The effect of mismatched recording conditions on human and automatic speaker recognition in forensic applications

Alexander, Anil; Botti, Filippo; Dessimoz, Damien; Drygajlo, Andrzej

doi:10.1016/j.forsciint.2004.09.078

Cited by 33 publications

(23 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The National Institute of Standards and Technology (NIST) 3 provides a common evaluation framework for text-independent speaker recognition methods [156]. NIST evaluations include test trials under both matched conditions such as telephone only, and unmatched conditions such as language effects (matched languages vs unmatched languages), cross channel and two-speaker detection.…”

Section: Performance Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

An overview of text-independent speaker recognition: From features to supervectors

Kinnunen¹,

Li²

2010

Speech Communication

1,240

706

View full text Add to dashboard Cite

This paper gives an overview of automatic speaker recognition technology, with an emphasis on text-independent recognition. Speaker recognition has been studied actively for several decades. We give an overview of both the classical and the state-of-the-art methods. We start with the fundamentals of automatic speaker recognition, concerning feature extraction and speaker modeling. We elaborate advanced computational techniques to address robustness and session variability. The recent progress from vectors towards supervectors opens up a new area of exploration and represents a technology trend. We also provide an overview of this recent development and discuss the evaluation methodology of speaker recognition systems. We conclude the paper with discussion on future directions.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

“…Much of information is exchanged between two parties in telephone conversations, including between criminals, and in recent years there has been increasing interest to integrate automatic speaker recognition to supplement auditory and semi-automatic analysis methods [3,76,174,185,223].…”

Section: Introductionmentioning

confidence: 99%

An overview of text-independent speaker recognition: From features to supervectors

Kinnunen¹,

Li²

2010

Speech Communication

1,240

706

View full text Add to dashboard Cite

show abstract

“…That is, in this particular instance, the main component of the developmental team consisted of engineers 3,52 , with the phoneticians (it appears anyway) serving as consultants. In this case, the research program is being carried out by an investigative team spread throughout Australia and Malaysia.…”

Section: Collaborationmentioning

confidence: 99%

Barriers to Progress in Speaker Identification with Comments on the Trayvon Martin Case

Hollien

2013

LESLI

View full text Add to dashboard Cite

Linguistics and phonetics overlap in many areas. The essay to follow reviews some of the problems experienced by phoneticians in one of these regions. It may provide some insight for linguists when they are confronted by barriers in their own field. The present example involves individuals who are attempting to identify speakers from voice analysis. The fundamental challenge they face is, of course, caused by the thousands of variables associated with that task. Included here are differences among speakers' gender, age, size, physiology, language, dialect, psychological/health states, background/education, reason for speaking, situation, environment, configuration of the acoustic channel --plus many others. Many formal assessment procedures --both aural-perceptual ones conducted by humans or machine/computer based systems --have been proposed and/or used for the cited analyses. Unfortunately, however, few have enjoyed particularly high levels of success. Worse yet, reasonable progress has suffered from external impedances; the report to follow will outline some of them. Among the problems considered are: 1) competition (verification vs. identification, from voiceprints), 2) concept disputes 3) the continued undervaluation of relevant evidence and 4) markedly dissimilar philosophies of professionals from different disciplines. A response in the form of a short review of the data and concepts which clearly support the possibility of robust speaker identification is presented. Also included are suggestions as to how to enhance the effectiveness of disciplines such as ours.

show abstract

“…Prosody seems to assume an important role in speech recordings with background noise. Reference [4] studied the impact of background noise in speaker recognition. The authors had added white noise in telephone calls and tested the possible cues listeners use to identify speakers in the presence of noise.…”

Section: Introductionmentioning

confidence: 99%

Prosodic characteristics of different varieties of Brazilian Portuguese

Constantini¹,

Barbosa²

2015

Rev. Bras. Crimin.

View full text Add to dashboard Cite

ResumoAnalisamos um conjunto particular de parâmetros prosódicos para caracterizar sete variedades do Português Brasileiro (PB). As amostras de fala de 35 indivíduos do sexo masculino, com idade média de 35,4 anos, de São Paulo, Minas Gerais, Rio de Janeiro, Paraná, Distrito Federal (DF), região Nordeste (NE) e região Norte (N) foram coletadas. As amostras foram segmentadas em unidades de vogal-a-vogal (unidades VV) e oito medidas foram extraídas: taxa de elocução, média, desvio padrão, assimetria de zscore suave de duração da unidade VV, taxa de proeminência, taxa de não-proeminente da unidade VV/s, ênfase espectral e mediana de F0. One-Way ANOVA (p <0,05) indicou significado para a taxa de não-proeminente da unidade VV, o desvio padrão, a assimetria de z-score, a ênfase espectral e a mediana de F0. Os resultados separaram variedades faladas no Norte daquelas no Sul. A descrição das características prosódicas é relevante para fins forenses, já que pode ser usado como prova e apoio durante a resolução do caso.Palavras-Chave: Fonética Forense; Dialetos; Prosódia. AbstractWe analyzed a particular set of prosodic parameters in order to characterize seven Brazilian Portuguese (BP) varieties. Speech samples from 35 male subjects, mean age of 35.4 years, from São Paulo, Minas Gerais, Rio de Janeiro, Paraná, Distrito Federal (DF), Northeast region (NE) and North region (N) were collected. The samples were segmented into Vowel-to-vowel units (VV units) and eight measures were extracted: speech rate, mean, standard deviation and skewness of smooth z-score of VV unit duration, prominence rate, rate of non-prominent VV unit/s, spectral emphasis and median of F0. One-Way ANOVA (p<0.05) has indicated significance for rate of non-prominent VV unit/s, standard deviation and skewness of z-score, spectral emphasis and median of F0. The findings separated varieties spoken in the North from those spoken in the South. The description of prosodic characteristics is relevant for forensic purposes since it can be used as evidence and support during case resolution.

show abstract

The effect of mismatched recording conditions on human and automatic speaker recognition in forensic applications

Cited by 33 publications

References 6 publications

An overview of text-independent speaker recognition: From features to supervectors

An overview of text-independent speaker recognition: From features to supervectors

Barriers to Progress in Speaker Identification with Comments on the Trayvon Martin Case

Prosodic characteristics of different varieties of Brazilian Portuguese

Contact Info

Product

Resources

About