2020/07/17 by Xiaosu Tong, Che-Wei Huang, Tong, Xiaosu +13
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2007.09245
arxiv created 2020/07/17 · openalex publication_date 2020/07/17 · arxiv updated 2020/07/21 · openalex created_date 2020/07/23 · openalex updated_date 2026/07/28
In this paper, we propose a streaming model to distinguish voice queries intended for a smart-home device from background speech. The proposed model consists of multiple CNN layers with residual connections, followed by a stacked LSTM architecture. The streaming capability is achieved by using unidirectional LSTM layers and a causal mean aggregation layer to form the final utterance-level prediction up to the current frame. In order to avoid redundant computation during online streaming inference, we use a caching mechanism for every convolution operation. Experimental results on a device-directed vs. non device-directed task show that the proposed model yields an equal error rate reduction of 41% compared to our previous best model on this task. Furthermore, we show that the proposed model is able to accurately predict earlier in time compared to the attention-based models.