A study on the roles of total variability space and session variability modeling in speaker recognition

Autor: Jean-François Bonastre, Achintya Kumar Sarkar, Driss Matrouf

Publikováno v: International Journal of Speech Technology. 19:111-120

Speaker verification (SV) using i-vector concept becomes state-of-the-art. In this technique, speakers are projected onto the total variability space and represented by vectors called i-vectors. During testing, the i-vectors of the test speech segmen

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9f26a670a2269baab5b12b843278edc4
https://doi.org/10.1007/s10772-015-9324-2

Speaker recognition using discriminative learning of Large Margin GMM

Autor: Jourani, Reda

Publikováno v: Traitement du signal et de l'image [eess.SP]. Université Paul Sabatier-Toulouse III, 2012. Français

Most of state-of-the-art speaker recognition systems are based on Gaussian Mixture Models (GMM), trained using maximum likelihood estimation and maximum a posteriori (MAP) estimation. The generative training of the GMM does not however directly optim

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::11728c0fcdcd7e3fc1f19310f61c362c
https://tel.archives-ouvertes.fr/tel-00807563/file/manuscrit-UPS.pdf

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Deep Boltzmann Machines for i-Vector Based Audio-Visual Person Identification.

Autor: Alam, Mohammad Rafiqul, Bennamoun, Mohammed, Togneri, Roberto, Sohel, Ferdous

Publikováno v: Image & Video Technology: 7th Pacific-Rim Symposium, PSIVT 2015, Auckland, New Zealand, November 25-27, 2015, Revised Selected Papers; 2016, p631-641, 11p