Litcius/Paper detail

Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition

Tsendsuren Munkhdalai, Khe Chai Sim, Angad Chandorkar, Fan Gao, M. Chua, Trevor Strohman, Françoise Beaufays

2022ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)21 citationsDOI

Abstract

Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result. However, the traditional re-scoring approaches based on an external language model is prone to diverge during the personalized training. In this work, we introduce a model-based end-to-end contextual adaptation approach that is decoder-agnostic and amenable to on-device personalization. Our on-device simulation experiments demonstrate that the proposed approach outperforms the traditional re-scoring technique by 12% relative WER and 15.7% entity mention specific F1-score in a continuous personalization scenario.

Topics & Concepts

Computer sciencePersonalizationAdaptation (eye)Associative propertySpeech recognitionLanguage modelArtificial neural networkArtificial intelligenceNatural language processingMachine learningOpticsPhysicsWorld Wide WebPure mathematicsMathematicsSpeech Recognition and SynthesisSpeech and Audio ProcessingSpeech and dialogue systems
Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition | Litcius