53 citations · 115 across the 24 of their papers we have counts for
3 papers · 1 filter
RescoreBERT: Discriminative Speech Recognition Rescoring with BERT
Liyan Xu, Yile Gu, Jari Kolehmainen +5
Second-pass rescoring is an important component in automatic speech recognition (ASR) systems that is used to improve the outputs from a first-pass decoder by implementing a lattic…
Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition
Chao-Han Huck Yang, Zeeshan Ahmed, Yile Gu +5
In this work, we aim to enhance the system robustness of end-to-end automatic speech recognition (ASR) against adversarially-noisy speech examples. We focus on a rigorous and empir…
A Likelihood Ratio based Domain Adaptation Method for E2E Models
Chhavi Choudhury, Ankur Gandhe, Xiaohan Ding +1
End-to-end (E2E) automatic speech recognition models like Recurrent Neural Networks Transducer (RNN-T) are becoming a popular choice for streaming ASR applications like voice assis…