Identifying speaker-dependent acoustic parameters in Spanish vowels

Marrero, Victoria; Battaner, Elena; Gil, Juana María Sancho; Llisterri, Joaquim; Machuca, María Jesús; Marquina, Montserrat; Mota, Carme de la; Rı́os, Antonio

doi:10.1121/1.2935781

Cited by 7 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies have shown that both F3 and F4 are important to speaker recognition [4] and that strengthening the presence of higher formants can improve the robustness of cross-session speaker recognition [4].…”

Section: Chart 1: Impact Of Vtl and Pitch Rescaling On Speaker Recognmentioning

confidence: 99%

Perturbation and pitch normalization as enhancements to speaker recognition

Lawson¹,

Linderman

Leonard³

et al. 2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

This study proposes an approach to improving speaker recognition through the process of minute vocal tract length perturbation of training files, coupled with pitch normalization for both train and test data. The notion of perturbation as a method for improving the robustness of training data for supervised classification is taken from the field of optical character recognition, where distorting characters within a certain range has shown strong improvements across disparate conditions. This paper demonstrates that acoustic perturbation, in this case analysis, distortion, and resynthesis of vocal tract length for a given speaker, significantly improves speaker recognition when the resulting files are used to augment or replace the training data. A pitch length normalization technique is also discussed, which is combined with perturbation to improve open-set speaker recognition from an EER of 20% to 6.7%.

show abstract

Section: Chart 1: Impact Of Vtl and Pitch Rescaling On Speaker Recognmentioning

confidence: 99%

Perturbation and pitch normalization as enhancements to speaker recognition

Lawson¹,

Linderman

Leonard³

et al. 2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

show abstract

“…A preliminary result, using the vowels in each recording, is obtained, and due to the great amount working, 17 speaker is using to evaluate the vowels, the vowel /a/, present the best performance, the vowels /u/ has been exclude because of its low frequency of occurrence in Spanish [14], [15], and the vowels /i/, is exclude, because has less in comparison with the others vowels, but in a future work will be used.…”

Section: Discussionmentioning

confidence: 99%

Feature Extraction Using LPC-Residual and MelFrequency Cepstral Coefficients in Forensic Speaker Recognition

Curipe¹,

Camacho²

2013

IJCEE

View full text Add to dashboard Cite

Abstract-In this paper, we investigated the form to improve the performance in the recognition, involved at the forensic area. To improve, we use Linear Predictive Coding (LPC) and it residual; it was compared with Mel Frequency Cepstral Coefficients (MFCC). The classification technique was Gaussian Mixture Model (GMM). The collection data is in Spanish language, using spontaneous speech from 37 male speaker of Mexican Spanish, we have three recordings, between each recording exist 3 week and one month of separation respectively, this allows us in real condition work, we use non contemporaneous recording and scarcity of data to training and testing the performance of the forensic recognition task. Two conclusions can be drawn from the results, the first, MFCC has better performance with long recording, LPC-residual has better performance with short recording. Index Terms-Forensic speaker recognition (FSR), gaussian mixture model (GMM), linear predictive coding-residual (LPC-residual), mel frequency cepstral coefficients (MFCC).

show abstract

Recurrent neural network based approach to recognize assamese fricatives using experimentally derived acoustic-phonetic features

Patgiri

Sarma

2013

2013 1st International Conference on Emerging Trends and Applications in Computer Science

View full text Add to dashboard Cite

Identifying speaker-dependent acoustic parameters in Spanish vowels

Cited by 7 publications

References 15 publications

Perturbation and pitch normalization as enhancements to speaker recognition

Perturbation and pitch normalization as enhancements to speaker recognition

Feature Extraction Using LPC-Residual and MelFrequency Cepstral Coefficients in Forensic Speaker Recognition

Recurrent neural network based approach to recognize assamese fricatives using experimentally derived acoustic-phonetic features

Contact Info

Product

Resources

About