Method and system for speech emotion recognition

A computer program product tangibly embodied in a computer-readable storage device and comprising instructions that when executed by a processor perform a method using speech emotion recognition for enriching speech to text communications between users in a speech chat session, the method comprising:

• applying a set of rules for speech emotion recognition to convert observed emotions in a speech sample and to enrich text with visual emotion content in the speech to text communications by:
• generating a data set of speech samples with labels of a plurality of emotion classes;
• selecting a set of acoustic features from each of the plurality of emotion classes;
• applying the set of rules for the speech emotion recognition based on at least one of the selected set of acoustic features and the data set of speech samples;
• computing a number of rules that have been satisfied from the set of rules for the speech emotion recognition that have applied to the selected set of acoustic features to label the selected set of acoustic features;
• and
• presenting the enriched text in speech-to-text communications in accordance with labeled acoustic features between users in the speech chat session for visual notice of the observed emotion in the speech sample.

A system comprising:

• at least one processor;
• and
• at least one computer-readable storage device comprising instructions that when executed causes performance of a method for processing speech samples using speech emotion recognition for enriching speech to text communications between users in a speech chat, the system comprising:
• a set of rules for the speech emotion recognition implemented by the processor to convert observed emotions in a speech sample and to enrich text with visual emotion content in the speech to text communications, wherein the processor configured to:
• generate a data set of speech samples with labels of a plurality of emotion classes;
• extract a set of acoustic features from each emotion class;
• apply the set of rules for the speech emotion recognition based on at least one of a selected set of acoustic features and the data set of speech samples;
• compute a number of rules that have been satisfied from the set of rules for the speech emotion recognition applied to the selected set of acoustic features to label the selected set of acoustic features;
• and
• present the enriched text in the speech to text communications in accordance with labeled acoustic features between users in a speech chat session for visual notice of the observed emotion in the speech sample.