Adaptive batching to reduce recognition latency

US11183178B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Hosam A. Khalil · Redmond, US
• Emilian Stoimenov · Bellevue, US
• Yifan Gong · Sammamish, US
• Chaojun Liu · Redmond, US
• Christopher Hakan BASOGLU · Everett, US
• Amit Agarwal · Milpitas, US
• Naveen Parihar · Bellevue, US
• Sayan Dev PATHAK · Kirkland, US

Key dates

• Filing date: Jan 27, 2020
• Grant date: Nov 23, 2021
• Expiry date: Feb 28, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G10L15/16
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size greater than the first batch size, and input of the second batch to the speech recognition network.