Designing the interaction among human language and a registered emotional database enables us to explore how the system performs and has multiple approaches for emotion detection in patient services. As of now, clustering techniques were primarily used in many prominent areas and in emotional speech recognition, even though it shows best results a new approach to the design is focused on Long Short-Term Memory (LSTM), Bi-Directional LSTM and Gated Recurrent Unit (GRU) as an estimation method for emotional Tamil datasets is available in this paper. A new approach of Deep Hierarchal LSTM/BiLSTM/GRU layer is designed to obtain the best result for long term learning voice dataset. Different combinations of deep learning hierarchal architecture like LSTM & GRU (DHLG), BiLSTM & GRU (DHBG), GRU & LSTM (DHGL), GRU & BiLSTM (DHGB) and dual GRU (DHGG) layer is designed with introduction of dropout layer to overcome the learning problem and gradient vanishing issues in emotional speech recognition. Moreover, to increase the design outcome within each emotional speech signal, various feature extraction combinations are utilized. From the analysis an average classification validity of the proposed DHGB model gives 82.86%, which is slightly higher than other models like DHGL (82.58), DHBG (82%), DHLG (81.14%) and DHGG (80%). Thus, by comparing all the models DHGB gives prominent outcome of 5% more than other four models with minimum training time and low dataset.
Emotional Speech Recognition using Deep Learning
