Jan Chorowski
9 papers · 2017–2023 · 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Gold 🗺️ Taxonomy Completionist (20) 🐣 Hot Topic Early Bird
🌈
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Machine Learning
(5)
Deep Learning
(4)
Speech & Audio
(4)
Natural Language Processing
(3)
Architectures
(3)
Learning Types
(3)
Artificial Intelligence
(2)
Analysis
(2)
Applications · Natural Language Processing
(2)
Core AI
(2)
Recognition
(2)
Computer Science
(1)
Interdisciplinary
(1)
Application Areas
(1)
Applications · Computer Science
(1)
Keywords
sequence-to-sequence model
(2)
speech representation
(2)
word error rate
(2)
unsupervised learning
(2)
speech recognition
(2)
contrastive predictive coding
(2)
self-supervised learning
(1)
k-means clustering
(1)
representation learning
(1)
autoregressive generation
(1)
speaker recognition
(1)
acoustic modeling
(1)
linear methods
(1)
connectionist temporal classification
(1)
information retrieval
(1)
variational inference
(1)
probabilistic model
(1)
text modeling
(1)
state space model
(1)
acoustic model
(1)
Papers
Efficient Transformers with Dynamic Token Pooling
ACL 2023
Aligned Contrastive Predictive Coding
Interspeech 2021
Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw
Interspeech 2021
A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning
Interspeech 2020
Lattice Generation in Attention-Based Speech Recognition Models
Interspeech 2019
Towards Using Context-Dependent Symbols in CTC Without State-Tying Decision Trees
Interspeech 2019
Input Switched Affine Networks: An RNN Architecture Designed for Interpretability
ICML 2017
Sequence-to-Sequence Models Can Directly Translate Foreign Speech
Interspeech 2017
Towards Better Decoding and Language Model Integration in Sequence to Sequence Models
Interspeech 2017