Emotional speech processing

Abstract

The invention relates to emotional speech processing. A method for emotion or speaking style recognition and / or clustering comprises receiving one or more speech samples, generating a set of training data by extracting one or more acoustic features from every frame of the one or more speech samples, and generating a model from the set of training data, wherein the model identifies emotion or speaking style dependent information in the set of training data. The method may further comprise receiving one or more test speech samples, generating a set of test data by extracting one or more acoustic features from every frame of the one or more test speeches, and transforming the set of test data using the model to better represent emotion / speaking style dependent information, and use the transformed data for clustering and / or classification to discover speech with similar emotion or speaking style. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Description

[0001] Related applications [0002] This application claims priority to commonly assigned US Provisional Patent Application No. 62 / 030,013, filed July 28, 2014, the entire disclosure of which is incorporated herein by reference. This application also claims priority to commonly assigned US Patent Application Serial No. 14 / 743,673, filed June 18, 2015, the entire disclosure of which is incorporated herein by reference. technical field [0003] The present disclosure relates to speech processing, and more particularly to emotional speech processing. Background technique [0004] Emotional speech processing is important for many applications including user interfaces, games and more. However, processing emotional speech is very challenging. For example, emotional speech characteristics are significantly different from spoken / conversational speech, and thus statistical sound recognition models trained with spoken speech do not perform well when encountered with emotional spee...

AI Technical Summary

Problems solved by technology

However, processing emotional speech is very challenging

For example, emotional speech characteristics are significantly different from spoken / conversational speech, and thus statistical sound recognition models trained with spoken speech do not perform well when encountered with emotional speech

In addition, emotion recognition is difficult because different speakers have different ways of expressing their emotions, and thus the classes are ambiguous and indistinguishable

Images