US 12,439,203 B2
Divisive normalization method, device, audio feature extractor and a chip
Huaqiu Zhang, Guangdong (CN); Saeid Haghighatshoar, Guangdong (CN); Dylan Richard Muir, Guangdong (CN); Hao Liu, Guangdong (CN); Peng Zhou, Guangdong (CN); and Ning Qiao, Guangdong (CN)
Assigned to ShenZhen SynSense Technology Co., Ltd., Guongdong (CN)
Appl. No. 18/020,282
Filed by ShenZhen SynSense Technology Co., Ltd., Guangdong (CN)
PCT Filed Mar. 24, 2022, PCT No. PCT/CN2022/082719
§ 371(c)(1), (2) Date Feb. 8, 2023,
PCT Pub. No. WO2023/137861, PCT Pub. Date Jul. 27, 2023.
Claims priority of application No. 202210051924.9 (CN), filed on Jan. 18, 2022.
Prior Publication US 2023/0300529 A1, Sep. 21, 2023
Int. Cl. H04S 3/00 (2006.01); H04R 3/04 (2006.01)
CPC H04R 3/04 (2013.01) [H04S 3/008 (2013.01); H04S 2400/01 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A divisive normalization method comprising:
S1: receiving input spikes train;
S2: yielding averaged values of the input spikes train in an averaging window to produce a threshold parameter; and
S3: deciding whether to enable an integrate-and-fire (IAF) counter counting via the number of input spikes in each clock period, and when a count value of the integrate-and-fire counter reaches the threshold parameter, producing a single output spike and performing reset, wherein a size of the averaging window comprises at least one frame period, and the frame period comprises at least one clock period;
wherein the input spikes train is a pre-normalized spikes train yielded by audio front end;
wherein the audio front end processes an original audio signal collected by a microphone and yields the pre-normalized spikes train.