Speech security on human-computer interaction

人机交互的语音安全

• 批准号: 22K21304
• 负责人: MAWALIM CandyOlivia
• 金额: $ 1.83万
• 依托单位: Japan Advanced Institute of Science and Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Research Activity Start-up
• 财政年份: 2022
• 资助国家: 日本
• 起止时间: 2022-08-31 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-22K21304/
• 关键词: voice privacy; time scale modification; phase vocoder; speaker anonymization; gender; HCI; speech security

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.

在本财政年度，我们提出了基于时间尺度修改（TSM）算法的说话人匿名方法。研究发现，基于相位声码器的TSM方法更适合于说话人匿名，这是由于人类语音的谐波结构。所提出的方法比基线系统更好地平衡了隐私和实用性指标。此外，我们还利用使用x向量说话人嵌入构建的性别分类器模型分析了匿名化对性别感知的影响。我们的研究结果在2022年语音隐私挑战赛上发表，与2022年Interspeech会议和2022年亚太信号和信息处理协会组织的第14届年会联合举行。

项目成果

F0 Modification via PV-TSM Algorithm for Speaker Anonymization Across Gender

• DOI: 10.23919/apsipaasc55919.2022.9979993
• 发表时间: 2022-11
• 期刊: 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
• 作者: Candy Olivia Mawalim;S. Okada;M. Unoki

Personality trait estimation in group discussions using multimodal analysis and speaker embedding

• DOI: 10.1007/s12193-023-00401-0
• 发表时间: 2023-02
• 期刊: Journal on Multimodal User Interfaces
• 影响因子: 2.9
• 作者: Candy Olivia Mawalim;S. Okada;Y. Nakano;M. Unoki

Speech Intelligibility Prediction for Hearing Aids Using an Auditory Model and Acoustic Parameters

使用听觉模型和声学参数预测助听器的语音清晰度

• DOI: 10.23919/apsipaasc55919.2022.9980000
• 发表时间: 2022
• 期刊: Proc. APSIPA2022
• 作者: Titalim Benita Angela;Mawalim Candy Olivia;Okada Shogo;Unoki Masashi
• 通讯作者: Unoki Masashi

Multimodal Analysis for Communication Skill and Self-Efficacy Level Estimation in Job Interview Scenario

面试场景中沟通技巧和自我效能水平评估的多模态分析

• 发表时间: 2022
• 作者: Ohba Tomoya;Mawalim Candy Olivia;Katada Shun;Kuroki Haruki;Okada Shogo
• 通讯作者: Okada Shogo

Speaker anonymization by pitch shifting based on time-scale modification

• DOI: 10.21437/spsc.2022-7
• 发表时间: 2022-09
• 期刊: 2nd Symposium on Security and Privacy in Speech Communication
• 作者: Candy Olivia Mawalim;S. Okada;M. Unoki