Training device, emotion recognition device, training method, emotion recognition method, and program
The unsupervised speaker adaptive emotion recognition model addresses the high labeling costs of conventional technologies by using a pre-trained encoder and attention pooling layer to extract emotional clues without speaker labels, enhancing emotion recognition accuracy and adaptability across speakers.
WO2025017807A1PCT designated stage expired Publication Date: 2025-01-23NIPPON TELEGRAPH & TELEPHONE CORP
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- PCT/JP2023/026139
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-07-14
- Publication Date
- 2025-01-23
Smart Images
Figure JP2023026139_23012025_PF_FP_ABST
Abstract
A training device according to one aspect of the present disclosure comprises: an acoustic feature sequence extraction unit that uses a given voice and a first parameter to extract an acoustic feature sequence representing features of the voice; a speaker attention unit that uses information relating to a speaker extracted from the voice, the acoustic feature sequence, and a second parameter to extract information indicating a clue to an emotional expression for each speaker from the acoustic feature sequence on the basis of the information relating to the speaker; a posterior probability calculation unit that uses the information indicating the clue to the emotional expression for each speaker and a third parameter to calculate posterior probability for each predetermined emotion class; and a training unit that uses the posterior probability for each emotion class and the correct answer of the emotion class to which the voice belongs to update the first parameter, the second parameter, and the third parameter.
Need to check novelty before this filing date? Find Prior Art