Frank Zhang

Affiliations:
  • Facebook AI, USA


According to our database1, Frank Zhang authored at least 20 papers between 2019 and 2021.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2021
Scaling ASR Improves Zero and Few Shot Learning.
CoRR, 2021

Improved Language Identification Through Cross-Lingual Self-Supervised Learning.
CoRR, 2021

Benchmarking LF-MMI, CTC And RNN-T Criteria For Streaming ASR.
Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Streaming Attention-Based Models with Augmented Memory for End-To-End Speech Recognition.
Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Improving RNN Transducer Based ASR with Auxiliary Tasks.
Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Transformer in Action: A Comparative Study of Transformer-Based Acoustic Models for Large Scale Speech Recognition Applications.
Proceedings of the IEEE International Conference on Acoustics, 2021

Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2021

On Lattice-Free Boosted MMI Training of HMM and CTC-Based Full-Context ASR Models.
Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

2020
Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition.
CoRR, 2020

Fast, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces.
CoRR, 2020

Multilingual Graphemic Hybrid ASR with Massive Data Augmentation.
Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages and Collaboration and Computing for Under-Resourced Languages, 2020

Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces.
Proceedings of the Interspeech 2020, 2020

Streaming Transformer-Based Acoustic Models Using Self-Attention with Augmented Memory.
Proceedings of the Interspeech 2020, 2020

Weak-Attention Suppression for Transformer Based Speech Recognition.
Proceedings of the Interspeech 2020, 2020

Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model.
Proceedings of the Interspeech 2020, 2020

Transformer-Based Acoustic Modeling for Hybrid Speech Recognition.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

DEJA-VU: Double Feature Presentation and Iterated Loss in Deep Transformer Networks.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Training ASR Models By Generation of Contextual Information.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
Deja-vu: Double Feature Presentation in Deep Transformer Networks.
CoRR, 2019

Multilingual ASR with Massive Data Augmentation.
CoRR, 2019


  Loading...