Vladimir Bataev

Orcid: 0009-0005-7845-5042

According to our database1, Vladimir Bataev authored at least 19 papers between 2018 and 2025.

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

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Pushing the Limits of Beam Search Decoding for Transducer-based ASR models.
CoRR, June, 2025

NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding.
CoRR, May, 2025

WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection.
CoRR, May, 2025

RNN-Transducer-based Losses for Speech Recognition on Noisy Targets.
CoRR, April, 2025

HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024
Three-in-One: Fast and Accurate Transducer for Hybrid-Autoregressive ASR.
CoRR, 2024

Label-Looping: Highly Efficient Decoding For Transducers.
Proceedings of the IEEE Spoken Language Technology Workshop, 2024

Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU.
Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter.
Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

2023
NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2023.
Proceedings of the 20th International Conference on Spoken Language Translation, 2023

Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Powerful and Extensible WFST Framework for Rnn-Transducer Losses.
Proceedings of the IEEE International Conference on Acoustics, 2023

2021
Digital Peter: Dataset, Competition and Handwriting Recognition Methods.
CoRR, 2021

Digital Peter: New Dataset, Competition and Handwriting Recognition Methods.
Proceedings of the HIP@ICDAR 2021: The 6th International Workshop on Historical Document Imaging and Processing, 2021

2020
Techniques for Vocabulary Expansion in Hybrid Speech Recognition Systems.
CoRR, 2020

2019
The STC ASR System for the VOiCES from a Distance Challenge 2019.
Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

R-Vectors: New Technique for Adaptation to Room Acoustics.
Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

2018
Exploring End-to-End Techniques for Low-Resource Speech Recognition.
Proceedings of the Speech and Computer - 20th International Conference, 2018


  Loading...