Sciweavers

28 search results - page 1 / 6
» Noise robust exemplar-based connected digit recognition
Sort
View
ICASSP
2010
IEEE
13 years 5 months ago
Noise robust exemplar-based connected digit recognition
This paper proposes a noise robust exemplar-based speech recognition system where noisy speech is modeled as a linear combination of a set of speech and noise exemplars. The metho...
Jort F. Gemmeke, Tuomas Virtanen
INTERSPEECH
2010
12 years 11 months ago
Using a DBN to integrate sparse classification and GMM-based ASR
The performance of an HMM-based speech recognizer using MFCCs as input is known to degrade dramatically in noisy conditions. Recently, an exemplar-based noise robust ASR approach,...
Yang Sun, Jort F. Gemmeke, Bert Cranen, Louis ten ...
ICPR
2002
IEEE
14 years 5 months ago
Robust Appearance-Based Object Recognition Using a Fully Connected Markov Random Field
This paper presents a new kernel method for appearance-based object recognition, highly robust to noise and occlusion. It consists of a fully connected Markov Random Field that in...
Barbara Caputo, Sahla Bouattour, Heinrich Niemann
ICASSP
2011
IEEE
12 years 8 months ago
Structured discriminative models for noise robust continuous speech recognition
Recently there has been interest in structured discriminative models for speech recognition. In these models sentence posteriors are directly modelled, given a set of features ext...
Anton Ragni, Mark John Francis Gales
ICASSP
2011
IEEE
12 years 8 months ago
Non-negative matrix deconvolution in noise robust speech recognition
High noise robustness has been achieved in speech recognition by using sparse exemplar-based methods with spectrogram windows spanning up to 300 ms. A downside is that a large exe...
Antti Hurmalainen, Jort F. Gemmeke, Tuomas Virtane...