Výsledky vyhledávání - "Khursheed, Mohammad"

Report

Small-footprint slimmable networks for keyword spotting

Autor: Akhtar, Zuhaib, Khursheed, Mohammad Omar, Du, Dongsu, Liu, Yuzong

In this work, we present Slimmable Neural Networks applied to the problem of small-footprint keyword spotting. We show that slimmable neural networks allow us to create super-nets from Convolutioanl Neural Networks and Transformers, from which sub-ne

Externí odkaz: http://arxiv.org/abs/2304.12183

Zobrazit plný text záznamu

Report

Latency Control for Keyword Spotting

Autor: Jose, Christin, Wang, Joseph, Strimel, Grant P., Khursheed, Mohammad Omar, Mishchenko, Yuriy, Kulis, Brian

Conversational agents commonly utilize keyword spotting (KWS) to initiate voice interaction with the user. For user experience and privacy considerations, existing approaches to KWS largely focus on accuracy, which can often come at the expense of in

Externí odkaz: http://arxiv.org/abs/2206.07261

Zobrazit plný text záznamu

Report

Tiny-CRNN: Streaming Wakeword Detection In A Low Footprint Setting

Autor: Khursheed, Mohammad Omar, Jose, Christin, Kumar, Rajath, Fu, Gengshen, Kulis, Brian, Cheekatmalla, Santosh Kumar

In this work, we propose Tiny-CRNN (Tiny Convolutional Recurrent Neural Network) models applied to the problem of wakeword detection, and augment them with scaled dot product attention. We find that, compared to Convolutional Neural Network models, F

Externí odkaz: http://arxiv.org/abs/2109.14725

Zobrazit plný text záznamu

Report

Small Footprint Convolutional Recurrent Networks for Streaming Wakeword Detection

Autor: Khursheed, Mohammad Omar, Jose, Christin, Kumar, Rajath, Fu, Gengshen, Kulis, Brian, Cheekatmalla, Santosh Kumar

In this work, we propose small footprint Convolutional Recurrent Neural Network models applied to the problem of wakeword detection and augment them with scaled dot product attention. We find that false accepts compared to Convolutional Neural Networ

Externí odkaz: http://arxiv.org/abs/2011.12941

Zobrazit plný text záznamu

Report

Analyzing Gender Bias within Narrative Tropes

Autor: Gala, Dhruvil, Khursheed, Mohammad Omar, Lerner, Hannah, O'Connor, Brendan, Iyyer, Mohit

Popular media reflects and reinforces societal biases through the use of tropes, which are narrative elements, such as archetypal characters and plot arcs, that occur frequently across media. In this paper, we specifically investigate gender bias wit

Externí odkaz: http://arxiv.org/abs/2011.00092

Zobrazit plný text záznamu