Srinivasan Umesh
Orcid: 0000-0002-5957-1444
According to our database1,
Srinivasan Umesh
authored at least 109 papers
between 1992 and 2024.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
Online presence:
-
on orcid.org
On csauthors.net:
Bibliography
2024
2023
FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning.
CoRR, 2023
Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition.
CoRR, 2023
SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis.
CoRR, 2023
The Tag-Team Approach: Leveraging CLS and Language Tagging for Enhancing Multilingual ASR.
CoRR, 2023
Channel-Aware Pretraining Of Joint Encoder-Decoder Self-Supervised Model For Telephonic-Speech ASR.
Proceedings of the IEEE International Conference on Acoustics, 2023
SLICER: Learning Universal Audio Representations Using Low-Resource Self-Supervised Pre-Training.
Proceedings of the IEEE International Conference on Acoustics, 2023
Proceedings of the IEEE International Conference on Acoustics, 2023
Data2vec-Aqc: Search for the Right Teaching Assistant in the Teacher-Student Training Setup.
Proceedings of the IEEE International Conference on Acoustics, 2023
Proceedings of the IEEE International Conference on Acoustics, 2023
Towards Developing State-of-The-Art TTS Synthesisers for 13 Indian Languages with Signal Processing Aided Alignments.
Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023
2022
S-Vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder.
IEEE ACM Trans. Audio Speech Lang. Process., 2022
IEEE J. Sel. Top. Signal Process., 2022
Channel-Aware Pretraining of Joint Encoder-Decoder Self-Supervised Model for Telephonic-Speech ASR.
CoRR, 2022
Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages.
CoRR, 2022
Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition.
CoRR, 2022
CoRR, 2022
A Discourse Aware Sequence Learning Approach for Emotion Recognition in Conversations.
CoRR, 2022
CoRR, 2022
CoRR, 2022
Domain Adaptation of Low-Resource Target-Domain Models Using Well-Trained ASR Conformer Models.
Proceedings of the IEEE Spoken Language Technology Workshop, 2022
Proceedings of the IEEE Spoken Language Technology Workshop, 2022
CCC-WAV2VEC 2.0: Clustering AIDED Cross Contrastive Self-Supervised Learning of Speech Representations.
Proceedings of the IEEE Spoken Language Technology Workshop, 2022
DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances.
Proceedings of the Interspeech 2022, 2022
Span Classification with Structured Information for Disfluency Detection in Spoken Utterances.
Proceedings of the Interspeech 2022, 2022
Gram Vaani ASR Challenge on spontaneous telephone speech recordings in regional variations of Hindi.
Proceedings of the Interspeech 2022, 2022
Proceedings of the Interspeech 2022, 2022
Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition.
Proceedings of the Interspeech 2022, 2022
Investigation of Robustness of Hubert Features from Different Layers to Domain, Accent and Language Variations.
Proceedings of the IEEE International Conference on Acoustics, 2022
2021
Exploring the use of Common Label Set to Improve Speech Recognition of Low Resource Indian Languages.
Proceedings of the IEEE International Conference on Acoustics, 2021
2020
S-vectors: Speaker Embeddings based on Transformer's Encoder for Text-Independent Speaker Verification.
CoRR, 2020
Improving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020
Investigation of Methods to Improve the Recognition Performance of Tamil-English Code-Switched Data in Transformer Framework.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020
2018
FMLLR Speaker Normalization With i-Vector: In Pseudo-FMLLR and Distillation Framework.
IEEE ACM Trans. Audio Speech Lang. Process., 2018
Investigating the Effect of Audio Duration on Dementia Detection Using Acoustic Features.
Proceedings of the Interspeech 2018, 2018
Proceedings of the Interspeech 2018, 2018
Proceedings of the Interspeech 2018, 2018
2017
DNNs for unsupervised extraction of pseudo speaker-normalized features without explicit adaptation data.
Speech Commun., 2017
Speech Commun., 2017
Proceedings of the Twenty-third National Conference on Communications, 2017
Proceedings of the Twenty-third National Conference on Communications, 2017
Proceedings of the Interspeech 2017, 2017
Proceedings of the Interspeech 2017, 2017
Joint Estimation of Articulatory Features and Acoustic Models for Low-Resource Languages.
Proceedings of the Interspeech 2017, 2017
Transfer Learning and Distillation Techniques to Improve the Acoustic Modeling of Low Resource Languages.
Proceedings of the Interspeech 2017, 2017
2016
Modified Mean and Variance Normalization: Transforming to Utterance-Specific Estimates.
Circuits Syst. Signal Process., 2016
DNNs for Unsupervised Extraction of Pseudo FMLLR Features Without Explicit Adaptation Data.
Proceedings of the Interspeech 2016, 2016
Overcoming Data Sparsity in Acoustic Modeling of Low-Resource Language by Borrowing Data and Model Parameters from High-Resource Languages.
Proceedings of the Interspeech 2016, 2016
Articulatory Feature Extraction Using CTC to Build Articulatory Classifiers Without Forced Frame Alignments for Speech Recognition.
Proceedings of the Interspeech 2016, 2016
2015
Speech Commun., 2015
Pronunciation Adaptation For Disordered Speech Recognition Using State-Specific Vectors of Phone-Cluster Adaptive Training.
Proceedings of the 6th Workshop on Speech and Language Processing for Assistive Technologies, 2015
Proceedings of the Twenty First National Conference on Communications, 2015
Investigation of different acoustic modeling techniques for low resource Indian language data.
Proceedings of the Twenty First National Conference on Communications, 2015
Speaker adaptation of convolutional neural network using speaker specific subspace vectors of SGMM.
Proceedings of the INTERSPEECH 2015, 2015
2014
Acoustic modelling for speech recognition in Indian languages in an agricultural commodities task domain.
Speech Commun., 2014
Improving deep neural networks using state projection vectors of subspace Gaussian mixture model as features.
Proceedings of the 2014 IEEE Spoken Language Technology Workshop, 2014
Experiments on front-end techniques and segmentation model for robust Indian Language speech recognizer.
Proceedings of the Twentieth National Conference on Communications, 2014
Cross-lingual acoustic modeling for Indian languages based on Subspace Gaussian Mixture Models.
Proceedings of the Twentieth National Conference on Communications, 2014
2013
Modified cepstral mean normalization - transforming to utterance specific non-zero mean.
Proceedings of the INTERSPEECH 2013, 2013
Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013
Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013
Modified splice and its extension to non-stereo data for noise robust speech recognition.
Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013
2012
IEEE Trans. Speech Audio Process., 2012
Multiple background models for speaker verification using the concept of vocal tract length and MLLR super-vector.
Int. J. Speech Technol., 2012
Proceedings of the 11th International Conference on Information Science, 2012
Computationally efficient speaker identification using fast-MLLR based anchor modeling.
Proceedings of the 2012 IEEE International Conference on Acoustics, 2012
Proceedings of the 2012 IEEE International Conference on Acoustics, 2012
Proceedings of the 2012 IEEE International Conference on Acoustics, 2012
2011
Eigen-Voice Based Anchor Modeling System for Speaker Identification Using MLLR Super-Vector.
Proceedings of the INTERSPEECH 2011, 2011
Proceedings of the INTERSPEECH 2011, 2011
Proceedings of the INTERSPEECH 2011, 2011
Use of VTL-wise models in feature-mapping framework to achieve performance of multiple-background models in speaker verification.
Proceedings of the IEEE International Conference on Acoustics, 2011
2010
Computationally Efficient Speaker Identification for Large Population Tasks using MLLR and Sufficient Statistics.
Proceedings of the Odyssey 2010: The Speaker and Language Recognition Workshop, Brno, Czech Republic, June 28, 2010
Investigation of Speaker-Clustered UBMs based on Vocal Tract Lengths and MLLR matrices for Speaker Verification.
Proceedings of the Odyssey 2010: The Speaker and Language Recognition Workshop, Brno, Czech Republic, June 28, 2010
Fast computation of speaker characterization vector using MLLR and sufficient statistics in anchor model framework.
Proceedings of the INTERSPEECH 2010, 2010
2009
Text-independent speaker identification using vocal tract length normalization for building universal background model.
Proceedings of the INTERSPEECH 2009, 2009
A study on the influence of covariance adaptation on jacobian compensation in vocal tract length normalization.
Proceedings of the INTERSPEECH 2009, 2009
Using VTLN matrices for rapid and computationally-efficient speaker adaptation with robustness to first-pass transcription errors.
Proceedings of the INTERSPEECH 2009, 2009
Proceedings of the INTERSPEECH 2009, 2009
Proceedings of the INTERSPEECH 2009, 2009
Improving the performance of VTLN under mismatched speaker conditions and making it approach that of matched speaker conditions.
Proceedings of the IEEE International Conference on Acoustics, 2009
2008
A shift-based approach to speaker normalization using non-linear frequency-scaling model.
Speech Commun., 2008
Study of jacobian compensation using linear transformation of conventional MFCC for VTLN.
Proceedings of the INTERSPEECH 2008, 2008
Use of spectral centre of gravity for generating speaker invariant features for automatic speech recognition.
Proceedings of the INTERSPEECH 2008, 2008
A computationally efficient approach to warp factor estimation in VTLN using EM algorithm and sufficient statistics.
Proceedings of the INTERSPEECH 2008, 2008
2007
A Study of Filter Bank Smoothing in MFCC Features for Recognition of Children's Speech.
IEEE Trans. Speech Audio Process., 2007
Proceedings of the INTERSPEECH 2007, 2007
Proceedings of the IJCAI 2007, 2007
2006
Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006
Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006
2005
Implementing frequency-warping and VTLN through linear transformation of conventional MFCC.
Proceedings of the INTERSPEECH 2005, 2005
2004
Proceedings of the INTERSPEECH 2004, 2004
Proceedings of the 2004 IEEE International Conference on Acoustics, 2004
Proceedings of the 2004 IEEE International Conference on Acoustics, 2004
2003
Proceedings of the 2003 IEEE International Conference on Acoustics, 2003
2002
Proceedings of the IEEE International Conference on Acoustics, 2002
Proceedings of the IEEE International Conference on Acoustics, 2002
2000
Exploiting frequency-scaling invariance properties of the scale transform for automatic speech recognition.
Proceedings of the Sixth International Conference on Spoken Language Processing, 2000
1999
Proceedings of the 1999 IEEE International Conference on Acoustics, 1999
1998
Proceedings of the 1998 IEEE International Conference on Acoustics, 1998
1997
Proceedings of the 1997 IEEE International Conference on Acoustics, 1997
1996
Estimation of parameters of exponentially damped sinusoids using fast maximum likelihood estimation with application to NMR spectroscopy data.
IEEE Trans. Signal Process., 1996
Proceedings of the 4th International Conference on Spoken Language Processing, 1996
Proceedings of the 1996 IEEE International Conference on Acoustics, 1996
1992
Proceedings of the 1992 IEEE International Conference on Acoustics, 1992