Attention-based Contextual Language Model Adaptation for Speech Recognition

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance was spoken, provides a rich input signal. We introduce an att...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Richard Diehl Martinez, Novotney, Scott, Bulyko, Ivan, Rastrow, Ariya, Stolcke, Andreas, Gandhe, Ankur
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 02.06.2021
Subjects
Automatic speech recognition
Datasets
Voice recognition
Online AccessGet full text

Cover

More Information
Summary:Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance was spoken, provides a rich input signal. We introduce an attention mechanism for training neural speech recognition language models on both text and non-linguistic contextual data. When applied to a large de-identified dataset of utterances collected by a popular voice assistant platform, our method reduces perplexity by 7.0% relative over a standard LM that does not incorporate contextual information. When evaluated on utterances extracted from the long tail of the dataset, our method improves perplexity by 9.0% relative over a standard LM and by over 2.8% relative when compared to a state-of-the-art model for contextual LM.
ISSN:2331-8422