Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition
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 continues personalization scenario.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderLanguage ModelingLanguage Modellingspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation
Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memory-based or in-context learning. We propose FAAST, a forward-only assoc…
Image ClassificationFast Weight Long Short-Term Memory
Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs). As recent studies introduced fast weights only to…
RetrievalBrain-like associative learning using a nanoscale non-volatile phase change synaptic device array
Recent advances in neuroscience together with nanoscale electronic device technology have resulted in huge interests in realizing brain-like computing hardwares using emerging nanoscale memory devices as synaptic element…
Learning Associative Inference Using Fast Weight Memory
Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. To this end, we a…
Language ModellingMeta Reinforcement LearningQuestion Answeringreinforcement-learning+1GATED FAST WEIGHTS FOR ASSOCIATIVE RETRIEVAL
We improve previous end-to-end differentiable neural networks (NNs) with fast weight memories. A gate mechanism updates fast weights at every time step of a sequence through two separate outer-product-based matrices gene…
Retrieval