Research on children's emotional speech recognition technology based on Attention-LSTM

A children's speech emotion recognition technique based on an attention long short-term memory (Attention-LSTM) network is proposed in this paper. The core idea is to use an attention-LSTM network to realize speech emotion recognition based on the combination of articulatory features and acoustic features. Compared to existing methods in this field, it demonstrates significant innovation. In terms of experimental validation, the proposed method shows a 9.77 percentage improvement in emotion recognition accuracy through weighted averaging compared to that using only acoustic features or an LSTM classifier. These results can serve as valuable references for researchers working on emotion recognition in children's speech.