• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Solving the cocktail party problem using deep learning

Research Project

Project/Area Number 18K19819
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Review Section Medium-sized Section 61:Human informatics and related fields
Research InstitutionOsaka University

Principal Investigator

Kitazawa Shigeru  大阪大学, 生命機能研究科, 教授 (00251231)

Project Period (FY) 2018-06-29 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥6,240,000 (Direct Cost: ¥4,800,000、Indirect Cost: ¥1,440,000)
Fiscal Year 2019: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2018: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Keywordsカクテルパーティー効果 / 深層学習 / transformer / 聴覚野
Outline of Final Research Achievements

We can hear what others are saying even at a party where many people are talking. In this study, we attempted to create an artificial neural network that directs attention to one of the overlapping speech signals by autonomous learning, with the goal of creating a neural circuit model that can be compared to the human brain. We showed that an artificial neural circuit model (transformer) equipped with an attention mechanism could "recognize" environmental sounds as multiple objects and acquire a mechanism to "pay attention" to any one of them. This audio-transformer may be a promising neural model for solving the mystery of the "cocktail party problem".

Academic Significance and Societal Importance of the Research Achievements

カクテルパーティー効果は私たちが日常で体験できる現象だが、その神経基盤は未知である。本研究では「特定の音に対して注意を向ける」人工神経回路を自律的な学習で作りだすことに成功した。最近Googleのグループなどが二人の音声を聞き分けることだけに特化した人工神経回路を発表しているが、それらは正解を与えて学習させる「教師付学習」を用いている。我々はそのような強制的な学習を行わずとも、環境音を聞いているうちに「自然に」音の特徴を使って聞き分けるように人工神経回路を育てることが可能であることを示した。ヒトは教師付学習を行っていないので、我々の得たモデルはよりヒトの脳に近いことが期待される。

Report

(5 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • 2018 Research-status Report
  • Research Products

    (4 results)

All 2020 2019 2018 Other

All Presentation (2 results) Book (1 results) Remarks (1 results)

  • [Presentation] Emergence of color constancy in an autoencoder with biologically plausible “batch normalization”2019

    • Author(s)
      Takuto Yamamoto *; Shigeru Kitazawa
    • Organizer
      第29回日本神経回路学会全国大会
    • Related Report
      2019 Research-status Report
  • [Presentation] Emergence of visual receptive field remapping in a convolutional neural network for sensory prediction2018

    • Author(s)
      Akiyama O, Kitazawa S
    • Organizer
      第41回日本神経科学学会大会
    • Related Report
      2018 Research-status Report
  • [Book] 医師・医学生のための人工知能入門2020

    • Author(s)
      北澤 茂
    • Total Pages
      192
    • Publisher
      中外医学社
    • Related Report
      2020 Research-status Report 2019 Research-status Report
  • [Remarks]

    • URL

      https://kitazawa-lab.jp/index.html

    • Related Report
      2019 Research-status Report

URL: 

Published: 2018-07-25   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi