Srinivasan Umesh

135 papers A* 1A 37C 5Misc 21Journal 44Unranked 27

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Building Robust and Scalable Multilingual ASR for Indian Languages. CoRR Arjun Gangwar, Kaousheik Jayakumar, Srinivasan Umesh
2025	—	`conf`	EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion. EMNLP (Findings) Advait Joglekar, Divyanshu Singh, Rooshil Rohit Bhatia, Srinivasan Umesh
2025	J	`jnl`	EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion. CoRR Advait Joglekar, Divyanshu Singh, Rooshil Rohit Bhatia, Srinivasan Umesh
2025	J	`jnl`	Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching. CoRR Shoutrik Das, Nishant Singh, Arjun Gangwar, Srinivasan Umesh
2025	C	`conf`	MADASR 2.0: Multi-Lingual Multi-Dialect ASR Challenge in 8 Indian Languages. ASRU Saurabh Kumar, Sumit Sharma, Deekshitha G, Abhayjeet Singh, Amartyaveer, Sathvik Udupa, Sandhya Badiger, Sanjeev Khudanpur, Sunayana Sitaram, Srinivasan Umesh, Bhuvana Ramabhadran, Brian Kingsbury, Hema A. Murthy, Srikanth S. Narayanan, Howard Lakougna, Prasanta Kumar Ghosh
2024	A	`conf`	All Ears: Building Self-Supervised Learning based ASR models for Indian Languages at scale. INTERSPEECH Vasista Sai Lodagala, Abhishek Biswas, Shoutrik Das, Jordan Fernandes, Srinivasan Umesh
2024	Misc	`conf`	FusDom: Combining in-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning. ICASSP Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
2024	—	`conf`	Lite ASR Transformer: A Light Weight Transformer Architecture For Automatic Speech Recognition. SLT Narla John Metilda Sagaya Mary, Srinivasan Umesh
2024	J	`jnl`	On the relationship between speech and hearing. CoRR Srinivasan Umesh, Leon Cohen, Douglas J. Nelson
2024	—	`conf`	SPRING Lab IITM's Submission to Low Resource Indic Language Translation Shared Task. WMT Advait Joglekar, Hamees Ul Hasan Sayed, Srinivasan Umesh
2024	J	`jnl`	SPRING Lab IITM's submission to Low Resource Indic Language Translation Shared Task. CoRR Hamees Ul Hasan Sayed, Advait Joglekar, Srinivasan Umesh
2024	J	`jnl`	Shiksha: A Technical Domain focused Translation Dataset and Model for Indian Languages. CoRR Advait Joglekar, Srinivasan Umesh
2024	Misc	`conf`	Stable Distillation: Regularizing Continued Pre-Training for Low-Resource Automatic Speech Recognition. ICASSP Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
2023	—	`conf`	Channel-Aware Pretraining Of Joint Encoder-Decoder Self-Supervised Model For Telephonic-Speech ASR. ICASSP Workshops Vrunda N. Sukhadia, Srinivasan Umesh
2023	Misc	`conf`	Data2vec-Aqc: Search for the Right Teaching Assistant in the Teacher-Student Training Setup. ICASSP Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
2023	J	`jnl`	FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning. CoRR Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
2023	Misc	`conf`	MAST: Multiscale Audio Spectrogram Transformers. ICASSP Sreyan Ghosh, Ashish Seth, Srinivasan Umesh, Dinesh Manocha
2023	A	`conf`	SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis. INTERSPEECH Ramanan Sivaguru, Vasista Sai Lodagala, Srinivasan Umesh
2023	J	`jnl`	SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis. CoRR Ramanan Sivaguru, Vasista Sai Lodagala, Srinivasan Umesh
2023	Misc	`conf`	SLICER: Learning Universal Audio Representations Using Low-Resource Self-Supervised Pre-Training. ICASSP Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
2023	J	`jnl`	Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition. CoRR Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
2023	A	`conf`	Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages. INTERSPEECH 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
2023	A	`conf`	The Tag-Team Approach: Leveraging CLS and Language Tagging for Enhancing Multilingual ASR. INTERSPEECH Kaousheik Jayakumar, Vrunda N. Sukhadia, Arun Kumar A, Srinivasan Umesh
2023	J	`jnl`	The Tag-Team Approach: Leveraging CLS and Language Tagging for Enhancing Multilingual ASR. CoRR Kaousheik Jayakumar, Vrunda N. Sukhadia, A. Arunkumar, Srinivasan Umesh
2023	C	`conf`	Towards Developing State-of-The-Art TTS Synthesisers for 13 Indian Languages with Signal Processing Aided Alignments. ASRU Anusha Prakash, Srinivasan Umesh, Hema A. Murthy
2023	J	`jnl`	UNFUSED: UNsupervised Finetuning Using SElf supervised Distillation. CoRR Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
2023	—	`conf`	Unfused: Unsupervised Finetuning Using Self Supervised Distillation. ICASSP Workshops Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
2022	J	`jnl`	A Discourse Aware Sequence Learning Approach for Emotion Recognition in Conversations. CoRR Sreyan Ghosh, Harshvardhan Srivastava, Srinivasan Umesh
2022	J	`jnl`	Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition. CoRR Lodagala Durga Prasad, Ashish Seth, Sreyan Ghosh, Srinivasan Umesh
2022	—	`conf`	CCC-WAV2VEC 2.0: Clustering AIDED Cross Contrastive Self-Supervised Learning of Speech Representations. SLT Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
2022	J	`jnl`	CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations. CoRR Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
2022	J	`jnl`	Channel-Aware Pretraining of Joint Encoder-Decoder Self-Supervised Model for Telephonic-Speech ASR. CoRR Vrunda N. Sukhadia, A. Arunkumar, Srinivasan Umesh
2022	J	`jnl`	DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning. CoRR Sreyan Ghosh, Ashish Seth, Srinivasan Umesh
2022	A	`conf`	DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances. INTERSPEECH Sreyan Ghosh, Samden Lepcha, Sakshi Singh, Rajiv Ratn Shah, Srinivasan Umesh
2022	J	`jnl`	Decorrelating Feature Spaces for Learning General-Purpose Audio Representations. IEEE J. Sel. Top. Signal Process. Sreyan Ghosh, Ashish Seth, Srinivasan Umesh
2022	—	`conf`	Domain Adaptation of Low-Resource Target-Domain Models Using Well-Trained ASR Conformer Models. SLT Vrunda N. Sukhadia, Srinivasan Umesh
2022	J	`jnl`	Domain Adaptation of low-resource Target-Domain models using well-trained ASR Conformer Models. CoRR Vrunda N. Sukhadia, Srinivasan Umesh
2022	A	`conf`	Gram Vaani ASR Challenge on spontaneous telephone speech recordings in regional variations of Hindi. INTERSPEECH 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
2022	A	`conf`	Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition. INTERSPEECH A. Arunkumar, Vrunda Nileshkumar Sukhadia, Srinivasan Umesh
2022	J	`jnl`	Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition. CoRR A. Arunkumar, Vrunda N. Sukhadia, Srinivasan Umesh
2022	Misc	`conf`	Investigation of Robustness of Hubert Features from Different Layers to Domain, Accent and Language Variations. ICASSP Pratik Kumar, Vrunda N. Sukhadia, Srinivasan Umesh
2022	A	`conf`	Joint Encoder-Decoder Self-Supervised Pre-training for ASR. INTERSPEECH A. Arunkumar, Srinivasan Umesh
2022	J	`jnl`	MAST: Multiscale Audio Spectrogram Transformers. CoRR Sreyan Ghosh, Ashish Seth, Srinivasan Umesh, Dinesh Manocha
2022	J	`jnl`	MMER: Multimodal Multi-task learning for Emotion Recognition in Spoken Utterances. CoRR Harshvardhan Srivastava, Sreyan Ghosh, Srinivasan Umesh
2022	—	`conf`	PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations. SLT Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
2022	J	`jnl`	PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations. CoRR Lodagala V. S. V. Durga Prasad, Sreyan Ghosh, Srinivasan Umesh
2022	J	`jnl`	S-Vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder. IEEE ACM Trans. Audio Speech Lang. Process. Narla John Metilda Sagaya Mary, Srinivasan Umesh, Sandesh Varadaraju Katta
2022	J	`jnl`	SLICER: Learning universal audio representations using low-resource self-supervised pre-training. CoRR Ashish Seth, Sreyan Ghosh, Srinivasan Umesh, Dinesh Manocha
2022	A	`conf`	Span Classification with Structured Information for Disfluency Detection in Spoken Utterances. INTERSPEECH Sreyan Ghosh, Sonal Kumar, Yaman Kumar, Rajiv Ratn Shah, Srinivasan Umesh
2022	J	`jnl`	Span Classification with Structured Information for Disfluency Detection in Spoken Utterances. CoRR Sreyan Ghosh, Sonal Kumar, Yaman Kumar Singla, Rajiv Ratn Shah, Srinivasan Umesh
2022	J	`jnl`	Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages. CoRR 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
2022	J	`jnl`	data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup. CoRR Vasista Sai Lodagala, Sreyan Ghosh, Srinivasan Umesh
2021	J	`jnl`	Deep Clustering For General-Purpose Audio Representations. CoRR Sreyan Ghosh, Sandesh V. Katta, Ashish Seth, Srinivasan Umesh
2021	Misc	`conf`	Exploring the use of Common Label Set to Improve Speech Recognition of Low Resource Indian Languages. ICASSP Vishwas M. Shetty, Srinivasan Umesh
2020	Misc	`conf`	Improving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages. ICASSP Vishwas M. Shetty, Metilda Sagaya Mary N. J, Srinivasan Umesh
2020	Misc	`conf`	Investigation of Methods to Improve the Recognition Performance of Tamil-English Code-Switched Data in Transformer Framework. ICASSP Metilda Sagaya Mary N. J, Vishwas M. Shetty, Srinivasan Umesh
2020	J	`jnl`	Investigation of Speaker-adaptation methods in Transformer based ASR. CoRR Vishwas M. Shetty, Metilda Sagaya Mary N. J, Srinivasan Umesh
2020	J	`jnl`	S-vectors: Speaker Embeddings based on Transformer's Encoder for Text-Independent Speaker Verification. CoRR Metilda Sagaya Mary N. J, Sandesh V. Katta, Srinivasan Umesh
2019	—	`conf`	Building Multilingual End-to-End Speech Synthesisers for Indian Languages. SSW Anusha Prakash, Anju Leela Thomas, Srinivasan Umesh, Hema A. Murthy
2018	A	`conf`	Articulatory and Stacked Bottleneck Features for Low Resource Speech Recognition. INTERSPEECH Vishwas M. Shetty, Rini A. Sharon, Basil Abraham, Tejaswi Seeram, Anusha Prakash, Nithya Ravi, Srinivasan Umesh
2018	A	`conf`	Correlational Networks for Speaker Normalization in Automatic Speech Recognition. INTERSPEECH Rini A. Sharon, Sandeep Reddy Kothinti, Srinivasan Umesh
2018	J	`jnl`	FMLLR Speaker Normalization With i-Vector: In Pseudo-FMLLR and Distillation Framework. IEEE ACM Trans. Audio Speech Lang. Process. Neethu Mariam Joy, Sandeep Reddy Kothinti, Srinivasan Umesh
2018	A	`conf`	Investigating the Effect of Audio Duration on Dementia Detection Using Acoustic Features. INTERSPEECH Jochen Weiner, Miguel Angrick, Srinivasan Umesh, Tanja Schultz
2017	—	`conf`	Addressing data sparsity in DNN acoustic modeling. NCC Seeram Tejaswi, Srinivasan Umesh
2017	J	`jnl`	An automated technique to generate phone-to-articulatory label mapping. Speech Commun. Basil Abraham, Srinivasan Umesh
2017	—	`conf`	DNN acoustic models for dysarthric speech. NCC Seeram Tejaswi, Srinivasan Umesh
2017	J	`jnl`	DNNs for unsupervised extraction of pseudo speaker-normalized features without explicit adaptation data. Speech Commun. Neethu Mariam Joy, Murali Karthick Baskar, Srinivasan Umesh
2017	A	`conf`	Generalized Distillation Framework for Speaker Normalization. INTERSPEECH Neethu Mariam Joy, Sandeep Reddy Kothinti, Srinivasan Umesh, Basil Abraham
2017	A	`conf`	Joint Estimation of Articulatory Features and Acoustic Models for Low-Resource Languages. INTERSPEECH Basil Abraham, Srinivasan Umesh, Neethu Mariam Joy
2017	A	`conf`	On Improving Acoustic Models for TORGO Dysarthric Speech Database. INTERSPEECH Neethu Mariam Joy, Srinivasan Umesh, Basil Abraham
2017	A	`conf`	Transfer Learning and Distillation Techniques to Improve the Acoustic Modeling of Low Resource Languages. INTERSPEECH Basil Abraham, Tejaswi Seeram, Srinivasan Umesh
2016	A	`conf`	Articulatory Feature Extraction Using CTC to Build Articulatory Classifiers Without Forced Frame Alignments for Speech Recognition. INTERSPEECH Basil Abraham, Srinivasan Umesh, Neethu Mariam Joy
2016	A	`conf`	DNNs for Unsupervised Extraction of Pseudo FMLLR Features Without Explicit Adaptation Data. INTERSPEECH Neethu Mariam Joy, Murali Karthick Baskar, Srinivasan Umesh, Basil Abraham
2016	—	`conf`	Improved phone-cluster adaptive training acoustic model. SPCOM Neethu Mariam Joy, Srinivasan Umesh, Basil Abraham, K. Navneeth
2016	J	`jnl`	Modified Mean and Variance Normalization: Transforming to Utterance-Specific Estimates. Circuits Syst. Signal Process. Vikas Joshi, N. Vishnu Prasad, Srinivasan Umesh
2016	A	`conf`	Overcoming Data Sparsity in Acoustic Modeling of Low-Resource Language by Borrowing Data and Model Parameters from High-Resource Languages. INTERSPEECH Basil Abraham, Srinivasan Umesh, Neethu Mariam Joy
2015	—	`conf`	Improved acoustic modeling for automatic dysarthric speech recognition. NCC R. Sriranjani, M. Ramasubba Reddy, Srinivasan Umesh
2015	—	`conf`	Investigation of different acoustic modeling techniques for low resource Indian language data. NCC R. Sriranjani, Murali Karthick B, Srinivasan Umesh
2015	—	`conf`	Pronunciation Adaptation For Disordered Speech Recognition Using State-Specific Vectors of Phone-Cluster Adaptive Training. SLPAT@Interspeech R. Sriranjani, Srinivasan Umesh, M. Ramasubba Reddy
2015	A	`conf`	Speaker adaptation of convolutional neural network using speaker specific subspace vectors of SGMM. INTERSPEECH Murali Karthick B, Prateek Kolhar, Srinivasan Umesh
2015	J	`jnl`	Sub-band based histogram equalization in cepstral domain for speech recognition. Speech Commun. Vikas Joshi, Raghavendra Bilgi, Srinivasan Umesh, Luz García, M. Carmen Benítez
2014	J	`jnl`	Acoustic modelling for speech recognition in Indian languages in an agricultural commodities task domain. Speech Commun. Aanchan Mohan, Richard C. Rose, Sina Hamidi Ghalehjegh, Srinivasan Umesh
2014	—	`conf`	Cross-lingual acoustic modeling for Indian languages based on Subspace Gaussian Mixture Models. NCC Neethu Mariam Joy, Basil Abraham, K. Navneeth, Srinivasan Umesh
2014	—	`conf`	Experiments on front-end techniques and segmentation model for robust Indian Language speech recognizer. NCC R. Sriranjani, Murali Karthick Baskar, Srinivasan Umesh
2014	—	`conf`	Improving deep neural networks using state projection vectors of subspace Gaussian mixture model as features. SLT Murali Karthick B, Srinivasan Umesh
2013	C	`conf`	Acoustic modeling using transform-based phone-cluster adaptive training. ASRU Vimal Manohar, Srinivas C. Bhargav, Srinivasan Umesh
2013	C	`conf`	Improved cepstral mean and variance normalization using Bayesian framework. ASRU N. Vishnu Prasad, Srinivasan Umesh
2013	J	`jnl`	Modified SPLICE and its Extension to Non-Stereo Data for Noise Robust Speech Recognition. CoRR D. S. Pavan Kumar, N. Vishnu Prasad, Vikas Joshi, Srinivasan Umesh
2013	A	`conf`	Modified cepstral mean normalization - transforming to utterance specific non-zero mean. INTERSPEECH Vikas Joshi, N. Vishnu Prasad, Srinivasan Umesh
2013	C	`conf`	Modified splice and its extension to non-stereo data for noise robust speech recognition. ASRU D. S. Pavan Kumar, N. Vishnu Prasad, Vikas Joshi, Srinivasan Umesh
2012	Misc	`conf`	Computationally efficient speaker identification using fast-MLLR based anchor modeling. ICASSP Achintya Kumar Sarkar, Srinivasan Umesh, Jean-François Bonastre
2012	J	`jnl`	Multiple background models for speaker verification using the concept of vocal tract length and MLLR super-vector. Int. J. Speech Technol. Achintya Kumar Sarkar, Srinivasan Umesh
2012	Misc	`conf`	Noise and speaker compensation in the Log filter bank domain. ICASSP Vikas Joshi, Raghavendra Bilgi, Srinivasan Umesh, Luz García Martínez, M. Carmen Benítez Ortúzar
2012	Misc	`conf`	Robust speech recognition through selection of speaker and environment transforms. ICASSP Raghavendra Bilgi, Vikas Joshi, Srinivasan Umesh, Luz García Martínez, M. Carmen Benítez Ortúzar
2012	—	`conf`	Subspace based for Indian languages. ISSPA Aanchan Mohan, Srinivasan Umesh, Richard C. Rose
2012	J	`jnl`	VTLN Using Analytically Determined Linear-Transformation on Conventional MFCC. IEEE Trans. Speech Audio Process. D. Rama Sanand, Srinivasan Umesh
2011	A	`conf`	Efficient Speaker and Noise Normalization for Robust Speech Recognition. INTERSPEECH Vikas Joshi, Raghavendra Bilgi, Srinivasan Umesh, M. Carmen Benítez, Luz García
2011	A	`conf`	Eigen-Voice Based Anchor Modeling System for Speaker Identification Using MLLR Super-Vector. INTERSPEECH Achintya Kumar Sarkar, Srinivasan Umesh
2011	A	`conf`	Sub-Band Level Histogram Equalization for Robust Speech Recognition. INTERSPEECH Vikas Joshi, Raghavendra Bilgi, Srinivasan Umesh, Luz García, M. Carmen Benítez
2011	Misc	`conf`	Use of VTL-wise models in feature-mapping framework to achieve performance of multiple-background models in speaker verification. ICASSP Achintya Kumar Sarkar, Srinivasan Umesh
2010	—	`conf`	Computationally Efficient Speaker Identification for Large Population Tasks using MLLR and Sufficient Statistics. Odyssey Achintya Kumar Sarkar, Srinivasan Umesh, Shakti Prasad Rath
2010	A	`conf`	Fast computation of speaker characterization vector using MLLR and sufficient statistics in anchor model framework. INTERSPEECH Achintya Kumar Sarkar, Srinivasan Umesh
2010	—	`conf`	Investigation of Speaker-Clustered UBMs based on Vocal Tract Lengths and MLLR matrices for Speaker Verification. Odyssey Achintya Kumar Sarkar, Srinivasan Umesh
2009	A	`conf`	A study on the influence of covariance adaptation on jacobian compensation in vocal tract length normalization. INTERSPEECH D. Rama Sanand, Shakti Prasad Rath, Srinivasan Umesh
2009	A	`conf`	Acoustic class specific VTLN-warping using regression class trees. INTERSPEECH Shakti Prasad Rath, Srinivasan Umesh
2009	A	`conf`	Characterizing speaker variability using spectral envelopes of vowel sounds. INTERSPEECH A. N. Harish, D. Rama Sanand, Srinivasan Umesh
2009	Misc	`conf`	Improving the performance of VTLN under mismatched speaker conditions and making it approach that of matched speaker conditions. ICASSP D. Rama Sanand, Shakti Prasad Rath, Srinivasan Umesh
2009	A	`conf`	Text-independent speaker identification using vocal tract length normalization for building universal background model. INTERSPEECH Achintya Kumar Sarkar, Srinivasan Umesh, Shakti Prasad Rath
2009	A	`conf`	Using VTLN matrices for rapid and computationally-efficient speaker adaptation with robustness to first-pass transcription errors. INTERSPEECH Shakti Prasad Rath, Srinivasan Umesh, Achintya Kumar Sarkar
2008	A	`conf`	A computationally efficient approach to warp factor estimation in VTLN using EM algorithm and sufficient statistics. INTERSPEECH P. T. Akhil, Shakti Prasad Rath, Srinivasan Umesh, D. Rama Sanand
2008	J	`jnl`	A shift-based approach to speaker normalization using non-linear frequency-scaling model. Speech Commun. Rohit Sinha, Srinivasan Umesh
2008	A	`conf`	Study of jacobian compensation using linear transformation of conventional MFCC for VTLN. INTERSPEECH D. Rama Sanand, Srinivasan Umesh
2008	A	`conf`	Use of spectral centre of gravity for generating speaker invariant features for automatic speech recognition. INTERSPEECH D. Rama Sanand, V. Balaji, Rani R. Sandhya, Srinivasan Umesh
2007	J	`jnl`	A Study of Filter Bank Smoothing in MFCC Features for Recognition of Children's Speech. IEEE Trans. Speech Audio Process. Srinivasan Umesh, Rohit Sinha
2007	A	`conf`	Linear transformation approach to VTLN using dynamic frequency warping. INTERSPEECH D. Rama Sanand, D. Dinesh Kumar, Srinivasan Umesh
2007	A*	`conf`	Speaker-Invariant Features for Automatic Speech Recognition. IJCAI Srinivasan Umesh, D. Rama Sanand, G. Praveen
2006	—	`conf`	Study Of Non-Linear Frequency Warping Functions For Speaker Normalization. ICASSP (1) S. V. Bharath Kumar, Srinivasan Umesh, Rohit Sinha
2006	—	`conf`	Vtln Warping Factor Estimation Using Accumulation of Sufficient Statistics. ICASSP (1) Jonas Lööf, Hermann Ney, Srinivasan Umesh
2005	A	`conf`	Implementing frequency-warping and VTLN through linear transformation of conventional MFCC. INTERSPEECH Srinivasan Umesh, András Zolnay, Hermann Ney
2004	—	`conf`	An investigation into front-end signal processing for speaker normalization. ICASSP (1) Srinivasan Umesh, Rohit Sinha, S. V. Bharath Kumar
2004	—	`conf`	Non-uniform speaker normalization using affine-transformation. ICASSP (1) S. V. Bharath Kumar, Srinivasan Umesh, Rohit Sinha
2004	A	`conf`	Using VTLN for broadcast news transcription. INTERSPEECH Do Yeong Kim, Srinivasan Umesh, Mark J. F. Gales, Thomas Hain, Philip C. Woodland
2003	—	`conf`	A method for compensation of Jacobian in speaker normalization. ICASSP (1) Rohit Sinha, Srinivasan Umesh
2002	Misc	`conf`	A simple approach to non-uniform vowel normalization. ICASSP Srinivasan Umesh, S. V. Bharath Kumar, M. K. Vinay, Rajesh Sharma, Rohit Sinha
2002	J	`jnl`	Frequency warping and the Mel scale. IEEE Signal Process. Lett. Srinivasan Umesh, Leon Cohen, Douglas J. Nelson
2002	Misc	`conf`	Non-uniform scaling based speaker normalization. ICASSP Rohit Sinha, Srinivasan Umesh
2000	A	`conf`	Exploiting frequency-scaling invariance properties of the scale transform for automatic speech recognition. INTERSPEECH Srinivasan Umesh, Richard C. Rose, Sarangarajan Parthasarathy
1999	Misc	`conf`	Fitting the Mel scale. ICASSP Srinivasan Umesh, Leon Cohen, Douglas J. Nelson
1999	J	`jnl`	Scale transform in speech analysis. IEEE Trans. Speech Audio Process. Srinivasan Umesh, Leon Cohen, Nenad Marinovic, Douglas J. Nelson
1998	Misc	`conf`	Improved scale-cepstral analysis in speech. ICASSP Srinivasan Umesh, Leon Cohen, Douglas J. Nelson
1997	Misc	`conf`	Frequency-warping and speaker-normalization. ICASSP Srinivasan Umesh, Leon Cohen, Douglas J. Nelson
1996	Misc	`conf`	Computationally efficient estimation of sinusoidal frequency at low SNR. ICASSP Srinivasan Umesh, Douglas J. Nelson
1996	J	`jnl`	Estimation of parameters of exponentially damped sinusoids using fast maximum likelihood estimation with application to NMR spectroscopy data. IEEE Trans. Signal Process. Srinivasan Umesh, Donald W. Tufts
1996	—	`conf`	Frequency-warping in speech. ICSLP Srinivasan Umesh, Leon Cohen, Nenad Marinovic, Douglas J. Nelson
1992	Misc	`conf`	Resolving the components of transient signals by a multistage procedure. ICASSP Srinivasan Umesh, Donald W. Tufts