In recent years, with the rapid development of artificial intelligence technology, humanauditory intelligence perception has received extensive attention. The human-like auditory intelligentspeech separation of robots in complex acoustic environment is studied. Through in-depth learningof key technologies such as DNN-HMM, a new deep network cluster structure, optimizationobjectives and deep learning algorithm capable of denoising in complex frequency domain areproposed to improve the accuracy of speech recognition, solve the problem of speech separation inhuman-like hearing in harsh environments, realize high-quality auditory perception in realenvironments, and enhance intelligence in far-field and complex acoustic environments.Human-computer interaction performance.
展开▼