Name
Title | ||
|---|---|---|
A Low Latency Sequential Model and its User-Focused Evaluation for Automatic Punctuation of ASR Closed Captions |
Abstract | ||
|---|---|---|
•Low latency, real-time automatic punctuation model.•RNN-based punctuation outperforms the MaxEnt baseline.•Subjective tests confirm that humans prefer punctuated captions.•Deaf or hard of hearing users prefer automatic punctuation even more. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.csl.2020.101076 | Computer Speech & Language |
Keywords | DocType | Volume |
Punctuation,Recurrent neural network,LSTM,Maximum entropy,Low latency,Real-time modelling,User-focused evaluation,Mean opinion score,Closed captioning | Journal | 63 |
ISSN | Citations | PageRank |
0885-2308 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Máté Ákos Tündik | 1 | 1 | 1.03 |
| Balázs Tarján | 2 | 21 | 4.92 |
| György Szaszák | 3 | 51 | 13.21 |