Jay Mahadeokar
10 papers · 2020–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (19) π£ Hot Topic Early Bird π Conference Polyglot (3)
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(5)
π
Century Club
(10)
π₯
Unstoppable
(5)
Conferences
INTERSPEECH (8)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
word error rate
(5)
automatic speech recognition
(4)
on-device speech recognition
(3)
speech recognition
(2)
latency optimization
(2)
speech processing
(1)
state space model
(1)
domain adaptation
(1)
collaborative learning
(1)
flow matching
(1)
in-context learning
(1)
language model
(1)
beam search
(1)
multi-head attention
(1)
dialogue system
(1)
transformer encoder
(1)
cross-modal learning
(1)
named entity
(1)
multilingual speech
(1)
attention mechanism
(1)
Papers
AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs
NAACL 2024
Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
NIPS 2023
Multi-Head State Space Model for Speech Recognition
INTERSPEECH 2023
Federated Domain Adaptation for ASR with Full Self-Supervision
INTERSPEECH 2022
Streaming parallel transducer beam search with fast slow cascaded encoders
INTERSPEECH 2022
Dissecting User-Perceived Latency of On-Device E2E Speech Recognition
INTERSPEECH 2021
Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency
INTERSPEECH 2021
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
INTERSPEECH 2021
Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios
INTERSPEECH 2021
Contextual RNN-T for Open Domain ASR
INTERSPEECH 2020