SP-L2: Speech Analysis I |
Session Type: Lecture |
Time: Tuesday, March 16, 13:30 - 15:30 |
Location: Room B |
Session Chair: Douglas O'Shaughnessy, INRS,University of Quebec, Canada |
SP-L2.1: SINGLE-CHANNEL SOURCE SEPARATION USING SIMPLIFIED-TRAINING COMPLEX MATRIX FACTORIZATION |
Brian King; University of Washington |
Les Atlas; University of Washington |
SP-L2.2: ON THE ROBUSTNESS OF THE QUASI-HARMONIC MODEL OF SPEECH |
Yannis Pantazis; University of Crete |
Olivier Rosec; France Telecom |
Yannis Stylianou; University of Crete |
SP-L2.3: A SHORT-TIME OBJECTIVE INTELLIGIBILITY MEASURE FOR TIME-FREQUENCY WEIGHTED NOISY SPEECH |
Cees Taal; Delft University of Technology |
Richard Hendriks; Delft University of Technology |
Richard Heusdens; Delft University of Technology |
Jesper Jensen; Oticon A/S |
SP-L2.4: A MULTIPITCH TRACKING ALGORITHM FOR NOISY AND REVERBERANT SPEECH |
Zhaozhang Jin; Ohio State University |
DeLiang Wang; Ohio State University |
SP-L2.5: ROBUST SPEAKING RATE ESTIMATION USING BROAD PHONETIC CLASS RECOGNITION |
Jiahong Yuan; University of Pennsylvania |
Mark Liberman; University of Pennsylvania |
SP-L2.6: CLAP YOUR HANDS! CALIBRATING SPECTRAL SUBTRACTION FOR DEREVERBERATION |
Uwe Zäh; Universität Erlangen-Nürnberg |
Korbinian Riedhammer; Universität Erlangen-Nürnberg |
Tobias Bocklet; Universität Erlangen-Nürnberg |
Elmar Nöth; Universität Erlangen-Nürnberg |