A PRIVACY-PRESERVING AND LANGUAGE-INDEPENDENT SPEECH PROCESSING AND CHARACTERISTICS MEASURING METHOD FOR SPONTANEOUS CONVERSATION

被引:0
|
作者
Zhang, Ni [1 ]
机构
[1] Fujitsu Labs Ltd, Human Ctr Comp Lab, Kawasaki, Kanagawa 211, Japan
关键词
Speech processing; Prosodic features; Voiced/unvoiced sound; Hidden Markov Model; CLASSIFICATION;
D O I
暂无
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Conversation conveys important social signals of human interaction that indicates interest, service-awareness, persuasiveness, etc. Our research aims at perceiving human interest and intention by identifying social signals of interaction in their conversation. In this paper, the author introduces a privacy-preserving and language-independent speech processing approach to measure vocal interaction characteristics for spontaneous conversation in-between two people. The approach has been tested with Japanese, English, and Chinese so far. The experimental results prove that it is possible to identify the difference of speaking styles and interaction pattern using the conversation characteristics measured.
引用
收藏
页码:19 / 25
页数:7
相关论文
共 13 条
  • [1] A Privacy-preserving and Language-independent Speaking Detecting and Speaker Diarization Approach for Spontaneous Conversation using Microphones
    Zhang, Ni
    Yaginuma, Yoshinori
    [J]. PROCEEDINGS OF 2012 IEEE 11TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP) VOLS 1-3, 2012, : 499 - 502
  • [2] Privacy-Preserving Speech Processing
    Pathak, Manas A.
    Raj, Bhiksha
    Rane, Shantanu
    Smaragdis, Paris
    [J]. IEEE SIGNAL PROCESSING MAGAZINE, 2013, 30 (02) : 62 - 74
  • [3] Privacy-preserving Federated Learning and its application to natural language processing
    Nagy, Balazs
    Hegedus, Istvan
    Sandor, Noemi
    Egedi, Balazs
    Mehmood, Haaris
    Saravanan, Karthikeyan
    Loki, Gabor
    Kiss, Akos
    [J]. KNOWLEDGE-BASED SYSTEMS, 2023, 268
  • [4] A new algorithm-independent method for privacy-preserving data mining
    [J]. Li, G. (hit6006@126.com), 1600, Binary Information Press (10):
  • [5] SecureNLP: A System for Multi-Party Privacy-Preserving Natural Language Processing
    Feng, Qi
    He, Debiao
    Liu, Zhe
    Wang, Huaqun
    Choo, Kim-Kwang Raymond
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2020, 15 : 3709 - 3721
  • [7] PRIVACY-PRESERVING DISTRIBUTED SPEECH ENHANCEMENT FOR WIRELESS SENSOR NETWORKS BY PROCESSING IN THE ENCRYPTED DOMAIN
    Hendriks, Richard C.
    Erkin, Zekeriya
    Gerkmann, Timo
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7005 - 7009
  • [8] A new algorithm-independent method for privacy-preserving classification based on sample generation
    School of Electronic and Control Engineering, Chang’an University, Xi’an
    Shaanxi
    710064, China
    [J]. Open. Cybern. Syst. J, 1 (443-447):
  • [9] Language-independent processing in speech perception: Identification of English intervocalic consonants by speakers of eight European languages
    Cooke, Martin
    Garcia Lecumberri, Maria Luisa
    Scharenborg, Odette
    van Dommelen, Wim A.
    [J]. SPEECH COMMUNICATION, 2010, 52 (11-12) : 954 - 967
  • [10] Privacy-Preserving Data Processing Method for IoV Based on Homomorphic Conjugacy Search Problem
    Mi, Bo
    Zhou, Jinfu
    Huang, Darong
    Weng, Yuan
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (07) : 7374 - 7387