Wakeword and acoustic event detection

US11132990B1 · kind B1 · utility

Assignee

• AMAZON TECHNOLOGIES, INC. · US

Inventors

• Ming Sun · Shanghai, CN
• Thibaud Senechal · Cambridge, US
• Yixin Gao · Malden, US
• Anish Narendra Shah · Bedford, US
• Spyridon Matsoukas · Hopkinton, US
• Chao Wang · Newton, US
• Shiv Naga Prasad Vitaladevuni · Cambridge, US

Key dates

• Filing date: Jun 26, 2019
• Grant date: Sep 28, 2021
• Expiry date: Dec 20, 2039

Classification

• Technology area (CPC G): Physics
• CPC primary: G10L2015/088
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A system processes audio data to detect when it includes a representation of a wakeword or of an acoustic event. The system may receive or determine acoustic features for the audio data, such as log-filterbank energy (LFBE). The acoustic features may be used by a first, wakeword-detection model to detect the wakeword; the output of this model may be further processed using a softmax function, to smooth it, and to detect spikes. The same acoustic features may be also be used by a second, acoustic-event-detection model to detect the acoustic event; the output of this model may be further processed using a sigmoid function and a classifier. Another model may be used to extract additional features from the LFBE data; these additional features may be used by the other models.