S. Umesh
Professor
+91-44 2257 4461 (Work)
Publications - 108Publications - 108
Publications - 108Publications (108)
Sort by Year (most recent)
Sort by Year (oldest first)
Sort by Most Cited
Sort by Recently Added
Sort (A-Z)
Sort (Z-A)
OtherInvestigation of Methods to Improve the Recognition Performance of Tamil-English Code-Switched Data in Transformer Framework2020 | Institute of Electrical and Electronics Engineers Inc.- OtherImproving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages2020 | Institute of Electrical and Electronics Engineers Inc.
- ArticlesImproving acoustic models in TORGO dysarthric speech database2018 | Institute of Electrical and Electronics Engineers Inc.
- ArticlesFMLLR Speaker Normalization with i-Vector: In Pseudo-FMLLR and Distillation Framework2018 | Institute of Electrical and Electronics Engineers Inc.
OtherCorrelation networks for speaker normalization in automatic speech recognition2018 | International Speech Communication Association- OtherMessage from general Department and co-chairs2018 | International Speech Communication Association
- OtherArticulatory and stacked bottleneck features for low resource speech recognition2018 | International Speech Communication Association
- ConferencesGeneralized distillation framework for speaker normalization2017 | International Speech Communication Association
Open Access - ConferencesDNN acoustic models for dysarthric speech2017 | Institute of Electrical and Electronics Engineers Inc.
- ArticlesDNNs for unsupervised extraction of pseudo speaker-normalized features without explicit adaptation data2017 | Elsevier B.V.
- ConferencesAddressing data sparsity in DNN acoustic modeling2017 | Institute of Electrical and Electronics Engineers Inc.
- ConferencesJoint estimation of articulatory features and acoustic models for low-resource languages2017 | International Speech Communication AssociationOpen Access
- ConferencesTransfer learning and distillation techniques to improve the acoustic modeling of low resource languages2017 | International Speech Communication AssociationOpen Access
- ConferencesOn improving acoustic models for TORGO dysarthric speech database2017 | International Speech Communication Association
- ConferencesOvercoming data sparsity in acoustic modeling of low-resource language by borrowing data and model parameters from high-resource languages2016 | International Speech and Communication AssociationOpen Access
- ArticlesModified Mean and Variance Normalization: Transforming to Utterance-Specific Estimates2016 | Birkhauser Boston
- ConferencesDNNs for unsupervised extraction of pseudo FMLLR features without explicit adaptation data2016 | International Speech and Communication AssociationOpen Access
- ConferencesArticulatory feature extraction using CTC to build articulatory classifiers without forced frame alignments for speech recognition2016 | International Speech and Communication AssociationOpen Access
