activity
20182022
most citedImproving accuracy of rare words for RNN-Transducer through unigram shallow fusion

7 citations · 9 across the 6 of their papers we have counts for

collaborators

11 papers

cs.CL2022

USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder

Bolaji Yusuf, Ankur Gandhe, Alex Sokolov

Improving end-to-end speech recognition by incorporating external text data has been a longstanding research topic. There has been a recent focus on training E2E ASR models that ge…

cs.CL2022

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…

cs.CL2021

Prompt-tuning in ASR systems for efficient domain-adaptation

Saket Dingliwal, Ashish Shenoy, Sravan Bodapati +3

Automatic Speech Recognition (ASR) systems have found their use in numerous industrial applications in very diverse domains. Since domain-specific systems perform better than their…

cs.CL2021

Attention-based Contextual Language Model Adaptation for Speech Recognition

Richard Diehl Martinez, Scott Novotney, Ivan Bulyko +3

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however,…

cs.CL20212 cited

Domain-aware Neural Language Models for Speech Recognition

Linda Liu, Yile Gu, Aditya Gourav +5

As voice assistants become more ubiquitous, they are increasingly expected to support and perform well on a wide variety of use-cases across different domains. We present a domain-…

cs.CL2021

Personalization Strategies for End-to-End Speech Recognition Systems

Aditya Gourav, Linda Liu, Ankur Gandhe +9

The recognition of personalized content, such as contact names, remains a challenging problem for end-to-end speech recognition systems. In this work, we demonstrate how first and…