Inter and Intra-speaker Variability in French: An Analysis of Oral Vowels and Its Implication for Automatic Speaker Verification
نویسندگان
چکیده
Intra and inter-speaker variability is studied as a way to better understand how voice can be used as biometric data. Formant values from 328,016 exemplars of the 10 French oral vowels uttered by 111 speakers were compared to estimate their speaker discrimination power. The vowels /œ/, /ɛ/ and /a/ appear to convey more idiosyncratic information than other oral vowels. A more comprehensive phonetic analysis is carried out for each speaker on 2 samples leading to either high or low discrimination performance when used in the Alize/spkDet SVS. However, no direct explanation can be drawn from phonetic measures to predict
منابع مشابه
Clustering Algorithm in Automatic Speaker Verification
We propose a new modeling approach in Automatic Speaker Verification A.S.V based on Gaussians Mixtures Models and Maximum a posteriori adaptation MAP. We propose clustering algorithm for intra and inter speaker’s variability in voice module and contribute for Universal Speaker Model design. We compare the traditional approach which uses one specific customer model with the second called Univers...
متن کاملVariability compensated support vector machines applied to speaker verification
Speaker verification using SVMs has proven successful, specifically using the GSV Kernel [1] with nuisance attribute projection (NAP) [2]. Also, the recent popularity and success of joint factor analysis [3] has led to promising attempts to use speaker factors directly as SVM features [4]. NAP projection and the use of speaker factors with SVMs are methods of handling variability in SVM speaker...
متن کاملUsing Exciting and Spectral Envelope Information and Matrix Quantization for Improvement of the Speaker Verification Systems
Speaker verification from talking a few words of sentences has many applications. Many methods as DTW, HMM, VQ and MQ can be used for speaker verification. We applied MQ for its precise, reliable and robust performance with computational simplicity. We also used pitch frequency and log gain contour for further improvement of the system performance.
متن کاملClose Speakers Model and Comparative Study in Automatic Speaker Verification
The performance of speaker verification system degrades when the test segments are utterances of short duration, therefore, we investigate the use of model representing our target speaker with his close speaker and his own speech data. We propose to create a new Speaker Model who groups close speakers (CS) achieved with two clustering algorithms in Automatic Speaker Verification A.S.V. Intra an...
متن کاملUsing Exciting and Spectral Envelope Information and Matrix Quantization for Improvement of the Speaker Verification Systems
Speaker verification from talking a few words of sentences has many applications. Many methods as DTW, HMM, VQ and MQ can be used for speaker verification. We applied MQ for its precise, reliable and robust performance with computational simplicity. We also used pitch frequency and log gain contour for further improvement of the system performance.
متن کامل