Sciweavers

239 search results - page 18 / 48
» Lithuanian Speech Recognition Using the English Recognizer
Sort
View
LREC
2010
236views Education» more  LREC 2010»
14 years 11 months ago
ProPOSEC: A Prosody and PoS Annotated Spoken English Corpus
We have previously reported on ProPOSEL, a purpose-built Prosody and PoS English Lexicon compatible with the Python Natural Language ToolKit. ProPOSEC is a new corpus research res...
Claire Brierley, Eric Atwell
ICASSP
2009
IEEE
15 years 1 months ago
Strategies for modeling reverberant speech in the feature domain
The length of the room impulse response characterizing the acoustic path between speaker and microphone is significantly larger than the length of the analysis window used for fea...
Armin Sehr, Walter Kellermann
106
Voted
IJCNN
2006
IEEE
15 years 3 months ago
Reservoir-based techniques for speech recognition
— A solution for the slow convergence of most learning rules for Recurrent Neural Networks (RNN) has been proposed under the terms Liquid State Machines (LSM) and Echo State Netw...
David Verstraeten, Benjamin Schrauwen, Dirk Stroob...
ICMI
2005
Springer
136views Biometrics» more  ICMI 2005»
15 years 3 months ago
Probabilistic grounding of situated speech using plan recognition and reference resolution
Situated, spontaneous speech may be ambiguous along acoustic, lexical, grammatical and semantic dimensions. To understand such a seemingly difficult signal, we propose to model th...
Peter Gorniak, Deb Roy
ICASSP
2009
IEEE
15 years 4 months ago
The effectiveness of histogram equalization on environmental model adaptation
In this paper, we introduce a new histogram equalizationbased environmental model adaptation method for robust speech recognition in noise environments. The proposed method adapts...
Youngjoo Suh, Hoirin Kim