Correction Focused Language Model Training For Speech Recognition
Language models (LMs) have been commonly adopted to boost the performance of
automatic speech recognition (ASR) particularly in domain adaptation tasks. Conventional …
automatic speech recognition (ASR) particularly in domain adaptation tasks. Conventional …
Towards A World-English Language Model for on-Device Virtual Assistants
R Jalota, L Verwimp… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
Neural Network Language Models (NNLMs) for Virtual Assistants (VAs) are generally
language-, region-, and in some cases, device-dependent, which increases the effort to …
language-, region-, and in some cases, device-dependent, which increases the effort to …