Kaya, HeysemKarpov, Alexey A.Salah, Albert Ali2022-05-112022-05-112016978-3-319-40663-3978-3-319-40662-60302-97431611-3349https://doi.org/10.1007/978-3-319-40663-3_14https://hdl.handle.net/20.500.11776/608613th International Symposium on Neural Networks (ISNN) -- JUL 06-08, 2016 -- Saint Petersburg, RUSSIAOne of the challenges in speech emotion recognition is robust and speaker-independent emotion recognition. In this paper, we take a cascaded normalization approach, combining linear speaker level, non-linear value level and feature vector level normalization to minimize speaker-related effects and to maximize class separability with linear kernel classifiers. We use extreme learning machine classifiers on a four class (i.e. joy, anger, sadness, neutral) problem. We show the efficacy of our proposed method on the recently collected Turkish Emotional Speech Database.en10.1007/978-3-319-40663-3_14info:eu-repo/semantics/closedAccessAcoustic emotion recognitionSpeech emotion recognitionCascaded normalizationExtreme learning machinesELMCognitive LoadConference Object9719115123N/AWOS:0003863249000142-s2.0-84978818512Q3