INTERSPEECH 2010
11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Emotion Recognition Using Imperfect Speech Recognition

Florian Metze (1), Anton Batliner (2), Florian Eyben (3), Tim Polzehl (4), Björn Schuller (3), Stefan Steidl (2)

(1) Carnegie Mellon University, USA
(2) FAU Erlangen-Nürnberg, Germany
(3) Technische Universität München, Germany
(4) Deutsche Telekom Laboratories, Germany

This paper investigates the use of speech-to-text methods for assigning an emotion class to a given speech utterance. Previous work shows that an emotion extracted from text can convey complementary evidence to the information extracted by classifiers based on spectral, or other non-linguistic features. As speech-to-text usually presents significantly more computational effort, in this study we investigate the degree of speech-to-text accuracy needed for reliable detection of emotions from an automatically generated transcription of an utterance. We evaluate the use of hypotheses in both training and testing, and compare several classification approaches on the same task. Our results show that emotion recognition performance stays roughly constant as long as word accuracy doesn't fall below a reasonable value, making the use of speech-to-text viable for training of emotion classifiers based on linguistics.

Full Paper

Bibliographic reference.  Metze, Florian / Batliner, Anton / Eyben, Florian / Polzehl, Tim / Schuller, Björn / Steidl, Stefan (2010): "Emotion recognition using imperfect speech recognition", In INTERSPEECH-2010, 478-481.