Abstract | ||
---|---|---|
Classification performance for emotional user states found in the few realistic, spontaneous databases available is as yet not very high. We present a database with emotional children's speech in a human-robot scenario. Baseline classification per-formance for seven classes is 44.5%, for four classes 59.2%. We discuss possible strategies for tuning, e. g., using only pro-totypes (based on annotation correspondence or classification scores), or taking into account requirements and feasibility in possible applications (weighting of false alarms or speaker-specific overall frequencies). |
Year | Venue | Field |
---|---|---|
2005 | INTERSPEECH | Weighting,Annotation,One-class classification,Pattern recognition,Computer science,Speech recognition,Artificial intelligence |
DocType | Citations | PageRank |
Conference | 18 | 2.43 |
References | Authors | |
5 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anton Batliner | 1 | 1502 | 131.55 |
Stefan Steidl | 2 | 1140 | 79.71 |
Christian Hacker | 3 | 235 | 22.51 |
Elmar Nöth | 4 | 959 | 158.94 |
Heinrich Niemann | 5 | 1650 | 288.56 |