• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2022 年度 実施状況報告書

Speech security on human-computer interaction

研究課題

研究課題/領域番号 22K21304
研究機関北陸先端科学技術大学院大学

研究代表者

MAWALIM CandyOlivia  北陸先端科学技術大学院大学, 先端科学技術研究科, 助教 (10963720)

研究期間 (年度) 2022-08-31 – 2024-03-31
キーワードvoice privacy / time scale modification / phase vocoder / speaker anonymization / gender
研究実績の概要

In this fiscal year, we proposed speaker anonymization methods based on time scale modification (TSM) algorithms. The study finds that using the phase vocoder-based TSM method is more suitable for speaker anonymization due to the human voice's harmonic structures. The proposed method balances privacy and utility metrics better than baseline systems. Besides, we also analyzed the effect of anonymization on the perception of gender by utilizing a gender classifier model that was built using x-vector speaker embedding. The results of our study were presented at the Voice Privacy Challenge 2022, joint with the Interspeech 2022 conference and the 14th annual conference organized by Asia-Pacific Signal and Information Processing Association 2022.

現在までの達成度 (区分)
現在までの達成度 (区分)

2: おおむね順調に進展している

理由

The progress of this project is going well as planned. The speech analysis has been performed to obtain the features related to personally identified information (PII). We investigate pitch shifting using two major categories of TSM algorithms for speaker anonymization. Our recent finding from this study is that the human voice contains harmonic structures; thus, applying PV-TSM, which is more suited to a harmonic component, could benefit speaker anonymization. Subsequently, the phase adaptation may manipulate not only fundamental frequency but also the PII-related acoustics features. Our method outperformed the x-vector-based speaker method, which has limitations in its complex training process, low privacy in an a-a scenario, and low voice distinctiveness.

今後の研究の推進方策

In the currently proposed methods, several remaining issues exist. For instance, the speaker anonymization target needs to be clearly defined. As a result, the application for speaker anonymization has several limitations on the attack models. In the future, the development of more secure and robust speaker anonymization with attack models will be the focus. Hence, it can be applied for broader applications. Important ethical and privacy concerns will also be considered when developing speaker anonymization techniques.

次年度使用額が生じた理由

The incurring amount is required to fund ongoing research for publication and travel fees in the next fiscal year.

  • 研究成果

    (6件)

すべて 2023 2022

すべて 雑誌論文 (1件) (うち国際共著 1件、 査読あり 1件、 オープンアクセス 1件) 学会発表 (5件) (うち国際学会 5件)

  • [雑誌論文] Personality trait estimation in group discussions using multimodal analysis and speaker embedding2023

    • 著者名/発表者名
      Mawalim Candy Olivia、Okada Shogo、Nakano Yukiko I.、Unoki Masashi
    • 雑誌名

      Journal on Multimodal User Interfaces

      巻: - ページ: -

    • DOI

      10.1007/s12193-023-00401-0

    • 査読あり / オープンアクセス / 国際共著
  • [学会発表] Multimodal Analysis for Communication Skill and Self-Efficacy Level Estimation in Job Interview Scenario2022

    • 著者名/発表者名
      Ohba Tomoya、Mawalim Candy Olivia、Katada Shun、Kuroki Haruki、Okada Shogo
    • 学会等名
      The 21st International Conference on Mobile and Ubiquitous Multimedia (MUM 2022)
    • 国際学会
  • [学会発表] F0 Modification via PV-TSM Algorithm for Speaker Anonymization Across Gender2022

    • 著者名/発表者名
      Mawalim Candy Olivia、Okada Shogo、Unoki Masashi
    • 学会等名
      2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference
    • 国際学会
  • [学会発表] Speaker Anonymization by Pitch Shifting Based on Time-Scale Modification2022

    • 著者名/発表者名
      Mawalim Candy Olivia、Okada Shogo、Unoki Masashi
    • 学会等名
      The 2nd SPSC joined with 2nd VoicePrivacy Challenge Workshop, as a satellite to Interspeech 2022
    • 国際学会
  • [学会発表] Speech Intelligibility Prediction for Hearing Aids Using an Auditory Model and Acoustic Parameters2022

    • 著者名/発表者名
      Titalim Benita Angela、Mawalim Candy Olivia、Okada Shogo、Unoki Masashi
    • 学会等名
      2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference
    • 国際学会
  • [学会発表] OBISHI: Objective Binaural Intelligibility Score for the Hearing Impaired2022

    • 著者名/発表者名
      Mawalim Candy Olivia、Titalim Benita Angela、Okada Shogo、Unoki Masashi
    • 学会等名
      The 18th Australasian International Conference on Speech Science and Technology
    • 国際学会

URL: 

公開日: 2023-12-25  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi