Srinivasan Umesh

ORCID

Publication Activity (10 Years)

Years Active: 1992-2024
Publications (10 Years): 60

Top Venues

Publications

Srinivasan Umesh, Leon Cohen, Douglas J. Nelson
On the relationship between speech and hearing. CoRR (2024)
Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
Stable Distillation: Regularizing Continued Pre-Training for Low-Resource Automatic Speech Recognition. ICASSP (2024)
Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
FusDom: Combining in-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning. ICASSP (2024)
Anusha Prakash, Arun Kumar A, Ashish Seth, Bhagyashree Mukherjee, Ishika Gupta, Jom Kuriakose, Jordan Fernandes, K. V. Vikram, Mano Ranjith Kumar M., Metilda Sagaya Mary, Mohammad Wajahat, Mohana N, Mudit Batra, Navina K, Nihal John George, Nithya Ravi, Pruthwik Mishra, Sudhanshu Srivastava, Vasista Sai Lodagala, Vandan Mujadia, Kada Sai Venkata Vineeth, Vrunda N. Sukhadia, Dipti Misra Sharma, Hema A. Murthy, Pushpak Bhattacharyya, Srinivasan Umesh, Rajeev Sangal
Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages. INTERSPEECH (2023)
Vrunda N. Sukhadia, Srinivasan Umesh
Channel-Aware Pretraining Of Joint Encoder-Decoder Self-Supervised Model For Telephonic-Speech ASR. ICASSP Workshops (2023)
Kaousheik Jayakumar, Vrunda N. Sukhadia, A. Arunkumar, Srinivasan Umesh
The Tag-Team Approach: Leveraging CLS and Language Tagging for Enhancing Multilingual ASR. CoRR (2023)
Sreyan Ghosh, Ashish Seth, Srinivasan Umesh, Dinesh Manocha
MAST: Multiscale Audio Spectrogram Transformers. ICASSP (2023)
Anusha Prakash, Srinivasan Umesh, Hema A. Murthy
Towards Developing State-of-The-Art TTS Synthesisers for 13 Indian Languages with Signal Processing Aided Alignments. ASRU (2023)
Kaousheik Jayakumar, Vrunda N. Sukhadia, Arun Kumar A, Srinivasan Umesh
The Tag-Team Approach: Leveraging CLS and Language Tagging for Enhancing Multilingual ASR. INTERSPEECH (2023)
Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
Data2vec-Aqc: Search for the Right Teaching Assistant in the Teacher-Student Training Setup. ICASSP (2023)
Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
SLICER: Learning Universal Audio Representations Using Low-Resource Self-Supervised Pre-Training. ICASSP (2023)
Ramanan Sivaguru, Vasista Sai Lodagala, Srinivasan Umesh
SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis. INTERSPEECH (2023)
Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning. CoRR (2023)
Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
Unfused: Unsupervised Finetuning Using Self Supervised Distillation. ICASSP Workshops (2023)
Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition. CoRR (2023)
Ramanan Sivaguru, Vasista Sai Lodagala, Srinivasan Umesh
SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis. CoRR (2023)
Narla John Metilda Sagaya Mary, Srinivasan Umesh, Sandesh Varadaraju Katta
S-Vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder. IEEE ACM Trans. Audio Speech Lang. Process. 30 (2022)
Lodagala V. S. V. Durga Prasad, Sreyan Ghosh, Srinivasan Umesh
PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations. CoRR (2022)
Pratik Kumar, Vrunda N. Sukhadia, Srinivasan Umesh
Investigation of Robustness of Hubert Features from Different Layers to Domain, Accent and Language Variations. ICASSP (2022)
Lodagala Durga Prasad, Ashish Seth, Sreyan Ghosh, Srinivasan Umesh
Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition. CoRR (2022)
Sreyan Ghosh, Harshvardhan Srivastava, Srinivasan Umesh
A Discourse Aware Sequence Learning Approach for Emotion Recognition in Conversations. CoRR (2022)
A. Arunkumar, Vrunda N. Sukhadia, Srinivasan Umesh
Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition. CoRR (2022)
Vrunda N. Sukhadia, A. Arunkumar, Srinivasan Umesh
Channel-Aware Pretraining of Joint Encoder-Decoder Self-Supervised Model for Telephonic-Speech ASR. CoRR (2022)
Anish Bhanushali, Grant Bridgman, Deekshitha G, Prasanta Kumar Ghosh, Pratik Kumar, Saurabh Kumar, Adithya Raj Kolladath, Nithya Ravi, Aaditeshwar Seth, Ashish Seth, Abhayjeet Singh, Vrunda N. Sukhadia, Srinivasan Umesh, Sathvik Udupa, Lodagala V. S. V. Durga Prasad
Gram Vaani ASR Challenge on spontaneous telephone speech recordings in regional variations of Hindi. INTERSPEECH (2022)
Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
CCC-WAV2VEC 2.0: Clustering AIDED Cross Contrastive Self-Supervised Learning of Speech Representations. SLT (2022)
Vrunda N. Sukhadia, Srinivasan Umesh
Domain Adaptation of Low-Resource Target-Domain Models Using Well-Trained ASR Conformer Models. SLT (2022)
Sreyan Ghosh, Ashish Seth, Srinivasan Umesh
DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning. CoRR (2022)
Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations. CoRR (2022)
Anusha Prakash, Arun Kumar A, Ashish Seth, Bhagyashree Mukherjee, Ishika Gupta, Jom Kuriakose, Jordan Fernandes, K. V. Vikram, Mano Ranjith Kumar M., Metilda Sagaya Mary, Mohammad Wajahat, Mohana N, Mudit Batra, Navina K, Nihal John George, Nithya Ravi, Pruthwik Mishra, Sudhanshu Srivastava, Vasista Sai Lodagala, Vandan Mujadia, Kada Sai Venkata Vineeth, Vrunda N. Sukhadia, Dipti Misra Sharma, Hema A. Murthy, Pushpak Bhattacharya, Srinivasan Umesh, Rajeev Sangal
Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages. CoRR (2022)
Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations. SLT (2022)
Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup. CoRR (2022)
Sreyan Ghosh, Samden Lepcha, S. Sakshi, Rajiv Ratn Shah, Srinivasan Umesh
DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances. INTERSPEECH (2022)
A. Arunkumar, Vrunda Nileshkumar Sukhadia, Srinivasan Umesh
Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition. INTERSPEECH (2022)
A. Arunkumar, Srinivasan Umesh
Joint Encoder-Decoder Self-Supervised Pre-training for ASR. INTERSPEECH (2022)
Harshvardhan Srivastava, Sreyan Ghosh, Srinivasan Umesh
MMER: Multimodal Multi-task learning for Emotion Recognition in Spoken Utterances. CoRR (2022)
Sreyan Ghosh, Sonal Kumar, Yaman Kumar Singla, Rajiv Ratn Shah, Srinivasan Umesh
Span Classification with Structured Information for Disfluency Detection in Spoken Utterances. CoRR (2022)
Sreyan Ghosh, Sonal Kumar, Yaman Kumar, Rajiv Ratn Shah, Srinivasan Umesh
Span Classification with Structured Information for Disfluency Detection in Spoken Utterances. INTERSPEECH (2022)
Sreyan Ghosh, Ashish Seth, Srinivasan Umesh
Decorrelating Feature Spaces for Learning General-Purpose Audio Representations. IEEE J. Sel. Top. Signal Process. 16 (6) (2022)
Sreyan Ghosh, Sandesh V. Katta, Ashish Seth, Srinivasan Umesh
Deep Clustering For General-Purpose Audio Representations. CoRR (2021)
Vishwas M. Shetty, Srinivasan Umesh
Exploring the use of Common Label Set to Improve Speech Recognition of Low Resource Indian Languages. ICASSP (2021)
Vishwas M. Shetty, Metilda Sagaya Mary N. J, Srinivasan Umesh
Improving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages. ICASSP (2020)
Vishwas M. Shetty, Metilda Sagaya Mary N. J, Srinivasan Umesh
Investigation of Speaker-adaptation methods in Transformer based ASR. CoRR (2020)
Metilda Sagaya Mary N. J, Sandesh V. Katta, Srinivasan Umesh
S-vectors: Speaker Embeddings based on Transformer's Encoder for Text-Independent Speaker Verification. CoRR (2020)
Metilda Sagaya Mary N. J, Vishwas M. Shetty, Srinivasan Umesh
Investigation of Methods to Improve the Recognition Performance of Tamil-English Code-Switched Data in Transformer Framework. ICASSP (2020)
Anusha Prakash, Anju Leela Thomas, Srinivasan Umesh, Hema A. Murthy
Building Multilingual End-to-End Speech Synthesisers for Indian Languages. SSW (2019)
Jochen Weiner, Miguel Angrick, Srinivasan Umesh, Tanja Schultz
Investigating the Effect of Audio Duration on Dementia Detection Using Acoustic Features. INTERSPEECH (2018)
Vishwas M. Shetty, Rini A. Sharon, Basil Abraham, Tejaswi Seeram, Anusha Prakash, Nithya Ravi, Srinivasan Umesh
Articulatory and Stacked Bottleneck Features for Low Resource Speech Recognition. INTERSPEECH (2018)
Neethu Mariam Joy, Sandeep Reddy Kothinti, Srinivasan Umesh
FMLLR Speaker Normalization With i-Vector: In Pseudo-FMLLR and Distillation Framework. IEEE ACM Trans. Audio Speech Lang. Process. 26 (4) (2018)
Rini A. Sharon, Sandeep Reddy Kothinti, Srinivasan Umesh
Correlational Networks for Speaker Normalization in Automatic Speech Recognition. INTERSPEECH (2018)
Neethu Mariam Joy, Sandeep Reddy Kothinti, Srinivasan Umesh, Basil Abraham
Generalized Distillation Framework for Speaker Normalization. INTERSPEECH (2017)
Basil Abraham, Srinivasan Umesh
An automated technique to generate phone-to-articulatory label mapping. Speech Commun. 86 (2017)
Seeram Tejaswi, Srinivasan Umesh
DNN acoustic models for dysarthric speech. NCC (2017)
Seeram Tejaswi, Srinivasan Umesh
Addressing data sparsity in DNN acoustic modeling. NCC (2017)
Basil Abraham, Tejaswi Seeram, Srinivasan Umesh
Transfer Learning and Distillation Techniques to Improve the Acoustic Modeling of Low Resource Languages. INTERSPEECH (2017)
Basil Abraham, Srinivasan Umesh, Neethu Mariam Joy
Joint Estimation of Articulatory Features and Acoustic Models for Low-Resource Languages. INTERSPEECH (2017)
Neethu Mariam Joy, Murali Karthick Baskar, Srinivasan Umesh
DNNs for unsupervised extraction of pseudo speaker-normalized features without explicit adaptation data. Speech Commun. 92 (2017)
Neethu Mariam Joy, Murali Karthick Baskar, Srinivasan Umesh, Basil Abraham
DNNs for Unsupervised Extraction of Pseudo FMLLR Features Without Explicit Adaptation Data. INTERSPEECH (2016)
Basil Abraham, Srinivasan Umesh, Neethu Mariam Joy
Overcoming Data Sparsity in Acoustic Modeling of Low-Resource Language by Borrowing Data and Model Parameters from High-Resource Languages. INTERSPEECH (2016)
Basil Abraham, Srinivasan Umesh, Neethu Mariam Joy
Articulatory Feature Extraction Using CTC to Build Articulatory Classifiers Without Forced Frame Alignments for Speech Recognition. INTERSPEECH (2016)
Vikas Joshi, N. Vishnu Prasad, Srinivasan Umesh
Modified Mean and Variance Normalization: Transforming to Utterance-Specific Estimates. Circuits Syst. Signal Process. 35 (5) (2016)
R. Sriranjani, Murali Karthick B, Srinivasan Umesh
Investigation of different acoustic modeling techniques for low resource Indian language data. NCC (2015)
R. Sriranjani, M. Ramasubba Reddy, Srinivasan Umesh
Improved acoustic modeling for automatic dysarthric speech recognition. NCC (2015)
R. Sriranjani, Srinivasan Umesh, M. Ramasubba Reddy
Pronunciation Adaptation For Disordered Speech Recognition Using State-Specific Vectors of Phone-Cluster Adaptive Training. SLPAT@Interspeech (2015)
Vikas Joshi, Raghavendra Bilgi, Srinivasan Umesh, Luz García, M. Carmen Benítez
Sub-band based histogram equalization in cepstral domain for speech recognition. Speech Commun. 69 (2015)
Murali Karthick B, Prateek Kolhar, Srinivasan Umesh
Speaker adaptation of convolutional neural network using speaker specific subspace vectors of SGMM. INTERSPEECH (2015)
Aanchan Mohan, Richard C. Rose, Sina Hamidi Ghalehjegh, Srinivasan Umesh
Acoustic modelling for speech recognition in Indian languages in an agricultural commodities task domain. Speech Commun. 56 (2014)
Murali Karthick B, Srinivasan Umesh
Improving deep neural networks using state projection vectors of subspace Gaussian mixture model as features. SLT (2014)
Neethu Mariam Joy, Basil Abraham, K. Navneeth, Srinivasan Umesh
Cross-lingual acoustic modeling for Indian languages based on Subspace Gaussian Mixture Models. NCC (2014)
R. Sriranjani, Murali Karthick Baskar, Srinivasan Umesh
Experiments on front-end techniques and segmentation model for robust Indian Language speech recognizer. NCC (2014)
D. S. Pavan Kumar, N. Vishnu Prasad, Vikas Joshi, Srinivasan Umesh
Modified splice and its extension to non-stereo data for noise robust speech recognition. ASRU (2013)
N. Vishnu Prasad, Srinivasan Umesh
Improved cepstral mean and variance normalization using Bayesian framework. ASRU (2013)
D. S. Pavan Kumar, N. Vishnu Prasad, Vikas Joshi, Srinivasan Umesh
Modified SPLICE and its Extension to Non-Stereo Data for Noise Robust Speech Recognition. CoRR (2013)
Vikas Joshi, N. Vishnu Prasad, Srinivasan Umesh
Modified cepstral mean normalization - transforming to utterance specific non-zero mean. INTERSPEECH (2013)
Vimal Manohar, Srinivas C. Bhargav, Srinivasan Umesh
Acoustic modeling using transform-based phone-cluster adaptive training. ASRU (2013)
Raghavendra Bilgi, Vikas Joshi, Srinivasan Umesh, Luz García Martínez, M. Carmen Benítez Ortúzar
Robust speech recognition through selection of speaker and environment transforms. ICASSP (2012)
Achintya Kumar Sarkar, Srinivasan Umesh, Jean-François Bonastre
Computationally efficient speaker identification using fast-MLLR based anchor modeling. ICASSP (2012)
Vikas Joshi, Raghavendra Bilgi, Srinivasan Umesh, Luz García Martínez, M. Carmen Benítez Ortúzar
Noise and speaker compensation in the Log filter bank domain. ICASSP (2012)
D. Rama Sanand, Srinivasan Umesh
VTLN Using Analytically Determined Linear-Transformation on Conventional MFCC. IEEE Trans. Speech Audio Process. 20 (5) (2012)
Achintya Kumar Sarkar, Srinivasan Umesh
Multiple background models for speaker verification using the concept of vocal tract length and MLLR super-vector. Int. J. Speech Technol. 15 (3) (2012)
Aanchan Mohan, Srinivasan Umesh, Richard C. Rose
Subspace based for Indian languages. ISSPA (2012)
Vikas Joshi, Raghavendra Bilgi, Srinivasan Umesh, Luz García, M. Carmen Benítez
Sub-Band Level Histogram Equalization for Robust Speech Recognition. INTERSPEECH (2011)
Vikas Joshi, Raghavendra Bilgi, Srinivasan Umesh, M. Carmen Benítez, Luz García
Efficient Speaker and Noise Normalization for Robust Speech Recognition. INTERSPEECH (2011)
Achintya Kumar Sarkar, Srinivasan Umesh
Use of VTL-wise models in feature-mapping framework to achieve performance of multiple-background models in speaker verification. ICASSP (2011)
Achintya Kumar Sarkar, Srinivasan Umesh
Eigen-Voice Based Anchor Modeling System for Speaker Identification Using MLLR Super-Vector. INTERSPEECH (2011)
Achintya Kumar Sarkar, Srinivasan Umesh, Shakti Prasad Rath
Computationally Efficient Speaker Identification for Large Population Tasks using MLLR and Sufficient Statistics. Odyssey (2010)
Achintya Kumar Sarkar, Srinivasan Umesh
Fast computation of speaker characterization vector using MLLR and sufficient statistics in anchor model framework. INTERSPEECH (2010)
Achintya Kumar Sarkar, Srinivasan Umesh
Investigation of Speaker-Clustered UBMs based on Vocal Tract Lengths and MLLR matrices for Speaker Verification. Odyssey (2010)
Shakti Prasad Rath, Srinivasan Umesh, Achintya Kumar Sarkar
Using VTLN matrices for rapid and computationally-efficient speaker adaptation with robustness to first-pass transcription errors. INTERSPEECH (2009)
D. Rama Sanand, Shakti Prasad Rath, Srinivasan Umesh
A study on the influence of covariance adaptation on jacobian compensation in vocal tract length normalization. INTERSPEECH (2009)
D. Rama Sanand, Shakti Prasad Rath, Srinivasan Umesh
Improving the performance of VTLN under mismatched speaker conditions and making it approach that of matched speaker conditions. ICASSP (2009)
Shakti Prasad Rath, Srinivasan Umesh
Acoustic class specific VTLN-warping using regression class trees. INTERSPEECH (2009)
Achintya Kumar Sarkar, Srinivasan Umesh, Shakti Prasad Rath
Text-independent speaker identification using vocal tract length normalization for building universal background model. INTERSPEECH (2009)
A. N. Harish, D. Rama Sanand, Srinivasan Umesh
Characterizing speaker variability using spectral envelopes of vowel sounds. INTERSPEECH (2009)
Rohit Sinha, Srinivasan Umesh
A shift-based approach to speaker normalization using non-linear frequency-scaling model. Speech Commun. 50 (3) (2008)
P. T. Akhil, Shakti Prasad Rath, Srinivasan Umesh, D. Rama Sanand
A computationally efficient approach to warp factor estimation in VTLN using EM algorithm and sufficient statistics. INTERSPEECH (2008)
D. Rama Sanand, Srinivasan Umesh
Study of jacobian compensation using linear transformation of conventional MFCC for VTLN. INTERSPEECH (2008)
D. Rama Sanand, V. Balaji, Rani R. Sandhya, Srinivasan Umesh
Use of spectral centre of gravity for generating speaker invariant features for automatic speech recognition. INTERSPEECH (2008)
Srinivasan Umesh, D. Rama Sanand, G. Praveen
Speaker-Invariant Features for Automatic Speech Recognition. IJCAI (2007)
Srinivasan Umesh, Rohit Sinha
A Study of Filter Bank Smoothing in MFCC Features for Recognition of Children's Speech. IEEE Trans. Speech Audio Process. 15 (8) (2007)
D. Rama Sanand, D. Dinesh Kumar, Srinivasan Umesh
Linear transformation approach to VTLN using dynamic frequency warping. INTERSPEECH (2007)

Srinivasan Umesh.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Srinivasan Umesh