Picture for Vladimir Bataev

Vladimir Bataev

Three-in-One: Fast and Accurate Transducer for Hybrid-Autoregressive ASR

Add code
Oct 03, 2024
Viaarxiv icon

Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter

Add code
Jun 11, 2024
Viaarxiv icon

Label-Looping: Highly Efficient Decoding for Transducers

Add code
Jun 10, 2024
Viaarxiv icon

Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU

Add code
Jun 06, 2024
Viaarxiv icon

Powerful and Extensible WFST Framework for RNN-Transducer Losses

Add code
Mar 18, 2023
Viaarxiv icon

Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator

Add code
Feb 27, 2023
Viaarxiv icon

Digital Peter: Dataset, Competition and Handwriting Recognition Methods

Add code
Mar 16, 2021
Figure 1 for Digital Peter: Dataset, Competition and Handwriting Recognition Methods
Figure 2 for Digital Peter: Dataset, Competition and Handwriting Recognition Methods
Figure 3 for Digital Peter: Dataset, Competition and Handwriting Recognition Methods
Figure 4 for Digital Peter: Dataset, Competition and Handwriting Recognition Methods
Viaarxiv icon

Techniques for Vocabulary Expansion in Hybrid Speech Recognition Systems

Add code
Mar 19, 2020
Figure 1 for Techniques for Vocabulary Expansion in Hybrid Speech Recognition Systems
Figure 2 for Techniques for Vocabulary Expansion in Hybrid Speech Recognition Systems
Viaarxiv icon

Exploring End-to-End Techniques for Low-Resource Speech Recognition

Add code
Jul 02, 2018
Figure 1 for Exploring End-to-End Techniques for Low-Resource Speech Recognition
Figure 2 for Exploring End-to-End Techniques for Low-Resource Speech Recognition
Figure 3 for Exploring End-to-End Techniques for Low-Resource Speech Recognition
Figure 4 for Exploring End-to-End Techniques for Low-Resource Speech Recognition
Viaarxiv icon