V Ramasubramanian

About V Ramasubramanian

V Ramasubramanian, With an exceptional h-index of 16 and a recent h-index of 7 (since 2020), a distinguished researcher at International Institute of Information Technology Bangalore, specializes in the field of Speech recognition, Machine learning, Deep learning.

His recent articles reflect a diverse array of research interests and contributions to the field:

Connectionist Temporal Sequence Decoding: M-ary Hopfield Neural-Network with Multi-limit Cycle Formulation

Correction: Trainable windows for SincNet architecture.

Trainable windows for SincNet architecture

M-ary hopfield neural network for storage and retrieval of variable length sequences: multi-limit cycle approach

Few-shot learning for E2E speech recognition: architectural variants for support set generation

Few-shot learning for cross-lingual end-to-end speech recognition

Few-shot learning for frame-wise phoneme recognition: Adaptation of matching networks

End-to-end speech recognition from raw speech: Multi time-frequency resolution CNN architecture for efficient representation learning

V Ramasubramanian Information

University

Position

Professor International Institute of Information Technology Bangalore ()

Citations(all)

1094

Citations(since 2020)

188

Cited By

926

hIndex(all)

16

hIndex(since 2020)

7

i10Index(all)

25

i10Index(since 2020)

4

Email

University Profile Page

International Institute of Information Technology Bangalore

Google Scholar

View Google Scholar Profile

V Ramasubramanian Skills & Research Interests

Speech recognition

Machine learning

Deep learning

Top articles of V Ramasubramanian

Title

Journal

Author(s)

Publication Date

Connectionist Temporal Sequence Decoding: M-ary Hopfield Neural-Network with Multi-limit Cycle Formulation

Vandana M Ladwani

V Ramasubramanian

2023/9/22

Correction: Trainable windows for SincNet architecture.

EURASIP J. Audio Speech Music. Process.

HC Prashanth

Madhav Rao

Dhanya Eledath

V Ramasubramanian

2023/12/1

Trainable windows for SincNet architecture

EURASIP Journal on Audio, Speech, and Music Processing

Prashanth HC

Madhav Rao

Dhanya Eledath

Ramasubramanian V

2023/1/19

M-ary hopfield neural network for storage and retrieval of variable length sequences: multi-limit cycle approach

Vandana M Ladwani

V Ramasubramanian

2022/12/4

Few-shot learning for E2E speech recognition: architectural variants for support set generation

Dhanya Eledath

Narasimha Rao Thurlapati

V Pavithra

Tirthankar Banerjee

V Ramasubramanian

2022/8/29

Few-shot learning for cross-lingual end-to-end speech recognition

Dhanya Eledath

V Pavithra

Narasimha Rao Thurlapati

Tirthankar Banerjee

V Ramasubramanian

2021/9

Few-shot learning for frame-wise phoneme recognition: Adaptation of matching networks

Tirthankar Banerjee

Narasimha Rao Thurlapati

V Pavithra

S Mahalakshmi

Dhanya Eledath

...

2021/8/23

End-to-end speech recognition from raw speech: Multi time-frequency resolution CNN architecture for efficient representation learning

Dhanya Eledath

P Inbarajan

Anurag Biradar

Sathwick Mahadeva

V Ramasubramanian

2021/8/23

Harnessing Energy of M-ary Hopfield Neural Network for Connectionist Temporal Sequence Decoding

Vandana M Ladwani

V Ramasubramanian

2021/11/1

Approaches for multilingual phone recognition in code-switched and non-code-switched scenarios using Indian languages

ACM TRANSACTIONS on Asian and low-resource language information processing

KE Manjunath

Srinivasa KM Raghavan

K Sreenivasa Rao

Dinesh Babu Jayagopi

V Ramasubramanian

2021/7/1

Few shot learning for cross-lingual isolated word recognition

Tirthankar Banerjee

Dhanya Eledath

V Ramasubramanian

2021/10/21

M-ary hopfield neural network based associative memory formulation: Limit-cycle based sequence storage and retrieval

Vandana M Ladwani

V Ramasubramanian

2021

Component-specific temporal decomposition: application to enhanced speech coding and co-articulation analysis

Tilak Purohit

V Ramasubramanian

2020/7/19

Articulatory-feature-based methods for performance improvement of Multilingual Phone Recognition Systems using Indian languages

Sādhanā

KE Manjunath

Dinesh Babu Jayagopi

K Sreenivasa Rao

V Ramasubramanian

2020/12

Raw speech speaker-recognition

2020/7/7

Semi-supervised learning for acoustic model retraining: Handling speech data with noisy transcript

Abhijith Madan

Ayush Khopkar

Shreekantha Nadig

KM Srinivasa Raghavan

Dhanya Eledath

...

2020/7/19

Multilingual phone recognition: comparison of traditional versus common multilingual phone-set approaches and applications in code-switching

KE Manjunath

KM Srinivasa Raghavan

K Sreenivasa Rao

Dinesh Babu Jayagopi

V Ramasubramanian

2020

Jointly learning to align and transcribe using attention-based alignment and uncertainty-to-weigh losses

Shreekantha Nadig

Sumit Chakraborty

Anuj Shah

Chaitanay Sharma

V Ramasubramanian

...

2020/7/19

Multi-target hybrid CTC-Attentional Decoder for joint phoneme-grapheme recognition

Shreekantha Nadig

V Ramasubramanian

Sachit Rao

2020/7/19

End-to-end audio-scene classification from raw audio: Multi time-frequency resolution CNN architecture for efficient representation learning

T Vijaya Kumar

R Shunmuga Sundar

Tilak Purohit

V Ramasubramanian

2020/7/19

See List of Professors in V Ramasubramanian University(International Institute of Information Technology Bangalore)

Co-Authors

H-index: 39
Krothapalli Sreenivasa Rao

Krothapalli Sreenivasa Rao

Indian Institute of Technology Kharagpur

H-index: 19
Dinesh Babu Jayagopi

Dinesh Babu Jayagopi

International Institute of Information Technology Bangalore

H-index: 6
Harish Doddala

Harish Doddala

Massachusetts Institute of Technology

H-index: 4
Vaishnavi Yeruva

Vaishnavi Yeruva

North Western University

academic-engine