Sorry, you need to enable JavaScript to visit this website.

Poster for ICASSP 2024 paper "Hot-Fixing Wake Work Recognition for End-to-End ASR via Neural Model Reprogramming"

Citation Author(s):
Submitted by:
I-Fan Chen
Last updated:
15 April 2024 - 10:35pm
Document Type:
Document Year:
I-Fan Chen
Paper Code:

This paper proposes two novel variants of neural reprogramming to enhance wake word recognition in streaming end-to-end ASR models without updating model weights. The first, "trigger-frame reprogramming", prepends the input speech feature sequence with the learned trigger-frames of the target wake word to adjust ASR model’s hidden states for improved wake word recognition. The second, "predictor-state initialization", trains only the initial state vectors (cell and hidden states) of the LSTMs in the prediction network. When applying to a baseline LibriSpeech Emformer RNN-T model with a 98% wake word verification false rejection rate (FRR) on unseen wake words, the proposed approaches achieve 76% and 97% relative FRR reductions with no increase on false acceptance rate. In-depth characteristic analyses of the proposed approaches are also conducted to provide deeper insights. These approaches offer an effective hot-fixing methods to improve wake word recognition performance in deployed production ASR models without the need for model updates.

0 users have voted: