[PDF][PDF] Recent advances in end-to-end automatic speech recognition

J Li - APSIPA Transactions on Signal and Information …, 2022 - nowpublishers.com
Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

End-to-end speech recognition: A survey

R Prabhavalkar, T Hori, TN Sainath… - … on Audio, Speech …, 2023 - ieeexplore.ieee.org
In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …

Context-aware transformer transducer for speech recognition

FJ Chang, J Liu, M Radfar, A Mouchtaris… - 2021 IEEE automatic …, 2021 - ieeexplore.ieee.org
End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty
recognizing uncommon words, that appear infrequently in the training data. One promising …

Contextual adapters for personalized speech recognition in neural transducers

KM Sathyendra, T Muniyappa, FJ Chang… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR)
models is a challenge due to the lack of training data. A standard way to address this issue …

Contextual RNN-T for open domain ASR

M Jain, G Keren, J Mahadeokar, G Zweig… - ar** for contextual biasing in end-to-end ASR
R Huang, O Abdel-Hamid, X Li, G Evermann - arxiv preprint arxiv …, 2020 - arxiv.org
In recent years, all-neural, end-to-end (E2E) ASR systems gained rapid interest in the
speech recognition community. They convert speech input to text units in a single trainable …