Name
Title | ||
|---|---|---|
A study of continuous space word and sentence representations applied to ASR error detection |
Abstract | ||
|---|---|---|
•Experimental results of linguistic, signal, and acoustic word embeddings combined to prosodic features.•Experimental results show how much acoustic embeddings and prosodic features are very complementary to detect errors.•A new task-dedicated sentence embedding helps to improve the ASR error detection quality.•The task-dedicated sentence embedding outperforms a famous generic sentence embedding.•A comparison of our feed forward Multi-Layer Perceptron Multi Stream neural architecture to a bidirectional recurrent neural network. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.specom.2020.03.002 | Speech Communication |
Keywords | DocType | Volume |
ASR error detection,Neural networks,Prosodic features,Linguistic embeddings,Acoustic embeddings,Sentence embeddings | Journal | 120 |
ISSN | Citations | PageRank |
0167-6393 | 1 | 0.35 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| sahar ghannay | 1 | 9 | 5.65 |
| Yannick Estève | 2 | 298 | 50.89 |
| Nathalie Camelin | 3 | 39 | 14.29 |