US 11,837,236 B2
Speaker recognition based on signal segments weighted by quality
Hitoshi Yamamoto, Tokyo (JP); and Takafumi Koshinaka, Tokyo (JP)
Assigned to NEC CORPORATION, Tokyo (JP)
Filed by NEC Corporation, Tokyo (JP)
Filed on Dec. 8, 2021, as Appl. No. 17/545,107.
Application 17/545,107 is a continuation of application No. 16/475,743, granted, now 11,250,860, previously published as PCT/JP2017/008979, filed on Mar. 7, 2017.
Prior Publication US 2022/0101859 A1, Mar. 31, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 17/02 (2013.01); G10L 17/04 (2013.01); G10L 17/18 (2013.01); G10L 25/63 (2013.01)
CPC G10L 17/02 (2013.01) [G10L 17/04 (2013.01); G10L 17/18 (2013.01); G10L 25/63 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A speech processing device, comprising:
a processor; and
memory storing executable instructions that, when executed by the processor, causes the processor to perform as:
a contribution degree estimation unit configured to calculate a contribution degree representing a quality of a segment of a speech signal indicative of speech, the speech signal being divided into a plurality of segments; and
a speaker feature calculation unit configured to calculate a speaker feature from the speech signal, for recognizing attribute information of the speech signal, using the contribution degree as a weight of each segment of the speech signal, the speaker feature being indicative of individuality for identifying a speaker which utters the speech.