Speech Quality Evaluation on QA Evaluation Suite Speech Output
3.71MOSStep-Audio-2
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Step-Audio-2Backbone=Step-Audio-2, Text EE=-, Speech EE=-2026.03 | 3.71 | 1.51 | |
| SPAR-KBackbone=Step-Audio-2, Text EE=-, Speech EE=Triple (22)2026.03 | 3.668 | 1.51 | |
| SPAR-KBackbone=Step-Audio-2, Text EE=-, Speech EE=Odd (22)2026.03 | 3.65 | 2.19 | |
| SPAR-KBackbone=Step-Audio-2, Text EE=-, Speech EE=Even (22)2026.03 | 3.643 | 1.58 | |
| Step-Audio-2Backbone=Step-Audio-2, Text EE=-, Speech EE=Fixed (25)2026.03 | 3.058 | 3.4 | |
| GLM-4-VoiceBackbone=GLM-4-Voice, Text EE=-, Speech EE=-2026.03 | 2.982 | 4.31 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Odd (36)2026.03 | 2.982 | 5.06 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Even (33)2026.03 | 2.981 | 7.13 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=Even (36), Speech EE=-2026.03 | 2.979 | 12.8 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Even (36)2026.03 | 2.95 | 5.36 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=Conf (36), Speech EE=Even(36)2026.03 | 2.949 | 5.15 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Even (35)2026.03 | 2.942 | 6.44 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Triple (37)2026.03 | 2.909 | 5.77 | |
| GLM-4-VoiceBackbone=GLM-4-Voice, Text EE=-, Speech EE=Conf (36)2026.03 | 2.866 | 7.62 | |
| GLM-4-VoiceBackbone=GLM-4-Voice, Text EE=-, Speech EE=Fixed (38)2026.03 | 2.662 | 43.6 | |
| Step-Audio-2Backbone=Step-Audio-2, Text EE=-, Speech EE=Conf (26)2026.03 | 1.651 | 11.01 |