Sciweavers

249 search results - page 25 / 50
» Continuous speech recognition with a TF-IDF acoustic model
Sort
View
ICASSP
2009
IEEE
14 years 2 months ago
Generalized Baum-Welch algorithm for discriminative training on large vocabulary continuous speech recognition system
We propose a new optimization algorithm called Generalized Baum Welch (GBW) algorithm for discriminative training on hidden Markov model (HMM). GBW is based on Lagrange relaxation...
Roger Hsiao, Yik-Cheung Tam, Tanja Schultz
ACL
2008
13 years 8 months ago
Unsupervised Learning of Acoustic Sub-word Units
Accurate unsupervised learning of phonemes of a language directly from speech is demonstrated via an algorithm for joint unsupervised learning of the topology and parameters of a ...
Balakrishnan Varadarajan, Sanjeev Khudanpur, Emman...
SPEECH
2011
13 years 2 months ago
Intelligibility predictors and neural representation of speech
Intelligibility predictors tell us a great deal about human speech perception, in particular which acoustic factors strongly effect human behavior, and which do not. A particular...
Bryce E. Lobdell, Jont B. Allen, Mark Hasegawa-Joh...
ICASSP
2011
IEEE
12 years 11 months ago
Speech processing with a cortical representation of audio
Neurophysiological studies in the primary auditory cortex have recently demonstrated a rich diversity of responses that provide an explicit multidimensional representation of phon...
Nima Mesgarani, Shihab A. Shamma
LRE
2010
136views more  LRE 2010»
13 years 5 months ago
The Corpus DIMEx100: transcription and evaluation
In this paper the transcription and evaluation of the corpus DIMEx100 for Mexican Spanish is presented. First we describe the corpus and explain the linguistic and computational mo...
Luis Alberto Pineda, Hayde Castellanos, Javier Cu&...