Style variability in disfluency analysis for forensic speaker comparison

被引:2
|
作者
Harrington, Lauren [1 ]
Rhodes, Richard [2 ,4 ]
Hughes, Vincent [3 ]
机构
[1] Univ York, York, N Yorkshire, England
[2] Univ York, Dept Language & Linguist Sci, York, N Yorkshire, England
[3] Univ York, Forens Speech Sci, York, N Yorkshire, England
[4] JP French Associates, York, N Yorkshire, England
基金
英国艺术与人文研究理事会;
关键词
DISFLUENCIES; DISFLUENCY ANALYSIS; TOFFA; FORENSIC SPEAKER COMPARISON; SPEAKING STYLES; SPEECH; DISTURBANCES; FLUENCY;
D O I
10.1558/ijsll.20214
中图分类号
DF [法律]; D9 [法律];
学科分类号
0301 ;
摘要
Disfluencies are a natural part of speech, often going unnoticed by both speaker and listener. Recent research on disfluency profiles (McDougall and Duckworth 2017, 2018) shows that they contain speaker-specific information which could be analysed and compared in forensic speaker comparison (FSC) casework. Since samples in FSC tend to be mismatched for speaking situation and style, the present study investigates the consistency of speakers' disfluency production across three forensically relevant tasks: a mock police interview, a paired conversation and a voicemail message. Disfluency production was found to differ significantly across tasks; in some cases, extreme within-speaker variation was observed. The results demonstrate that a speaker's disfluency behaviour is unlikely to remain consistent across different situations. However, it was found that some individuals who demonstrated unusual production of a particular type of disfluency showed relatively consistent production of that type across all three tasks. Consequently, we recommend that disfluency analysis is not used in FSC where there are marked differences in speaking style or situation, unless distinctive disfluency production is observed in a sample.
引用
收藏
页码:31 / 58
页数:28
相关论文
共 50 条
  • [41] VARIABILITY OF STUTTERERS SPEECH DISFLUENCY - MENSTRUAL-CYCLE
    SILVERMAN, EM
    ZIMMER, CH
    SILVERMAN, FH
    [J]. PERCEPTUAL AND MOTOR SKILLS, 1974, 38 (03) : 1037 - 1038
  • [42] Speaker/Style-Dependent Neural Network Speech Synthesis Based on Speaker/Style Embedding
    Secujski, Milan
    Pekar, Darko
    Suzic, Sinisa
    Smirnov, Anton
    Nosek, Tijana
    [J]. JOURNAL OF UNIVERSAL COMPUTER SCIENCE, 2020, 26 (04) : 434 - 453
  • [43] The inference of identity in forensic speaker recognition
    Champod, C
    Meuwly, D
    [J]. SPEECH COMMUNICATION, 2000, 31 (2-3) : 193 - 203
  • [44] Probabilistic decision in forensic speaker identification
    Federico, A
    Paoloni, A
    [J]. FORENSIC SCIENCE INTERNATIONAL, 2003, 136 : 372 - 372
  • [45] Voice quality and forensic speaker identification
    Nolan, Francis
    [J]. GOVOR, 2007, 24 (02) : 111 - 128
  • [46] Forensic Speaker Recognition A need for caution
    Campbell, Joseph P.
    Shen, Wade
    Campbell, William M.
    Schwartz, Reva
    Bonastre, Jean-Francois
    Matrouf, Driss
    [J]. IEEE SIGNAL PROCESSING MAGAZINE, 2009, 26 (02) : 95 - 103
  • [47] Intra-speaker phonetic variation in read speech: comparison with inter-speaker variability in a controlled population
    Audibert, Nicolas
    Fougeronl, Cecile
    [J]. INTERSPEECH 2022, 2022, : 4755 - 4759
  • [48] SENSE OF STYLE - INTRODUCTION TO STYLE FOR PUBLIC SPEAKER - BLANKENSHIP,J
    BURKS, DM
    [J]. SPEECH TEACHER, 1971, 20 (03): : 225 - 226
  • [49] Histomorphological analysis of the variability of the human skeleton: forensic implications
    Cummaudo, Marco
    Cappella, Annalisa
    Biraghi, Miranda
    Raffone, Caterina
    Marquez-Grant, Nicholas
    Cattaneo, Cristina
    [J]. INTERNATIONAL JOURNAL OF LEGAL MEDICINE, 2018, 132 (05) : 1493 - 1503
  • [50] SPEAKER VARIABILITY IN SPEECH BASED EMOTION MODELS - ANALYSIS AND NORMALISATION
    Sethu, Vidhyasaharan
    Epps, Julien
    Ambikairajah, Eliathamby
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7522 - 7526