Ehsan Variani
11 papers · 2016–2022 · 2 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (17)
π§
Keyword Pioneer
π
Keyword Champion
π₯
Mega-Team Β· Squad
π
Century Club Β· Bronze
π
Conference Pioneer
Venues
Top co-authors
Research topics
Keywords
automatic speech recognition
(6)
speech recognition
(5)
acoustic model
(4)
language model
(4)
word error rate
(2)
hybrid autoregressive transducer
(2)
neural network
(2)
feature extraction
(2)
acoustic modeling
(2)
speech enhancement
(1)
deep neural network
(1)
recurrent neural network
(1)
computational complexity
(1)
weight interpolation
(1)
label bia
(1)
neural network model
(1)
on-device inference
(1)
simulated data
(1)
beam search
(1)
end-to-end training
(1)
Papers
Global Normalization for Streaming Speech Recognition in a Modular Framework
NeurIPS 2022
Improving Rare Word Recognition with LM-aware MWER Training
Interspeech 2022
On Adaptive Weight Interpolation of the Hybrid Autoregressive Transducer
Interspeech 2022
UserLibri: A Dataset for ASR Personalization Using Only Text
Interspeech 2022
A Hybrid Seq-2-Seq ASR Design for On-Device and Server Applications
Interspeech 2021
An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling
Interspeech 2021
Efficient Implementation of the Room Simulator for Training Deep Neural Network Acoustic Models
Interspeech 2018
Acoustic Modeling for Google Home
Interspeech 2017
End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow
Interspeech 2017
Complex Linear Projection (CLP): A Discriminative Approach to Joint Feature Extraction and Acoustic Modeling
Interspeech 2016
Reducing the Computational Complexity of Multimicrophone Acoustic Models with Integrated Feature Extraction
Interspeech 2016