US 11,705,117 B2
Adaptive batching to reduce recognition latency
Hosam A. Khalil, Redmond, WA (US); Emilian Y. Stoimenov, Redmond, WA (US); Yifan Gong, Sammamish, WA (US); Chaojun Liu, Redmond, WA (US); Christopher H. Basoglu, Everett, WA (US); Amit K. Agarwal, Redmond, WA (US); Naveen Parihar, Bellevue, WA (US); and Sayan Pathak, Kirkland, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Oct. 13, 2021, as Appl. No. 17/500,585.
Application 17/500,585 is a continuation of application No. 16/773,205, filed on Jan. 27, 2020, granted, now 11,183,178.
Claims priority of provisional application 62/960,240, filed on Jan. 13, 2020.
Prior Publication US 2022/0068269 A1, Mar. 3, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/197 (2013.01); G10L 15/30 (2013.01); G10L 15/22 (2006.01); G10L 15/05 (2013.01); G10L 15/02 (2006.01)
CPC G10L 15/197 (2013.01) [G10L 15/02 (2013.01); G10L 15/05 (2013.01); G10L 15/22 (2013.01); G10L 15/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a processing unit; and
a storage device including program code that when executed by the processing unit causes the system to:
collect a first batch comprising a first number of raw acoustic feature frames of the audio signal, the first number equal to a first batch size;
input the first batch to a speech recognition network;
in response to a word hypothesis output by the speech recognition network, collect a second batch comprising a second number of acoustic feature frames of the audio signal, the second number equal to a second batch size; and
input the second batch to the speech recognition network.