Picture for Jiedan Zhu

Jiedan Zhu

Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition

Add code
Oct 31, 2022
Viaarxiv icon

Dynamic Speech Endpoint Detection with Regression Targets

Add code
Oct 25, 2022
Viaarxiv icon

Streaming parallel transducer beam search with fast-slow cascaded encoders

Add code
Mar 29, 2022
Figure 1 for Streaming parallel transducer beam search with fast-slow cascaded encoders
Figure 2 for Streaming parallel transducer beam search with fast-slow cascaded encoders
Figure 3 for Streaming parallel transducer beam search with fast-slow cascaded encoders
Figure 4 for Streaming parallel transducer beam search with fast-slow cascaded encoders
Viaarxiv icon

Efficient Dynamic WFST Decoding for Personalized Language Models

Add code
Oct 23, 2019
Figure 1 for Efficient Dynamic WFST Decoding for Personalized Language Models
Figure 2 for Efficient Dynamic WFST Decoding for Personalized Language Models
Figure 3 for Efficient Dynamic WFST Decoding for Personalized Language Models
Figure 4 for Efficient Dynamic WFST Decoding for Personalized Language Models
Viaarxiv icon