US 12,394,421 B2
Speaker identification apparatus, speaker identification method, and recording medium
Katsunori Daimo, Osaka (JP)
Assigned to PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICA, Torrance, CA (US)
Filed by Panasonic Intellectual Property Corporation of America, Torrance, CA (US)
Filed on Aug. 9, 2022, as Appl. No. 17/883,972.
Application 17/883,972 is a continuation of application No. PCT/JP2021/004224, filed on Feb. 5, 2021.
Claims priority of provisional application 62/981,235, filed on Feb. 25, 2020.
Claims priority of application No. 2020-146245 (JP), filed on Aug. 31, 2020.
Prior Publication US 2022/0383880 A1, Dec. 1, 2022
Int. Cl. G10L 17/06 (2013.01); G10L 17/02 (2013.01); G10L 25/63 (2013.01)
CPC G10L 17/06 (2013.01) [G10L 17/02 (2013.01); G10L 25/63 (2013.01)] 11 Claims
OG exemplary drawing
 
10. A speaker identification method of identifying a speaker of utterance data indicating a voice of an utterance subjected to identification, the speaker identification method comprising:
estimating, from an acoustic feature value calculated from the utterance data, an emotion contained in the voice of the utterance indicated by the utterance data, using a trained deep neural network (DNN); and
outputting, based on the acoustic feature value calculated from the utterance data, a score for identifying the speaker of the utterance data, using an estimation result in the estimating,
wherein the score is calculated using a different method for each of emotions obtained from estimation results each of which is the estimation result.