Sciweavers

302 search results - page 50 / 61
» Reservoir-based techniques for speech recognition
Sort
View
LREC
2008
118views Education» more  LREC 2008»
13 years 9 months ago
Evaluation of several Maximum Likelihood Linear Regression Variants for Language Adaptation
Multilingual Automatic Speech Recognition (ASR) systems are of great interest in multilingual environments. We studied the case of the Comunitat Valenciana where the two official ...
Míriam Luján-Mares, Carlos D. Mart&i...
MLMI
2007
Springer
14 years 1 months ago
Term-Weighting for Summarization of Multi-party Spoken Dialogues
This paper explores the issue of term-weighting in the genre of spontaneous, multi-party spoken dialogues, with the intent of using such term-weights in the creation of extractive ...
Gabriel Murray, Steve Renals
ICASSP
2010
IEEE
13 years 8 months ago
An improved consensus-like method for Minimum Bayes Risk decoding and lattice combination
In this paper we describe a method for Minimum Bayes Risk decoding for speech recognition. This is a technique similar to Consensus a.k.a. Confusion Network Decoding, in which we ...
Haihua Xu, Daniel Povey, Lidia Mangu, Jie Zhu
SIGIR
2009
ACM
14 years 2 months ago
Web derived pronunciations for spoken term detection
Indexing and retrieval of speech content in various forms such as broadcast news, customer care data and on-line media has gained a lot of interest for a wide range of application...
Dogan Can, Erica Cooper, Arnab Ghoshal, Martin Jan...
ICASSP
2008
IEEE
14 years 2 months ago
Discriminative feature selection for hidden Markov models using Segmental Boosting
We address the feature selection problem for hidden Markov models (HMMs) in sequence classification. Temporal correlation in sequences often causes difficulty in applying featur...
Pei Yin, Irfan A. Essa, Thad Starner, James M. Reh...