Rohit Prabhavalkar
23 papers · 2010–2024 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🗺️ Taxonomy Completionist (25) 🏃 Academic Marathon · Half 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(12)
🧬
Topic Evolution
💎
Century Club · Bronze
⚡
Prolific Year · Productive
📈
Trend Setter
🔥
Unstoppable · Bronze
❓
The Questioner
🗃️
Keyword Collector
(91)
🚀
Conference Pioneer
Venues
Top co-authors
Research topics
Speech & Audio
(17)
Recognition
(17)
Machine Learning
(14)
Deep Learning
(11)
Application Areas
(10)
Architectures
(7)
Optimization & Theory · Machine Learning
(5)
Artificial Intelligence
(3)
Learning Types · Machine Learning
(3)
Optimization & Theory · Deep Learning
(3)
Techniques
(3)
Core AI
(2)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Natural Language Processing
(1)
Keywords
automatic speech recognition
(11)
word error rate
(6)
speech recognition
(5)
end-to-end speech recognition
(5)
attention mechanism
(3)
model compression
(3)
connectionist temporal classification
(2)
representation learning
(2)
semi-supervised learning
(2)
on-device speech recognition
(2)
contextual biasing
(2)
sequence-to-sequence model
(2)
recurrent neural network transducer
(2)
collaborative learning
(1)
sequence alignment
(1)
discriminative training
(1)
optimal transport
(1)
cross attention
(1)
cross-modal representation
(1)
gradient clipping
(1)
Papers
Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers
NeurIPS 2024
Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm
Interspeech 2024
Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR
NAACL 2024
Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping
Interspeech 2024
Massive End-to-end Speech Recognition Models with Time Reduction
NAACL 2024
Text Injection for Neural Contextual Biasing
Interspeech 2024
How to Estimate Model Transferability of Pre-Trained Speech Models?
Interspeech 2023
Improving Joint Speech-Text Representations Without Alignment
Interspeech 2023
A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
Interspeech 2022
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
Interspeech 2022
Improving Deliberation by Text-Only and Semi-Supervised Training
Interspeech 2022
Improving Rare Word Recognition with LM-aware MWER Training
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
Anti-Aliasing Regularization in Stacking Layers
Interspeech 2020
On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition
Interspeech 2019
Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models
Interspeech 2019
Two-Pass End-to-End Speech Recognition
Interspeech 2019
Compression of End-to-End Models
Interspeech 2018
A Comparison of Sequence-to-Sequence Models for Speech Recognition
Interspeech 2017
An Analysis of “Attention” in Sequence-to-Sequence Models
Interspeech 2017
On the Efficient Representation and Execution of Deep Acoustic Models
Interspeech 2016
Investigations into the Crandem Approach to Word Recognition
NAACL 2010