Viswanathan Ramasubramanian
Research Subjects
Viswanathan Ramasubramanian has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
K.K. Paliwal
6 shared publicationsA. Sricharan
PES Institute of Technology - Bangalore South Campus (PESIT-BSC), Bangalore, 560100, India
5 shared publicationsMythri Thippareddy
PES Institute of Technology - Bangalore South Campus (PESIT-BSC), Bangalore, 560100, India
5 shared publications- Krothapalli Sreenivasa Rao
ICFAI Foundation for Higher Education
4 shared publications - Vandana M. Ladwani
PES University
4 shared publications D. N. Krishna
PES Institute of Technology - Bangalore South Campus (PESIT-BSC), Bangalore, India
3 shared publications
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 2368-2384
Few-Shot Learning Model With Small Scale Pre-Training for Cross-Lingual E2E ASR
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 2368-2384
Few-Shot Learning Model With Small Scale Pre-Training for Cross-Lingual E2E ASR
- Open Access
- 28 November 2025
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2025 (1) , 41
Accent-robust speech recognition for English in low-resource settings using Manifold Mixup
- 28 November 2025
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2025 (1) , 41
Open AccessAccent-robust speech recognition for English in low-resource settings using Manifold Mixup
- 22 June 2025
- Published by Springer Nature
- p. 43-56
Clustering by Limit-Cycles in Hopfield Neural Network
- 22 June 2025
- Published by Springer Nature
- p. 43-56
Clustering by Limit-Cycles in Hopfield Neural Network
- 22 September 2023
- Published by Springer Nature
- p. 255-268
Connectionist Temporal Sequence Decoding: M-ary Hopfield Neural-Network with Multi-limit Cycle Formulation
- 22 September 2023
- Published by Springer Nature
- p. 255-268
Connectionist Temporal Sequence Decoding: M-ary Hopfield Neural-Network with Multi-limit Cycle Formulation
- 15 December 2022
- Published by Springer Nature
- p. 13-23
Harnessing Energy of M-ary Hopfield Neural Network for Connectionist Temporal Sequence Decoding
- 15 December 2022
- Published by Springer Nature
- p. 13-23
Harnessing Energy of M-ary Hopfield Neural Network for Connectionist Temporal Sequence Decoding
- Open Access
- 21 October 2021
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Few shot learning for cross-lingual isolated word recognition
We address the problem of low resource machine learning in the form of few-shot learning (FSL) applied to word recognition in both mono-lingual and cross-lingual settings. Recently, we proposed an adaptation of a FSL framework, matching networks (MN) to a suite of speech recognition tasks such as multi-speaker small-to-medium vocabulary word recognition and frame-wise phoneme recognition tasks under mel-spectrogram and single-frame feature representations. In this paper, we extend this FSL adaptation of MN to multi-speaker isolated word recognition (IWR), in a framework termed MN-IWR. The IWR task is specifically set in a ‘command-and-control’ (C&C) scenario with the requirement of needing only very few-shot examples (e.g. up to 20) for a target IWR classification task with vocabularies defined dynamically. Moreover, our proposed MN-IWR framework addresses a cross-domain and cross-lingual setting defined as below: a model is trained on a possibly large set of words in a source-language and used for inference on a cross-domain task (vocabulary of words different from the training vocabulary) or a cross-lingual task (vocabulary of words from a target-language different from the source-language). In this work, we present the main formulation of the MN-IWR framework, its adaptation from source-to-target tasks and results on TIMIT vocabulary of words in a mono-lingual setting and on English, Kannada and Tamil words in cross-lingual settings and report very high performances of the proposed MN-IWR FSL paradigm over conventional IWR classification without the FSL advantage of the MN formulation.
- 21 October 2021
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessFew shot learning for cross-lingual isolated word recognition
We address the problem of low resource machine learning in the form of few-shot learning (FSL) applied to word recognition in both mono-lingual and cross-lingual settings. Recently, we proposed an adaptation of a FSL framework, matching networks (MN) to a suite of speech recognition tasks such as multi-speaker small-to-medium vocabulary word recognition and frame-wise phoneme recognition tasks under mel-spectrogram and single-frame feature representations. In this paper, we extend this FSL adaptation of MN to multi-speaker isolated word recognition (IWR), in a framework termed MN-IWR. The IWR task is specifically set in a ‘command-and-control’ (C&C) scenario with the requirement of needing only very few-shot examples (e.g. up to 20) for a target IWR classification task with vocabularies defined dynamically. Moreover, our proposed MN-IWR framework addresses a cross-domain and cross-lingual setting defined as below: a model is trained on a possibly large set of words in a source-language and used for inference on a cross-domain task (vocabulary of words different from the training vocabulary) or a cross-lingual task (vocabulary of words from a target-language different from the source-language). In this work, we present the main formulation of the MN-IWR framework, its adaptation from source-to-target tasks and results on TIMIT vocabulary of words in a mono-lingual setting and on English, Kannada and Tamil words in cross-lingual settings and report very high performances of the proposed MN-IWR FSL paradigm over conventional IWR classification without the FSL advantage of the MN formulation.
- 7 September 2021
- Published by Springer Nature
- p. 420-432
M-ary Hopfield Neural Network Based Associative Memory Formulation: Limit-Cycle Based Sequence Storage and Retrieval
- 7 September 2021
- Published by Springer Nature
- p. 420-432
M-ary Hopfield Neural Network Based Associative Memory Formulation: Limit-Cycle Based Sequence Storage and Retrieval
- 30 July 2020
- Published by Springer Nature in Sādhanā
- Vol. 45 (1) , 1-14
Articulatory-feature-based methods for performance improvement of Multilingual Phone Recognition Systems using Indian languages
- 30 July 2020
- Published by Springer Nature in Sādhanā
- Vol. 45 (1) , 1-14
Articulatory-feature-based methods for performance improvement of Multilingual Phone Recognition Systems using Indian languages
- 9 September 2019
- Published by Springer Nature
- p. 57-75
Multi-modal Associative Storage and Retrieval Using Hopfield Auto-associative Memory Network
- 9 September 2019
- Published by Springer Nature
- p. 57-75
Multi-modal Associative Storage and Retrieval Using Hopfield Auto-associative Memory Network