V. Ramasubramanian

63 papers A 11Misc 7Journal 13Unranked 32

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Accent-robust speech recognition for English in low-resource settings using Manifold Mixup. EURASIP J. Audio Speech Music. Process. Tirthankar Banerjee, V. Ramasubramanian
2025	—	`conf`	Adaptive Hierarchical Inference Framework for Enhanced Efficiency and Scalability in Complex IoT Decision-Making Systems. WF-IoT Eniyan M. K, T. S. V. Ramya, Vignesh G, V. Ramasubramanian, Vijaya Kumar Sundar, S. Vishnu, Vishnuvarthan Rajagopal
2025	—	`conf`	Clustering by Limit-Cycles in Hopfield Neural Network. AIAI (3) Jhelum Das, Vandana M. Ladwani, V. Ramasubramanian
2024	—	`conf`	Few-Shot Learning for Low-Resource E2E ASR: Mono-, Cross- and Multi-Lingual Scenarios. SPCOM Dhanya Eledath, V. Ramasubramanian
2023	—	`conf`	Connectionist Temporal Sequence Decoding: M-ary Hopfield Neural-Network with Multi-limit Cycle Formulation. ICANN (5) Vandana M. Ladwani, V. Ramasubramanian
2023	J	`jnl`	Correction: Trainable windows for SincNet architecture. EURASIP J. Audio Speech Music. Process. Prashanth H. C., Madhav Rao, Dhanya Eledath, V. Ramasubramanian
2022	—	`conf`	Few-shot learning for E2E speech recognition: architectural variants for support set generation. EUSIPCO Dhanya Eledath, Narasimha Rao Thurlapati, V. Pavithra, Tirthankar Banerjee, V. Ramasubramanian
2022	—	`conf`	M-ary Hopfield neural network for storage and retrieval of variable length sequences: Multi-limit cycle approach. SSCI Vandana M. Ladwani, V. Ramasubramanian
2021	J	`jnl`	Approaches for Multilingual Phone Recognition in Code-switched and Non-code-switched Scenarios Using Indian Languages. ACM Trans. Asian Low Resour. Lang. Inf. Process. K. E. Manjunath, Srinivasa Raghavan K. M., K. Sreenivasa Rao, Dinesh Babu Jayagopi, V. Ramasubramanian
2021	—	`conf`	End-to-end speech recognition from raw speech: Multi time-frequency resolution CNN architecture for efficient representation learning. EUSIPCO Dhanya Eledath, P. Inbarajan, Anurag Biradar, Sathwick Mahadeva, V. Ramasubramanian
2021	—	`conf`	Few shot learning for cross-lingual isolated word recognition. AIMLSystems Tirthankar Banerjee, Dhanya Eledath, V. Ramasubramanian
2021	—	`conf`	Few-Shot learning for frame-Wise phoneme recognition: Adaptation of matching networks. EUSIPCO Tirthankar Banerjee, Narasimha Rao Thurlapati, V. Pavithra, S. Mahalakshmi, Dhanya Eledath, V. Ramasubramanian
2021	—	`conf`	Harnessing Energy of M-ary Hopfield Neural Network for Connectionist Temporal Sequence Decoding. MIKE Vandana M. Ladwani, V. Ramasubramanian
2021	—	`conf`	M-ary Hopfield Neural Network Based Associative Memory Formulation: Limit-Cycle Based Sequence Storage and Retrieval. ICANN (4) Vandana M. Ladwani, V. Ramasubramanian
2020	—	`conf`	Component-specific temporal decomposition: application to enhanced speech coding and co-articulation analysis. SPCOM Tilak Purohit, V. Ramasubramanian
2020	—	`conf`	End-to-end audio-scene classification from raw audio: Multi time-frequency resolution CNN architecture for efficient representation learning. SPCOM T. Vijaya Kumar, R. Shunmuga Sundar, Tilak Purohit, V. Ramasubramanian
2020	—	`conf`	Jointly learning to align and transcribe using attention-based alignment and uncertainty-to-weigh losses. SPCOM Shreekantha Nadig, Sumit Chakraborty, Anuj Shah, Chaitanay Sharma, V. Ramasubramanian, Sachit Rao
2020	—	`conf`	Multi-target hybrid CTC-Attentional Decoder for joint phoneme-grapheme recognition. SPCOM Shreekantha Nadig, V. Ramasubramanian, Sachit Rao
2020	—	`conf`	Semi-supervised learning for acoustic model retraining: Handling speech data with noisy transcript. SPCOM Abhijith Madan, Ayush Khopkar, Shreekantha Nadig, Srinivasa Raghavan K. M., Dhanya Eledath, V. Ramasubramanian
2019	—	`conf`	Detection of emotional states of OCD patients in an exposure-response prevention therapy scenario. SMM Kaajal Gupta, Anzar Zulfiqar, Pushpa Ramu, Tilak Purohit, V. Ramasubramanian
2019	J	`jnl`	Development and analysis of multilingual phone recognition systems using Indian languages. Int. J. Speech Technol. K. E. Manjunath, Dinesh Babu Jayagopi, K. Sreenivasa Rao, V. Ramasubramanian
2019	—	`conf`	Multi-modal Associative Storage and Retrieval Using Hopfield Auto-associative Memory Network. ICANN (1) Rachna Shriwas, Prasun Joshi, Vandana M. Ladwani, V. Ramasubramanian
2018	A	`conf`	Indian Languages ASR: A Multilingual Phone Recognition Framework with IPA Based Common Phone-set, Predicted Articulatory Features and Feature fusion. INTERSPEECH K. E. Manjunath, K. Sreenivasa Rao, Dinesh Babu Jayagopi, V. Ramasubramanian
2018	A	`conf`	Semi-supervised and Active-learning Scenarios: Efficient Acoustic Model Refinement for a Low Resource Indian Language. INTERSPEECH Maharajan Chellapriyadharshini, Anoop Toffy, Srinivasa Raghavan K. M., V. Ramasubramanian
2018	J	`jnl`	Semi-supervised and Active-learning Scenarios: Efficient Acoustic Model Refinement for a Low Resource Indian Language. CoRR Maharajan Chellapriyadharshini, Anoop Toffy, Srinivasa Raghavan K. M., V. Ramasubramanian
2017	—	`conf`	Hopfield net framework for audio search. NCC Vandana M. Ladwani, Y. Vaishnavi, R. Shreyas, B. R. Vinay Kumar, N. Harisha, S. Yogesh, P. Shivaganga, V. Ramasubramanian
2017	—	`conf`	Prosodic differential for narrow-focus word-stress in speech synthesis. NCC Anusha Kamat, Abhishek Krishnamurthy, D. N. Krishna, V. Ramasubramanian
2016	Misc	`conf`	Template based techniques for automatic segmentation of TTS unit database. ICASSP S. Adithya, Sunil Rao, C. Mahima, S. Vishnu, Mythri Thippareddy, V. Ramasubramanian
2015	—	`conf`	Spoken Document Retrieval: Sub-sequence DTW Framework and Variants. MIKE Akshay Khatwani, Komala Pawar, Sushma Hegde, Sudha Rao, Adithya Seshasayee, V. Ramasubramanian
2013	Misc	`conf`	Two-class verifier framework for audio indexing. ICASSP V. Ramasubramanian, S. Thiyagarajan, G. Pradnya, Heiko Claussen, Justinian Rosca
2011	Misc	`conf`	Continuous audio analytics by HMM and Viterbi decoding. ICASSP V. Ramasubramanian, R. Karthik, S. Thiyagarajan, Srikanth Cherla
2010	A	`conf`	Audio analytics by template modeling and 1-pass DP based decoding. INTERSPEECH Srikanth Cherla, V. Ramasubramanian
2009	—	`conf`	High Performance On-line Session-adaptation for Handling Inter-session Speaker Variability in Variable-text Speaker-recognition. ICAPR S. Thiyagarajan, V. Ramasubramanian
2009	A	`conf`	Ultra low bit-rate speech coding based on unit-selection with joint spectral-residual quantization: no transmission of any residual information. INTERSPEECH V. Ramasubramanian, D. Harish
2008	—	`conf`	Accented Indian english ASR: Some early results. SLT Kaustubh Kulkarni, Sohini Sengupta, V. Ramasubramanian, Josef G. Bauer, Georg Stemmer
2008	Misc	`conf`	Acoustic modeling by phoneme templates and modified one-pass DP decoding for continuous speech recognition. ICASSP V. Ramasubramanian, Kaustubh Kulkarni, Bernhard Kaemmerer
2008	Misc	`conf`	Comparison of segment quantizers: VQ, MQ, VLSQ and unit-selection algorithms for ultra low bit-rate speech coding. ICASSP D. Harish, V. Ramasubramanian
2008	A	`conf`	Low complexity near-optimal unit-selection algorithm for ultra low bit-rate speech coding based on n-best lattice and Viterbi search. INTERSPEECH V. Ramasubramanian, D. Harish
2008	A	`conf`	Speech enhancement based on hypothesized Wiener filtering. INTERSPEECH V. Ramasubramanian, Deepak Vijaywargi
2008	—	`conf`	Towards fast, view-invariant human action recognition. CVPR Workshops Srikanth Cherla, Kaustubh Kulkarni, Amit A. Kale, V. Ramasubramanian
2007	—	`conf`	An Optimal Unit-Selection Algorithm for Ultra Low Bit-Rate Speech Coding. ICASSP (4) V. Ramasubramanian, D. Harish
2006	A	`conf`	An unified unit-selection framework for ultra low bit-rate speech coding. INTERSPEECH V. Ramasubramanian, D. Harish
2006	A	`conf`	Highly noise robust text-dependent speaker recognition based on hypothesized wiener filtering. INTERSPEECH V. Ramasubramanian, Deepak Vijaywargiay, Kumar V. Praveen
2006	—	`conf`	Text-Dependent Speaker-Recognition Using One-Pass Dynamic Programming Algorithm. ICASSP (1) V. Ramasubramanian, Amitava Das, Kumar V. Praveen
2006	—	`conf`	Text-dependent speaker-recognition systems based on one-pass dynamic programming algorithm. Odyssey V. Ramasubramanian, Kumar V. Praveen, Deepak Vijaywargiay, D. Harish, S. Thiyagarajan, Amitava Das
2005	—	`conf`	Automatic Language Identification Using Ergodic HMM. ICASSP (1) S. A. SantoshKumar, V. Ramasubramanian
2005	A	`conf`	Stochastic pronunciation modeling by ergodic-HMM of acoustic sub-word units. INTERSPEECH V. Ramasubramanian, P. Srinivas, T. V. Sreenivas
2004	—	`conf`	Automatically derived units for segment vocoders. ICASSP (1) V. Ramasubramanian, Thippur V. Sreenivas
2003	A	`conf`	Language identification using parallel sub-word recognition - an ergodic HMM equivalence. INTERSPEECH V. Ramasubramanian, A. K. V. Sai Jayram, T. V. Sreenivas
2003	—	`conf`	Language identification using parallel sub-word recognition. ICASSP (1) A. K. V. Sai Jayram, V. Ramasubramanian, Thippur V. Sreenivas
2002	A	`conf`	Automatic language identification using acoustic sub-word units. INTERSPEECH A. K. V. Sai Jayram, V. Ramasubramanian, T. V. Sreenivas
2002	Misc	`conf`	Robust parameters for automatic segmentation of speech. ICASSP A. K. V. Sai Jayram, V. Ramasubramanian, T. V. Sreenivas
2000	J	`jnl`	Comments on "modified K-means algorithm for vector quantizer design". IEEE Trans. Image Process. Kuldip K. Paliwal, V. Ramasubramanian
2000	J	`jnl`	Fast nearest-neighbor search algorithms based on approximation-elimination search. Pattern Recognit. V. Ramasubramanian, Kuldip K. Paliwal
1999	J	`jnl`	Fast nearest-neighbor search based on Voronoi projections and its application to vector quantization encoding. IEEE Trans. Speech Audio Process. V. Ramasubramanian, Kuldip K. Paliwal
1997	J	`jnl`	Fast Vector Quantization Encoding Based onK-d Tree Backtracking Search Algorithm. Digit. Signal Process. V. Ramasubramanian, Kuldip K. Paliwal
1997	—	`conf`	Reducing the complexity of the LPC vector quantizer using the k-d tree search algorithm. EUROSPEECH V. Ramasubramanian, Kuldip K. Paliwal
1997	J	`jnl`	Voronoi Projection-Based Fast Nearest-Neighbor Search Algorithms: Box-Search and Mapping Table-Based Search Techniques. Digit. Signal Process. V. Ramasubramanian, Kuldip K. Paliwal
1992	J	`jnl`	An efficient approximation-elimination algorithm for fast nearest-neighbour search based on a spherical distance coordinate formulation. Pattern Recognit. Lett. V. Ramasubramanian, Kuldip K. Paliwal
1992	Misc	`conf`	An efficient approximation-elimination algorithm for fast-nearest-neighbour search (speech coding). ICASSP V. Ramasubramanian, Kuldip K. Paliwal
1992	J	`jnl`	Fast K-dimensional tree algorithms for nearest neighbor search with application to vector quantization encoding. IEEE Trans. Signal Process. V. Ramasubramanian, Kuldip K. Paliwal
1989	J	`jnl`	Effect of ordering the codebook on the efficiency of the partial distance search algorithm for vector quantization. IEEE Trans. Commun. Kuldip K. Paliwal, V. Ramasubramanian
1989	—	`conf`	Speech Recognition for Knowledge Based Computer Systems. KBCS P. V. S. Rao, S. Krishnan, Pinaki Poddar, V. Ramasubramanian, K. Samudravijaya, A. Sen