Automatic Speech Recognition on Multilingual ASR Corpus Global - all 15 languages
9CERembedding-based H-Softmax
Evaluation Results
| Method | Links | |
|---|---|---|
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-large, Distance Metric=2-med S-Euc2025.01 | 9 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-XL, Distance Metric=Wtd Corr2025.01 | 9.1 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-base, Distance Metric=2-med S-Euc2025.01 | 9.2 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=LABSE, Distance Metric=Median Euc2025.01 | 9.2 | |
| embedding-based H-SoftmaxTraining=All, Strategy=Mono-Map, Weighting=Avg CB2025.01 | 9.2 | |
| H-Softmax (Huffman)Training=All, Softmax Type=Huffman2025.01 | 10.4 | |
| SoftmaxTraining=All, Softmax Type=Standard Softmax2025.01 | 11.8 |