- Read more about Poster for ICASSP 2024 paper "Hot-Fixing Wake Work Recognition for End-to-End ASR via Neural Model Reprogramming"
- Log in to post comments
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.
- Categories:
17 Views