Sciweavers

367 search results - page 49 / 74
» Large-Vocabulary Speech Recognition Algorithms
Sort
View
MLMI
2007
Springer
15 years 5 months ago
Using Prosodic Features in Language Models for Meetings
Abstract. Prosody has been actively studied as an important knowledge source for speech recognition and understanding. In this paper, we are concerned with the question of exploiti...
Songfang Huang, Steve Renals
103
Voted
ICASSP
2011
IEEE
14 years 2 months ago
Source-normalised-and-weighted LDA for robust speaker recognition using i-vectors
The recently developed i-vector framework for speaker recognition has set a new performance standard in the research field. An i-vector is a compact representation of a speaker u...
Mitchell McLaren, David A. van Leeuwen
EUSAI
2003
Springer
15 years 4 months ago
Experimental Evaluation of Variations in Primary Features Used for Accelerometric Context Recognition
The paper describes initial results in an ongoing project aimed at providing and analyzing standardized, representative data sets for typical context recognition tasks. Such data ...
Ernst A. Heinz, Kai S. Kunze, Stefan Sulistyo, Hol...
ICML
2009
IEEE
15 years 12 months ago
Large margin training for hidden Markov models with partially observed states
Large margin learning of Continuous Density HMMs with a partially labeled dataset has been extensively studied in the speech and handwriting recognition fields. Yet due to the non...
Thierry Artières, Trinh Minh Tri Do
SIGIR
2005
ACM
15 years 4 months ago
On the collective classification of email "speech acts"
We consider classification of email messages as to whether or not they contain certain “email acts”, such as a request or a commitment. We show that exploiting the sequential ...
Vitor Rocha de Carvalho, William W. Cohen