Spoken Language Identification On Lre07
Metrics
10 sec
3 sec
30 sec
Average
Results
Performance results of various models on this benchmark
| Paper Title | |||||
|---|---|---|---|---|---|
| Kaldi i-vector | 11.93 | 26.04 | 4.52 | 14.17 | VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION |
| Kaldi i-vector DNN | 7.84 | 19.67 | 3.31 | 10.27 | VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION |
| Phonotactic | 6.28 | 18.59 | 1.34 | 8.73 | VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION |
| GMM-MMI | 5.90 | 17.28 | 2.10 | 8.42 | VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION |
| Fusion of models | 4.54 | 15.29 | 1.30 | 7.04 | VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION |
| Resnet34 (noisy data) | 3.33 | 10.58 | 1.72 | 5.21 | VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION |
| Resnet34 (cleaned data) | 3.14 | 9.39 | 1.90 | 4.81 | VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION |
| CNN-LDE | 2.61 | 8.25 | 1.16 | 4.00 | VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION |
| CNN-SAP | 2.49 | 8.59 | 1.09 | 4.06 | VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION |
0 of 9 row(s) selected.