Using a PCA-based dataset similarity measure to improve cross-corpus emotion recognition. (September 2018)

• Record Type: Journal Article
• Authors: Siegert, Ingo; Böck, Ronald; Wendemuth, Andreas
• Is Part Of: Computer speech & language. Volume 51(2018)
• Page Start: 1
• Page End: 23
• Publication Date: 2018-09
• Subjects: PCA -- Dataset similarity -- Cross-corpus emotion recognition -- Automatic similarity scoring; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2018.02.002
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Presented a method for informed selection of similar datasets based on distribution of acoustic characteristics. Applied method for cross-corpus emotion recognition from speech using state-of-the-art approaches. Outperformed uninformed cross-corpus analyses as well as feature normalization as alternative method. Influence of various factors that could be seen as alternative explanation for improvement were excluded by various experiments. Abstract: In emotion recognition from speech, huge amounts of training material are needed for the development of classification engines. As most current corpora do not supply enough material, a combination of different datasets is advisable. Unfortunately, data recording is done differently and various emotion elicitation and emotion annotation methods are used. Therefore, a combination of corpora is usually not possible without further effort. The manuscript's aim is to answer the question which corpora are similar enough to jointly be used as training material. A corpus similarity measure based on PCA-ranked features is presented and similar datasets are identified. To evaluate our method we used nine well-known benchmark corpora and automatically identified a sub-set of six most similar datasets. To test that the identified most similar six datasets influence the classification performance, we conducted several cross-corpora emotion recognition experiments comparing our identified six most similar datasets with other combinations. Our most similar sub-set outperforms all other combinations of corpora, the combination of all nine datasets as well as feature normalization techniques. Also influencing side-effects on the recognition rate were excluded. Finally, the predictive power of our measure is shown: increasing similarity score, expressing decreasing similarity, result in decreasing recognition rates. Thus, our similarity measure answers the question which corpora should be included into joint training.