Downloads: 113 | Views: 123

Review Papers | Computer Science & Engineering | India | Volume 3 Issue 11, November 2014

Identification of Emotions from Speech using Anchor Model

Surabhi G. Agrawal | Shabda Dongaonkar ^[2]

Abstract: A technique for refining the anchor modelling system introduced enhanced emotion detection system from speech. Anchor representation was then put on the speaker detection issue. Identification mistake transaction productivity uncovered that the anchor displaying system missed the mark supply of a state-of the-craftsmanship GMM-UBM framework. It had been more observed that its computational efficiency was exceptional to that specific of the GMMUBM. Correlation of the anchor product and GMM-UBM programs for speaker indexing uncovered an indistinguishable trade-off between point of interest versus review productivity and computational efficiency. A cascaded speaker indexing system was arranged that uses the anchor item program as the first stage and the GMM-UBM as the second stage. In that configuration, the anchor system diminished the data pressing on the GMM-UBM while to some degree lessening effectiveness in working parts of low review. The impact of the cascaded project was to join the peculiarities of both projects at the inconvenience of some decrease in both computational productivity and accuracy of recognition. For extensive chronicles, the detection effectiveness of the anchor program and the absence of computational productivity of the GMM-UBM project can keep their application to speaker indexing. The cascading system may give a handy treatment to the speaker indexing application.

Keywords: anchor modelling system, cascaded speaker, computational productivity, data pressing

Edition: Volume 3 Issue 11, November 2014,

Pages: 2156 - 2158

Similar Articles with Keyword 'anchor'