Improving acoustic models in TORGO dysarthric speech database NM Joy, S Umesh IEEE Transactions on Neural Systems and Rehabilitation Engineering 26 (3 …, 2018 | 78 | 2018 |
Generalized Distillation Framework for Speaker Normalization. NM Joy, SR Kothinti, S Umesh, B Abraham Interspeech, 739-743, 2017 | 13 | 2017 |
Joint Estimation of Articulatory Features and Acoustic Models for Low-Resource Languages. B Abraham, S Umesh, NM Joy Interspeech, 2153-2157, 2017 | 10 | 2017 |
Articulatory Feature Extraction Using CTC to Build Articulatory Classifiers Without Forced Frame Alignments for Speech Recognition. B Abraham, S Umesh, NM Joy Interspeech, 798-802, 2016 | 10 | 2016 |
FMLLR speaker normalization with i-vector: In pseudo-FMLLR and distillation framework NM Joy, SR Kothinti, S Umesh IEEE/ACM Transactions on Audio, Speech, and Language Processing 26 (4), 797-805, 2018 | 8 | 2018 |
DNNs for unsupervised extraction of pseudo speaker-normalized features without explicit adaptation data NM Joy, MK Baskar, S Umesh Speech Communication 92, 64-76, 2017 | 8 | 2017 |
Deep scattering power spectrum features for robust speech recognition NM Joy, D Oglic, Z Cvetkovic, P Bell, S Renals Interspeech 2020, 1673-1677, 2020 | 7 | 2020 |
Overcoming Data Sparsity in Acoustic Modeling of Low-Resource Language by Borrowing Data and Model Parameters from High-Resource Languages. B Abraham, S Umesh, NM Joy INTERSPEECH, 3037-3041, 2016 | 7 | 2016 |
A data-driven phoneme mapping technique using interpolation vectors of phone-cluster adaptive training B Abraham, NM Joy, NKS Umesh 2014 IEEE Spoken Language Technology Workshop (SLT), 36-41, 2014 | 7 | 2014 |
Cross-lingual acoustic modeling for Indian languages based on Subspace Gaussian Mixture Models NM Joy, B Abraham, K Navneeth, S Umesh 2014 Twentieth National Conference on Communications (NCC), 1-5, 2014 | 5 | 2014 |
DNNs for Unsupervised Extraction of Pseudo FMLLR Features Without Explicit Adaptation Data. NM Joy, MK Baskar, S Umesh, B Abraham INTERSPEECH, 3479-3483, 2016 | 4 | 2016 |
Improved acoustic modeling of low-resource languages using shared SGMM parameters of high-resource languages NM Joy, B Abraham, K Navneeth, S Umesh 2016 Twenty Second National Conference on Communication (NCC), 1-6, 2016 | 1 | 2016 |
Improved phone-cluster adaptive training acoustic model NM Joy, S Umesh, B Abraham, K Navneeth 2016 International Conference on Signal Processing and Communications (SPCOM …, 2016 | | 2016 |
Subspace modeling technique using monophones for speech recognition BS Ch, NM Joy, RR Bilgi, S Umesh 2013 National Conference on Communications (NCC), 1-5, 2013 | | 2013 |