Unsupervised learning in cross-corpus acoustic emotion recognition
- 1 December 2011
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2011 IEEE Workshop on Automatic Speech Recognition & Understanding
Abstract
One of the ever-present bottlenecks in Automatic Emotion Recognition is data sparseness. We therefore investigate the suitability of unsupervised learning in cross-corpus acoustic emotion recognition through a large-scale study with six commonly used databases, including acted and natural emotion speech, and covering a variety of application scenarios and acoustic conditions. We show that adding unlabeled emotional speech to agglomerated multi-corpus training sets can enhance recognition performance even in a challenging cross-corpus setting; furthermore, we show that the expected gain by adding unlabeled data on average is approximately half the one achieved by additional manually labeled data in leave-one-corpus-out validation.Keywords
This publication has 15 references indexed in Scilit:
- Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challengeSpeech Communication, 2011
- Cross-Corpus Acoustic Emotion Recognition: Variances and StrategiesIEEE Transactions on Affective Computing, 2010
- Emotion Recognition from Speech by Combining Databases and Fusion of ClassifiersLecture Notes in Computer Science, 2010
- Being bored? Recognising natural interest by extensive audiovisual integration for real-life applicationImage and Vision Computing, 2009
- The WEKA data mining softwareACM SIGKDD Explorations Newsletter, 2009
- Speech Emotion Recognition using an Enhanced Co-Training AlgorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- The HUMAINE Database: Addressing the Collection and Annotation of Naturalistic and Induced Emotional DataLecture Notes in Computer Science, 2006
- Unsupervised and active learning in automatic speech recognition for call classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Co-training for predicting emotions with spoken dialogue dataPublished by Association for Computational Linguistics (ACL) ,2004
- Combining labeled and unlabeled data with co-trainingPublished by Association for Computing Machinery (ACM) ,1998