Forensic Automatic Speaker Recognition with Degraded and Enhanced Speech

被引:0
|
作者
Kuenzel, Hermann [1 ]
Alexander, Paul [2 ]
机构
[1] Univ Marburg, Dept Phonet, D-35039 Marburg, Germany
[2] Cedar Audio Ltd, Cambridge CB21 5BS, England
来源
关键词
NOISE-REDUCTION;
D O I
暂无
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
In an exploratory study a set of signal degradations typically found in forensic speaker recognition tasks were investigated for their effects on the performance of an automatic forensic speaker recognition (SR) system. Enhancement algorithms tailored to the types and degrees of the degradations were applied. Comparing equal-error rates (EERs) for voice comparisons with ten male speakers based on the original, degraded, and enhanced voice signals the performance of the SR system was most affected by pop music in both single-channel and 2-channel recordings and noise inside a fast moving car-and the effects of exactly these types of additive noise could be reduced most by speech enhancement. Road traffic and restaurant noise did not affect the system's performance significantly (EERs <2%) and could not be reduced further. The same applies to severe amplitude clipping and room reverberation, which produced equal error rates between zero and half a percent.
引用
收藏
页码:244 / 253
页数:10
相关论文
共 50 条
  • [21] Improved automatic speech recognition through speaker normalization
    Giuliani, D
    Gerosa, M
    Brugnara, F
    [J]. COMPUTER SPEECH AND LANGUAGE, 2006, 20 (01): : 107 - 123
  • [22] Statistical Evaluation of Biometric Evidence in Forensic Automatic Speaker Recognition
    Drygajlo, Andrzej
    [J]. COMPUTATIONAL FORENSICS, PROCEEDINGS, 2009, 5718 : 1 - 12
  • [23] Interchangeability of calibration audio datasets for forensic automatic speaker recognition
    van der Vloed, David
    [J]. 12TH INTERNATIONAL WORKSHOP ON BIOMETRICS AND FORENSICS, IWBF 2024, 2024,
  • [24] Forensic identification reporting using automatic speaker recognition systems
    Gonzalez-Rodriguez, J
    Fierrez-Aguilar, J
    Ortega-Garcia, J
    [J]. 2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PROCEEDINGS: SPEECH II; INDUSTRY TECHNOLOGY TRACKS; DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS; NEURAL NETWORKS FOR SIGNAL PROCESSING, 2003, : 93 - 96
  • [25] On the Use of Speaker Information for Automatic Speech Recognition in Speaker-imbalanced Corpora
    Soky, Kak
    Li, Sheng
    Mimura, Masato
    Chu, Chenhui
    Kawahara, Tatsuya
    [J]. 2021 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2021, : 433 - 437
  • [26] Polyaural Array Processing for Automatic Speech Recognition in Degraded Environments
    Stern, Richard M.
    Gouvea, Evandro
    Thattai, Govindarajan
    [J]. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 2804 - +
  • [27] Extracting accent information from Urdu speech for forensic speaker recognition
    Tahir, Falak
    Saleem, Sajid
    Ahmad, Ayaz
    [J]. TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2019, 27 (05) : 3763 - 3778
  • [28] Enhanced Forensic Multiple Speaker Recognition in the Presence of Coloured Noise
    Denk, Florian
    da Costa, Joao Paulo C. L.
    Silveira, Matheus Almeida
    [J]. 2014 8TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATION SYSTEMS (ICSPCS), 2014,
  • [29] Impact of Emotional Speech to Automatic Speaker Recognition - Experiments on GEES Speech Database
    Jokic, Ivan
    Jokic, Stevan
    Delic, Vlado
    Peric, Zoran
    [J]. SPEECH AND COMPUTER, 2014, 8773 : 268 - 275
  • [30] Analyzing the impact of speaker localization errors on speech separation for automatic speech recognition
    Sivasankaran, Sunit
    Vincent, Emmanuel
    Fohr, Dominique
    [J]. 28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 346 - 350