Profiles
Research Units
Publications
Sign Up
Faculty Login
X
109 Publications
45 Journals
Srinivasan Umesh
Professor
Department of Electrical Engineering
umeshs@iitm.ac.in (Work)
+91-44-2257-4461 (Work)
Follow
Publications - 109
Overview
Publications (109)
Network (11)
Publications (109)
Sort by Year (most recent)
Sort by Year (most recent)
Sort by Year (oldest first)
Sort by Most Cited
Sort by Recently Added
Sort (A-Z)
Sort (Z-A)
Conferences
CCC-WAV2VEC 2.0: Clustering AIDED Cross Contrastive Self-Supervised Learning of Speech Representations
Lodagala V.S.
,
Ghosh S.
and
Srinivasan Umesh
2023 | Institute of Electrical and Electronics Engineers Inc.
Other
Investigation of Methods to Improve the Recognition Performance of Tamil-English Code-Switched Data in Transformer Framework
Srinivasan Umesh
,
Metilda Sagaya Mary N.J.
and
Shetty V.M.
2020 | Institute of Electrical and Electronics Engineers Inc.
Other
Improving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages
Srinivasan Umesh
,
Shetty V.M.
and
Sagaya Mary N J M.
2020 | Institute of Electrical and Electronics Engineers Inc.
Articles
Improving acoustic models in TORGO dysarthric speech database
Srinivasan Umesh
2018 | Institute of Electrical and Electronics Engineers Inc.
Other
Investigating the effect of audio duration on dementia detection using acoustic features
Srinivasan Umesh
,
Weiner J.
,
...
,
Schultz T.
(4 authors)
2018 | ISCA
Articles
FMLLR Speaker Normalization with i-Vector: In Pseudo-FMLLR and Distillation Framework
Srinivasan Umesh
2018 | Institute of Electrical and Electronics Engineers Inc.
Other
Correlation networks for speaker normalization in automatic speech recognition
Srinivasan Umesh
,
Rini Sharon A.
and
Reddy Kothinti S.
2018 | International Speech Communication Association
Other
Message from general Department and co-chairs
Srinivasan Umesh
,
Yegnanarayana B.
,
Chandra Sekhar C
,
Atul Narayan S P
and
Prasanna S.R.M.
2018 | International Speech Communication Association
Other
Articulatory and stacked bottleneck features for low resource speech recognition
Srinivasan Umesh
,
Shetty V.M.
,
...
,
Arul Prakash Karaiyan
and
B Ravindran
(7 authors)
2018 | International Speech Communication Association
Conferences
Open Access
Generalized distillation framework for speaker normalization
Srinivasan Umesh
2017 | International Speech Communication Association
Download
PDF
Publisher Copy
Conferences
DNN acoustic models for dysarthric speech
Srinivasan Umesh
2017 | Institute of Electrical and Electronics Engineers Inc.
Articles
An automated technique to generate phone-to-articulatory label mapping
Srinivasan Umesh
2017 | Elsevier B.V.
Articles
DNNs for unsupervised extraction of pseudo speaker-normalized features without explicit adaptation data
Srinivasan Umesh
2017 | Elsevier B.V.
Conferences
Addressing data sparsity in DNN acoustic modeling
Srinivasan Umesh
2017 | Institute of Electrical and Electronics Engineers Inc.
Conferences
Open Access
Joint estimation of articulatory features and acoustic models for low-resource languages
Srinivasan Umesh
2017 | International Speech Communication Association
Download
PDF
Publisher Copy
Conferences
On improving acoustic models for TORGO dysarthric speech database
Srinivasan Umesh
2017 | International Speech Communication Association
Conferences
Open Access
Transfer learning and distillation techniques to improve the acoustic modeling of low resource languages
Srinivasan Umesh
2017 | International Speech Communication Association
Download
PDF
Publisher Copy
Conferences
Open Access
Overcoming data sparsity in acoustic modeling of low-resource language by borrowing data and model parameters from high-resource languages
Srinivasan Umesh
2016 | International Speech and Communication Association
Download
PDF
Publisher Copy
Conferences
Open Access
DNNs for unsupervised extraction of pseudo FMLLR features without explicit adaptation data
Srinivasan Umesh
2016 | International Speech and Communication Association
Download
PDF
Publisher Copy
Conferences
Open Access
Articulatory feature extraction using CTC to build articulatory classifiers without forced frame alignments for speech recognition
Srinivasan Umesh
2016 | International Speech and Communication Association
Download
PDF
Publisher Copy
Showing 1-20 of 109 results
prev
1
2
3
4
5
6
next
Get all the updates from Srinivasan Umesh
Follow