Research Article
DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning
Table 1
Statistics of THCHS-30 database.
| Data set | Speaker | Male | Female | Age | Utterance | Duration (hour) |
| Training | 30 | 8 | 22 | 20–55 | 10893 | 27.23 h | Test | 10 | 1 | 9 | 19–50 | 2496 | 6.24 h |
|
|