Result 1 to 20 of 53 total
Lexical access experiments with context-dependent articulatory feature-based models (English)
ICASSP, 4900-4903 (2011).
1
Robust speech recognition using multiple prior models for speech reconstruction (English)
ICASSP, 4800-4803 (2011).
2
Investigations into the incorporation of the ideal binary mask in ASR (English)
ICASSP, 4804-4807 (2011).
3
Backpropagation training for multilayer conditional random field based phone recognition (English)
ICASSP, 5534-5537 (2010).
4
Investigations into the crandem approach to word recognition (English)
HLT-NAACL, 725-728 (2010).
5
Machine learning for text selection with expressive unit-selection voices (English)
INTERSPEECH, 1125-1128 (2010).
6
Learning speaker normalization using semisupervised manifold alignment (English)
INTERSPEECH, 2918-2921 (2010).
7
Discriminative language modeling using simulated ASR errors (English)
INTERSPEECH, 1049-1052 (2010).
8
Combining monaural and binaural evidence for reverberant speech segregation (English)
INTERSPEECH, 406-409 (2010).
9
Discriminative input stream combination for conditional random field phone recognition (English)
IEEE Transactions on Audio, Speech & Language Processing 17, No. 8, 1533-1546 (2009).
10
Multiple time resolution analysis of speech signal using MCE training with application to speech recognition (English)
ICASSP, 3801-3804 (2009).
11
Investigating phonetic information reduction and lexical confusability (English)
INTERSPEECH, 1659-1662 (2009).
12
CRANDEM: conditional random fields for word recognition (English)
INTERSPEECH, 3063-3066 (2009).
13
Evaluating parameters for mapping adult vowels to imitative babbling (English)
INTERSPEECH, 688-691 (2009).
14
A comparison of audio-free speech recognition error prediction methods (English)
INTERSPEECH, 1211-1214 (2009).
15
Monaural segregation of voiced speech using discriminative random fields (English)
INTERSPEECH, 856-859 (2009).
16
Conditional random fields for integrating local discriminative classifiers (English)
IEEE Transactions on Audio, Speech & Language Processing 16, No. 3, 617-628 (2008).
17
Latent phonetic analysis: use of singular value decomposition to determine features for CRF phone recognition (English)
ICASSP, 4541-4544 (2008).
18
Crandem systems: conditional random field acoustic models for hidden Markov models (English)
ICASSP, 4049-4052 (2008).
19
SCARE: a situated corpus with annotated referring expressions (English)
LREC (2008).
20
Result 1 to 20 of 53 total
Start
Contact
Print
General Help
