Ashtosh Sapru
4 papers · 2019–2022 · 1 venue · 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 ↓
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
Venues
Research topics
Keywords
speech recognition
(3)
acoustic modeling
(2)
long short-term memory
(2)
semi-supervised learning
(2)
data augmentation
(1)
neural network optimization
(1)
speaker embedding
(1)
label smoothing
(1)
model averaging
(1)
deep neural network
(1)
consistency regularization
(1)
word error rate
(1)
end-to-end speech recognition
(1)
dialect recognition
(1)
voice assistant
(1)
sequence discriminative training
(1)
multi-dialect speech recognition
(1)
wake word detection
(1)
phone mapping
(1)
iver vector
(1)
Papers
Using Data Augmentation and Consistency Regularization to Improve Semi-supervised Speech Recognition
Interspeech 2022
Improved Training Strategies for End-to-End Speech Recognition in Digital Voice Assistants
Interspeech 2020
Leveraging Unlabeled Speech for Sequence Discriminative Training of Acoustic Models
Interspeech 2020
Multi-Dialect Acoustic Modeling Using Phone Mapping and Online i-Vectors
Interspeech 2019