Technical Program

TA7a: Speech Processing

Session Type: Oral
Time: Tuesday, October 30, 08:15 - 09:55
Location: Acacia
Session Chair: Balu Santhanam, University of New Mexico
 
TA7a-1: SPEECH EMOTION RECOGNITION WITH DATA AUGMENTATION AND LAYER-WISE LEARNING RATE ADJUSTMENT
         Caroline Etienne; LIMSI
         Guillaume Fidanza; DreamQuark
         Andrei Petrovskii; DreamQuark
         Laurence Devillers; LIMSI
         Benoit Schmauch; DreamQuark
 
TA7a-2: LARGE DEVIATION FIRST FORMANT DEMODULATION VIA EMPIRICAL MODE DECOMPOSITION AND MULTIRATE FREQUENCY TRANSFORMATIONS
         Wenjing Liu; University of New Mexico
         Balu Santhanam; University of New Mexico
 
TA7a-3: A NEW FEATURE SET FOR MASKING-BASED MONAURAL SPEECH SEPARATION
         Shadi Pirhosseinloo; University of Kansas
         Jonathan Scott Brumberg; University of Kansas
 
TA7a-4: BAYESIAN GLOTTAL INVERSE FILTERING AND VOCAL TRACT AREA RECOVERY FOR ARTICULATORY SPEECH SYNTHESIS
         Adarsh Venkataramani; Arizona State University
         Antonia Papandreou-Suppappola; Arizona State University