Jay Mahadeokar

According to our database1, Jay Mahadeokar authored at least 43 papers between 2012 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Efficient Streaming LLM for Speech Recognition.
CoRR, 2024

Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech.
CoRR, 2024

M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses.
CoRR, 2024

Faster Speech-LLaMA Inference with Multi-token Prediction.
CoRR, 2024

The Llama 3 Herd of Models.
, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
et al.
CoRR, 2024

Towards scalable efficient on-device ASR with transfer learning.
CoRR, 2024

AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of a Multilingual ASR Model.
Proceedings of the IEEE International Conference on Acoustics, 2024

TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-Device ASR Models.
Proceedings of the IEEE International Conference on Acoustics, 2024

Effective Internal Language Model Training and Fusion for Factorized Transducer Model.
Proceedings of the IEEE International Conference on Acoustics, 2024

Prompting Large Language Models with Speech Recognition Abilities.
Proceedings of the IEEE International Conference on Acoustics, 2024

2023
Towards General-Purpose Speech Abilities for Large Language Models Using Unpaired Data.
CoRR, 2023

Towards Selection of Text-to-speech Data to Augment ASR Training.
CoRR, 2023

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Multi-Head State Space Model for Speech Recognition.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Anchored Speech Recognition with Neural Transducers.
Proceedings of the IEEE International Conference on Acoustics, 2023

Dynamic Speech Endpoint Detection with Regression Targets.
Proceedings of the IEEE International Conference on Acoustics, 2023

Improving fast-slow Encoder based Transducer with Streaming Deliberation.
Proceedings of the IEEE International Conference on Acoustics, 2023

Joint Federated Learning and Personalization for on-Device ASR.
Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022
An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition.
Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Streaming parallel transducer beam search with fast slow cascaded encoders.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Federated Domain Adaptation for ASR with Full Self-Supervision.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Streaming Transformer Transducer based Speech Recognition Using Non-Causal Convolution.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
TorchAudio: Building Blocks for Audio and Speech Processing.
CoRR, 2021

Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios.
CoRR, 2021

Alignment Restricted Streaming Recurrent Neural Network Transducer.
Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Deep Shallow Fusion for RNN-T Personalization.
Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Dissecting User-Perceived Latency of On-Device E2E Speech Recognition.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Memory-Efficient Speech Recognition on Smart Devices.
Proceedings of the IEEE International Conference on Acoustics, 2021

Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer.
Proceedings of the IEEE International Conference on Acoustics, 2021

2020
Contextual RNN-T For Open Domain ASR.
CoRR, 2020

Contextual RNN-T for Open Domain ASR.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Transformer-Based Acoustic Modeling for Hybrid Speech Recognition.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Spatial Attention for Far-Field Speech Recognition with Deep Beamforming Neural Networks.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
RNN-T For Latency Controlled ASR With Improved Beam Search.
CoRR, 2019

Transformer-Transducer: End-to-End Speech Recognition with Self-Attention.
CoRR, 2019

2014
Faster algorithm to find anti-risk path between two nodes of an undirected graph.
J. Comb. Optim., 2014

Short-text representation using diffusion wavelets.
Proceedings of the 23rd International World Wide Web Conference, 2014

2013
Faster replacement paths algorithms in case of edge or node failure for undirected, positive integer weighted graphs.
J. Discrete Algorithms, 2013

2012
Faster Replacement Paths Algorithm for Undirected, Positive Integer Weighted Graphs with Small Diameter.
Proceedings of the Combinatorial Algorithms, 23rd International Workshop, 2012


  Loading...