M
Mike Rodehorst
Publications - 3
Citations - 136
Mike Rodehorst is an academic researcher. The author has contributed to research in topics: Time delay neural network & Keyword spotting. The author has an hindex of 3, co-authored 3 publications receiving 89 citations.
Papers
More filters
Proceedings ArticleDOI
Compressed Time Delay Neural Network for Small-Footprint Keyword Spotting.
Ming Sun,David Snyder,Yixin Gao,Varun K. Nagaraja,Mike Rodehorst,Sankaran Panchapagesan,Nikko Strom,Spyros Matsoukas,Shiv Naga Prasad Vitaladevuni +8 more
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.
Proceedings ArticleDOI
Building a robust word-level wakeword verification network
TL;DR: This work proposes to use a large receptive field (LRF) word-level wakeword model, and in particular, a convolutional-recurrent-attention (CRA) network, which significantly outperforms previous baselines and has significantly fewer model parameters and multiplies, which makes it suitable for real-world production applications.
Proceedings ArticleDOI
An audio-based wakeword-independent verification system
TL;DR: An audio-based wakeword-independent verification model to determine whether a wakeword spotting model correctly woke and should respond or incorrectly woke andshould not respond is proposed, yielding a wakewords agnostic model.