Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Rajesh Janakiraman"'
Publikováno v:
2010 National Conference On Communications (NCC).
In this paper, we propose a novel idea for using two different feature streams in a continuous speech recognition system. Conventionally multiple feature streams are concatenated and HMMs trained to build triphone/syllable models. In this paper, inst
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::34300bb92cd746cf8f73a21ae52146fc
https://doi.org/10.1109/ncc.2010.5430186
https://doi.org/10.1109/ncc.2010.5430186
Publikováno v:
2010 National Conference On Communications (NCC).
The focus of this paper is two-fold: (a) to develop a knowledge-based robust syllable segmentation algorithm and (b) to establish the importance of accurate segmentation in both the training and testing phases of a speech recognition system. A robust
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1b9f970ec43be19a9d0524b1adc9e4d2
https://doi.org/10.1109/ncc.2010.5430189
https://doi.org/10.1109/ncc.2010.5430189