S. Umesh
8 papers · 2016–2018 · 1 venue · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (17) π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird π Keyword Champion (2) π§ Keyword Pioneer
π
Conference Pioneer
π
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(7)
Speech & Audio
(6)
Recognition
(6)
Deep Learning
(5)
Application Areas
(4)
Architectures
(3)
Learning Types Β· Deep Learning
(3)
Learning Types Β· Machine Learning
(3)
Artificial Intelligence
(2)
Core Methods
(2)
Learning Paradigms
(2)
Mathematics & Optimization
(1)
Optimization
(1)
Optimization & Theory Β· Machine Learning
(1)
Optimization & Theory Β· Deep Learning
(1)
Keywords
articulatory feature
(3)
low-resource language
(3)
automatic speech recognition
(3)
acoustic modeling
(3)
transfer learning
(2)
deep neural network
(2)
feature extraction
(2)
feature normalization
(2)
knowledge distillation
(2)
multilingual training
(2)
speaker adaptation
(1)
bidirectional long short-term memory
(1)
bottleneck feature
(1)
data pooling
(1)
parameter borrowing
(1)
speaker normalization
(1)
multilingual speech recognition
(1)
frame alignment
(1)
articulatory classifier
(1)
adaptation data
(1)
Papers
Articulatory and Stacked Bottleneck Features for Low Resource Speech Recognition
Interspeech 2018
Generalized Distillation Framework for Speaker Normalization
Interspeech 2017
Joint Estimation of Articulatory Features and Acoustic Models for Low-Resource Languages
Interspeech 2017
On Improving Acoustic Models for TORGO Dysarthric Speech Database
Interspeech 2017
Transfer Learning and Distillation Techniques to Improve the Acoustic Modeling of Low Resource Languages
Interspeech 2017
Articulatory Feature Extraction Using CTC to Build Articulatory Classifiers Without Forced Frame Alignments for Speech Recognition
Interspeech 2016
DNNs for Unsupervised Extraction of Pseudo FMLLR Features Without Explicit Adaptation Data
Interspeech 2016
Overcoming Data Sparsity in Acoustic Modeling of Low-Resource Language by Borrowing Data and Model Parameters from High-Resource Languages
Interspeech 2016