2020/08/05 by Adya, Saurabh, Garg, Vineet, Sigtia, Siddharth +2
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG) #Sound (cs.SD) #electronic engineering #information engineering
paper · doi:10.48550/arxiv.2008.02323
We consider the design of two-pass voice trigger detection systems. We focus on the networks in the second pass that are used to re-score candidate segments obtained from the first-pass. Our baseline is an acoustic model(AM), with BiLSTM layers, trained by minimizing the CTC loss. We replace the BiLSTM layers with self-attention layers. Results on internal evaluation sets show that self-attention networks yield better accuracy while requiring fewer parameters. We add an auto-regressive decoder network on top of the self-attention layers and jointly minimize the CTC loss on the encoder and the cross-entropy loss on the decoder. This design yields further improvements over the baseline. We retrain all the models above in a multi-task learning(MTL) setting, where one branch of a shared network is trained as an AM, while the second branch classifies the whole sequence to be true-trigger or not. Results demonstrate that networks with self-attention layers yield ∼60% relative reduction in false reject rates for a given false-alarm rate, while requiring 10% fewer parameters. When trained in the MTL setup, self-attention networks yield further accuracy improvements. On-device measurements show that we observe 70% relative reduction in inference time. Additionally, the proposed network architectures are ∼5X faster to train.