Search Results for author:
Found 7 papers, 0 papers with code
Synthetic Cross-accent Data Augmentation for Automatic Speech Recognition
In this work, we improve an accent-conversion model (ACM) which transforms native US-English speech into accented pronunciation.
Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
In this work, we present our Joint Audio/Text training method for Transformer Rescorer, to leverage unpaired text-only data which is relatively cheaper than paired audio-text data.
Named Entity Detection and Injection for Direct Speech Translation
In a sentence, certain words are critical for its semantic.
Integrating Categorical Features in End-to-End ASR
To be able to leverage data from existing domains is important for ASR accuracy in the new domain.
Class LM and word mapping for contextual biasing in End-to-End ASR
In ASR, many utterances contain rich named entities.
Network-Scale Traffic Modeling and Forecasting with Graphical Lasso and Neural Networks
In this paper, we apply GPR to traffic flow forecasting and show its potential.
Kernel Regression with Sparse Metric Learning
Generally, the function value for a test input is estimated by a weighted average of the surrounding training examples.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
