Sankaran Panchapagesan

TL;DR: It is shown that the combination of 3 techniques LVCSR-initialization, multi-task training and weighted cross-entropy gives the best results, with significantly lower False Alarm Rate than the LV CSR- initialization technique alone, across a wide range of Miss Rates.

TL;DR: This paper proposes to apply singular value decomposition (SVD) to further reduce TDNN complexity, and results show that the full-rank TDNN achieves a 19.7% DET AUC reduction compared to a similar-size deep neural network baseline.

TL;DR: This work proposes a max-pooling based loss function for training Long Short-Term Memory networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements and results show that LSTM models trained using cross-entropy loss or max- Pooling loss outperform a cross-ENTropy loss trained baseline feed-forward Deep Neural Network (DNN).

TL;DR: Two ways to improve deep neural network acoustic models for keyword spotting without increasing CPU usage by using low-rank weight matrices throughout the DNN and knowledge distilled from an ensemble of much larger DNNs used only during training are investigated.

TL;DR: This paper introduces a two-stage wake word system based on Deep Neural Network (DNN) acoustic modeling, proposes a new way to model the non-keyword background events using monophone-based units and presents how richer information can be extracted from those monophone units for final wake word detection.