Abstract | ||
---|---|---|
This work investigates spoken language understanding (SLU) systems in the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. Two SLU tasks are considered: named entity recognition (NER) and semantic slot filling (SF). For these tasks, in order to improve the model performance, we explore various techniques including speaker adaptation, a modification of the connectionist temporal classification (CTC) training criterion, and sequential pretraining. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-31372-2_4 | SLSP |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Natalia A. Tomashenko | 1 | 45 | 11.84 |
Antoine Caubrière | 2 | 3 | 3.48 |
Yannick Estève | 3 | 298 | 50.89 |
Antoine Laurent | 4 | 43 | 12.04 |
Emmanuel Morin | 5 | 42 | 16.13 |