corpus," In Proc. Language Resources and Evaluation Conference (LREC 2006), pp. 1368-1371, May 2006. (PDF) (Poster)

    19. Yasunori Ohishi, Masataka Goto, Katunobu Itou, and Kazuya Takeda, "Discrimination between Singing and Speaking Voices," In Proc. European Conference on Speech Communication and Technology (EUROSPEECH 2005), pp. 1141-1144, Sept. 2005. (PDF) (Oral)

    Others

    1. Yasunori Ohishi, "Audio content-based music retrieval," A special lecture at Graduate School of Information Science, Nagoya University, July 2014. (Lecture)

    2. Yasunori Ohishi, "Extracting Personal Characteristics from Singing Voice," Digital Media Analysis, Search and Management (DMASM) 2013, Feb. 2013. (Oral)

    3. Yasunori Ohishi, "Singing style extraction based on singing voice F0 model," NTT Technical review Digital Library, Aug. 2012.

    Awards

    Hobbies

    Links

    E-mail

    ohishi.yasunori{at}lab.ntt.co.jp