Verfahren und Vorrichtung zum Trainieren eines Sprachverbesserungsmodells, Vorrichtung, Medium und Programmprodukt

Details

Veröffentlichungs-Nr.

EP4718450

Anmeldetag

17. Juni 2024

Veröffentlichung

20. Februar 2025

Rechtsraum

EP

Abstract

The present disclosure relates to the field of artificial intelligence, and in particular, to a method for training the speech enhancement model and apparatus, an electronic device, and a storage medium. The method includes: extracting a first audio feature of a to-be-enhanced speech signal through an input layer in each instance of iterative training of an initial version of the speech enhancement model; performing dimension-reduction on the first audio feature through a dimension-reduction layer, to obtain a dimensionality-reduced second audio feature; performing, through a mapping layer, feature mapping on the second audio feature by using a cyclic iteration manner, to obtain a third audio feature, a quantity of output channels of the mapping layer increasing progressively in a cyclic iteration process; and inputting the third audio feature to an output layer, to obtain vector of the estimated gain, and performing parameter adjustment on the initial version of the speech enhancement model with reference to ground-true gain. The present disclosure can ensure a processing effect of a trained model, and reduce operation complexity to improve an operation speed, thereby meeting a real-time operation requirement and enhancing a communication experience.

Anmelder

Firma

Tencent Technology (Shenzhen) Company Limited

Land

🇨🇳 China