Print Email Facebook Twitter An open-set detection evaluation methodology applied to language and emotion recognition Title An open-set detection evaluation methodology applied to language and emotion recognition Author van Leeuwen, D.A. Truong, K.P. TNO Defensie en Veiligheid Publication year 2007 Abstract This paper introduces a detection methodology for recognition technologies in speech for which it is dif cult to obtain an abundance of non-target classes. An example is language recognition, where we would like to be able to measure the detection capability of a single target language without confounding with the modeling capability of non-target languages. The evaluation framework is based on a cross validation scheme leaving the non-target class out of the allowed training material for the detector. The framework allows us to use Detection Error Tradeoff curves properly. As another application example we apply the evaluation scheme to emotion recognition in order to obtain single-emotion detection performance assessment. Index Terms: detection methodology, open-set evaluation, language, emotion. Subject Detection methodologyEmotionLanguageOpen-set evaluationError detectionFace recognitionInformation retrieval systemsLinguisticsQuery languagesSpeechSpeech recognitionTargetsApplication examplesCross validationsDetection capabilitiesDetection errorsDetection methodologyEmotionEmotion detectionsEmotion recognitionsEvaluation frameworksEvaluation methodologiesEvaluation schemesLanguageLanguage recognitionsModeling capabilitiesOpen-set evaluationRecognition technologiesTarget classesTarget languagesTradeoff curvesTraining materialsSpeech communicationemotionsfacial expressionslanguagedetection To reference this document use: http://resolver.tudelft.nl/uuid:3eebf0cb-dcfb-4227-8fd9-23dc00470479 TNO identifier 19221 Source Interspeech 2007, 338-341 Document type conference paper Files To receive the publication files, please send an e-mail request to TNO Library.