Kushal Lakhotia
10 papers · 2021–2022 · 5 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 ↓+3 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (24) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 👥 Mega-Team · Squad
⚡
Prolific Year · Productive
❓
The Questioner
💎
Century Club · Bronze
Top co-authors
Research topics
Deep Learning
(8)
Machine Learning
(8)
Learning Types · Machine Learning
(6)
Artificial Intelligence
(5)
Natural Language Processing
(4)
Architectures
(4)
Core AI
(4)
Speech & Audio
(3)
Applications
(3)
Learning Types · Deep Learning
(3)
Models
(3)
Application Areas
(2)
Core Methods
(2)
Generation
(2)
Techniques
(2)
Keywords
self-supervised learning
(5)
representation learning
(3)
transfer learning
(2)
dense retrieval
(2)
speech processing
(2)
question answering
(2)
speech resynthesis
(2)
speech recognition
(2)
passage retrieval
(1)
domain adaptation
(1)
imitation learning
(1)
multimodal learning
(1)
audio-visual speech
(1)
speech synthesis
(1)
disentangled representation
(1)
generative model
(1)
language model
(1)
masked prediction
(1)
fact verification
(1)
domain generalization
(1)
Papers
Domain-matched Pre-training Tasks for Dense Retrieval
NAACL 2022
Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction
ICLR 2022
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
EMNLP 2022
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
ACL 2022
Text-Free Prosody-Aware Generative Spoken Language Modeling
ACL 2022
textless-lib: a Library for Textless Spoken Language Processing
NAACL 2022
XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
Interspeech 2022
FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation
EMNLP 2021
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Interspeech 2021
SUPERB: Speech Processing Universal PERformance Benchmark
Interspeech 2021