Abstract | ||
---|---|---|
One of the serious obstacles to the applications of speech emotion recognition systems in real-life settings is the lack of generalization of the emotion classifiers. Many recognition systems often present a dramatic drop in performance when tested on speech data obtained from different speakers, acoustic environments, linguistic content, and domain conditions. In this letter, we propose a novel u... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/LSP.2017.2672753 | IEEE Signal Processing Letters |
Keywords | Field | DocType |
Speech,Speech recognition,Training,Emotion recognition,Databases,Decoding,Neural networks | Autoencoder,Emotion recognition,Domain adaptation,Speech recognition,Artificial intelligence,Natural language processing,Labeled data,Discriminative model,Mathematics | Journal |
Volume | Issue | ISSN |
24 | 4 | 1070-9908 |
Citations | PageRank | References |
15 | 0.65 | 19 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jun Deng | 1 | 278 | 18.59 |
Xinzhou Xu | 2 | 38 | 3.45 |
Zixing Zhang | 3 | 397 | 31.73 |
Sascha Frühholz | 4 | 23 | 3.34 |
Björn Schuller | 5 | 6749 | 463.50 |