Project Team - 1. Arunachalam RM 2. Manoj S

Project Guide Mrs.Vasuki P Assistant Professor,

Dept. of IT

The speech signal is the fastest and the most natural method of communication between humans. This fact has motivated researchers to think of speech as a fast and efficient method of interaction between human and machine. However, this requires that the machine should have the sufficient intelligence to recognize human voices. Since the late fifties, there has been tremendous research on speech recognition, which refers to the process of converting the human speech into a sequence of words.

However, despite the great progress made in speech recognition, we are still far from having a natural interaction between man and machine because the machine does not understand the emotional state of the speaker. This has introduced a relatively recent research field, namely speech emotion recognition, which is defined as extracting the emotional state of a speaker from his or her speech. It is believed that speech emotion recognition can be used to extract useful semantics from speech, and hence, improves the performance of speech recognition systems.

Speech emotion recognition is particularly useful for applications which require natural manmachine interaction such as web movies and computer tutorial applications where the response of those systems to the user depends on the detected emotion. It is also useful for in-car board system where information of the mental state of the driver may be provided to the system to initiate his/her safety. It can be also employed as a diagnostic tool for therapists .

It may be also useful in automatic translation systems in which the emotional state of the speaker plays an important role in communication between parties. In aircraft cockpits, it has been found that speech recognition systems trained to stressed-speech achieve better performance than those trained by normal speech. Speech emotion recognition has also been used in call center applications and mobile communication. The main objective of employing speech emotion recognition is to adapt the system response upon detecting frustration or annoyance in the speaker's voice.

Passion for Machine Learning Scope of improvement in speech processing The increased use of technology has made it one

of mans best friends. The presence of a best friend during our bad mood swings is always helpful.

The objective of this project is to analyse the emotions and speech of the humans over a certain period of time which is captured either during their phone calls (mobile) or during their interactions with computer and provide them valuable solutions for neutralizing their emotions.

Emotion recognition analysis eventually leads to depression analysis.

Emotion recognition analysis can be used to neutralize the human emotions.

E-learning online tutor can adjust his presentation style according to the state of the learner.

In Medical industry, we can detect if a person has depressive symptoms and the severity of those symptoms without asking them any questions.

The ability to recognise the emotional states of others is believed to facilitate the detection of deception during criminal investigation.

In Call center system we can recognize voices and detect angriness in speech. This information can be used to prioritize angry calls.

Mobile/Computer Four trained actors (one young male, one

young female, one older male and one older female)

Speech/Emotion recorder Emotion analyser

Yoon W.-J. , Park K.-S., A Study of Emotion Recognition and and its application to mobile services, 4th International Conference, MDAI, Springer, 2007

Rached T.S., Perkusich A., Emotion Recognition Based on Brain-Computer Interface Systems, Brain-Computer Interface Systems, 2013

Lewis M (1993) The development of deception. In Lewis M, Saarin C, editors. Lying and deception in everyday life. New York.