Speaker Verification by Human Listeners: Experiments Comparing Human and Machine Performance Using the NIST 1998 Speaker Evaluation Data

Schmidt-Nielsen, Astrid; Crystal, Thomas H.

doi:10.1006/dspr.1999.0356

Cited by 51 publications

(36 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This exploratory study can help shed light on the acoustic cues used by the human auditory system for spoofing detection. There are a few interesting comparisons of human performance to that of ASV systems [88], [89], [90], but only one attempt to compare human performance to automatic spoofing detection [91]. This study compares the performance of 100 native English listeners to an automatic approach using a combination of MFCCand CNFP-based detectors.…”

Section: Table V Comparative Performance Of Several Post-evaluation mentioning

confidence: 99%

ASVspoof: The Automatic Speaker Verification Spoofing and Countermeasures Challenge

Yamagishi

Kinnunen

et al. 2017

IEEE J. Sel. Top. Signal Process.

250

302

View full text Add to dashboard Cite

Abstract-Concerns regarding the vulnerability of automatic speaker verification (ASV) technology against spoofing can undermine confidence in its reliability and form a barrier to exploitation. The absence of competitive evaluations and the lack of common datasets has hampered progress in developing effective spoofing countermeasures. This paper describes the ASV Spoofing and Countermeasures (ASVspoof) initiative, which aims to fill this void. Through the provision of a common dataset, protocols, and metrics, ASVspoof promotes a sound research methodology and fosters technological progress. This paper also describes the ASVspoof 2015 dataset, evaluation, and results with detailed analyses. A review of post-evaluation studies conducted using the same dataset illustrates the rapid progress stemming from ASVspoof and outlines the need for further investigation. Priority future research directions are presented in the scope of the next ASVspoof evaluation planned for 2017.

show abstract

Section: Table V Comparative Performance Of Several Post-evaluation mentioning

confidence: 99%

ASVspoof: The Automatic Speaker Verification Spoofing and Countermeasures Challenge

Yamagishi

Kinnunen

et al. 2017

IEEE J. Sel. Top. Signal Process.

250

302

View full text Add to dashboard Cite

show abstract

“…On the other hand, similar to speech recognition tasks, human listeners perform robustly in speaker recognition tasks [28]. The human ability to function well in noisy acoustic environments is due to a perceptual process termed auditory scene analysis (ASA) [2].…”

Section: Introductionmentioning

confidence: 99%

CASA-Based Robust Speaker Identification

Zhao

Shao

Wang

2012

IEEE Trans. Audio Speech Lang. Process.

143

View full text Add to dashboard Cite

Abstract-Conventional speaker recognition systems perform poorly under noisy conditions. Inspired by auditory perception, computational auditory scene analysis (CASA) typically segregates speech by producing a binary time-frequency mask. We investigate CASA for robust speaker identification. We first introduce a novel speaker feature, gammatone frequency cepstral coefficient (GFCC), based on an auditory periphery model, and show that this feature captures speaker characteristics and performs substantially better than conventional speaker features under noisy conditions. To deal with noisy speech, we apply CASA separation and then either reconstruct or marginalize corrupted components indicated by a CASA mask. We find that both reconstruction and marginalization are effective. We further combine the two methods into a single system based on their complementary advantages, and this system achieves significant performance improvements over related systems under a wide range of signal-to-noise ratios.Index Terms-Computational auditory scene analysis (CASA), gammatone frequency cepstral coefficient (GFCC), ideal binary mask, robust speaker identification.

show abstract

“…Traditionally, automatic speaker recognition systems have relied mostly on low-level characteristics by using short-term features related to the spectrum of the voice, associated mainly to the physical traits of the vocal apparatus. However, humans rely on several linguistic levels contained in the speech signal in order to identify people from voice alone [1]: the voice timbre, a characteristic laugh, specific and repeatedly used words, etc. In contrast to the spectral level, these linguistic features are mainly related to the learned habits and style.…”

Section: Introductionmentioning

confidence: 99%

Using Jitter and Shimmer in speaker verification

Farrús

Hernando

2009

IET Signal Process.

View full text Add to dashboard Cite

Jitter and shimmer are measures of the fundamental frequency and amplitude cycle-to-cycle variations, respectively. Both features have been largely used for the description of pathological voices, and since they characterise some aspects concerning particular voices, they are expected to have a certain degree of speaker specificity. In the current work, jitter and shimmer are successfully used in a speaker verification experiment. Moreover, both measures are combined with spectral and prosodic features using several types of normalisation and fusion techniques in order to obtain better verification results. The overall speaker verification system is also improved by using histogram equalisation as a normalisation technique previous to fusing the features by SVM.

show abstract

Speaker Verification by Human Listeners: Experiments Comparing Human and Machine Performance Using the NIST 1998 Speaker Evaluation Data

Cited by 51 publications

References 9 publications

ASVspoof: The Automatic Speaker Verification Spoofing and Countermeasures Challenge

ASVspoof: The Automatic Speaker Verification Spoofing and Countermeasures Challenge

CASA-Based Robust Speaker Identification

Using Jitter and Shimmer in speaker verification

Contact Info

Product

Resources

About