Speech Emotion Recognition

Inspiration

What it does

This is capitalizing on the fact that voice often reflects underlying emotion through tone and pitch.This is also the phenomenon that animals like dogs and horses employ to be able to understand human emotion. SER is tough because emotions are subjective and annotating audio is challenging.

How we built it

If you ever noticed, call centers employees never talk in the same manner, their way of pitching/talking to the customers changes with customers. Now, this does happen with common people too, but how is this relevant to call centers? Here is your answer, the employees recognize customers’ emotions from speech, so they can improve their service and convert more people. In this way, they are using speech emotion recognition. So, let’s discuss this project in detail.

Challenges we ran into

Least squares regression is one of the noted methods for speech emotion recognition. An ideal scientific SER system would be one that can develop real life and loud talking to recognize different state of emotions.

Accomplishments that we're proud of

After constructing various models, we got the better CNN model for the emotion distinction task. We reached 71%accuracy from the previously available model. Our model would’ve performed better with more data. Also, our model performed very well when distinguishing among a masculine and feminine voice. Our project can be extended to integrate with the robot to help it to have a better understanding of the mood the corresponding human is in, which will help it to have a better conversation as well as it can be integrated with various music applications to recommend songs to its users according to his/her emotions, it can also be used in various online shopping applications such as Amazon to improve the product recommendation for its users. Moreover, in the upcoming years we can construct a sequence-to-sequence model to create voice having different emotions. E g: a sad voice, an excited one etc.

What's next for Speech Emotion Recognition

We are going to start a mobile application for speech emotion recognition, and we are going add some more emotions . The Shape of the Speech signal determines what sound comes out. If the shape is determined accurately, then the correct representation of the sound being generated is obtained.

What we learned

Speech emotion recognition has found increasing applications in practice, e.g., in security, medicine, entertainment, education. However, the research work on speech emotion recognition is mainly conducted on pre-processed databases that, in general, consist of isolated utterances or phrases.

Built With

• python