Utterance-level classification on ARCH (RAVDESS, EMOVO, AudioMNIST, SLURP) post-VQ 57
37.85RAVDESS AccuracyDTM-Codec@50Hz
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| DTM-Codec@50HzSetting=VFR, |C|=16,3842026.06 | 37.85 | 36.01 | 21.94 | 14.53 | 68.26 | 68.05 | 7.11 | 0.96 | 33.79 | 29.89 | |
| DTM-Codec@40HzSetting=FFR, |C|=65,5362026.06 | 37.5 | 35.22 | 24.83 | 20.04 | 65.73 | 65.65 | 7 | 0.95 | 33.77 | 30.46 | |
| DTM-Codec@80HzSetting=VFR, |C|=16,3842026.06 | 37.5 | 33.25 | 23.81 | 16.4 | 58.62 | 58.13 | 6.97 | 0.84 | 31.73 | 27.16 | |
| X-Codec 2.0Setting=50Hz, |C|=65,536, Features=Wav2Vec2-BERT semantic features2026.06 | 37.15 | 32.88 | 20.75 | 15.59 | 68.49 | 68.15 | 7.74 | 1.22 | 33.53 | 29.46 | |
| DTM-Codec@80HzSetting=FFR, |C|=65,5362026.06 | 36.81 | 33.93 | 26.19 | 19.56 | 70.88 | 70.76 | 7 | 0.96 | 35.22 | 31.3 | |
| BigCodecSetting=80Hz, |C|=8,1922026.06 | 36.11 | 34.43 | 17.18 | 12.38 | 65.84 | 65.74 | 7.67 | 1.05 | 31.7 | 28.4 | |
| DTM-Codec@25HzSetting=FFR, |C|=65,5362026.06 | 35.42 | 33.56 | 26.7 | 22.13 | 65.07 | 64.77 | 7.45 | 1.06 | 33.66 | 30.38 | |
| DTM-Codec@50HzSetting=FFR, |C|=65,5362026.06 | 34.72 | 31.69 | 24.49 | 18.71 | 69.63 | 69.55 | 7.23 | 1.05 | 34.02 | 30.25 | |
| DTM-Codec@40HzSetting=VFR, |C|=16,3842026.06 | 32.99 | 28.97 | 21.09 | 17.12 | 70.69 | 70.45 | 7.61 | 1.15 | 33.09 | 29.42 | |
| DTM-Codec@25HzSetting=VFR, |C|=16,3842026.06 | 32.64 | 28.61 | 27.38 | 22.75 | 65.84 | 65.45 | 7.6 | 1.19 | 33.37 | 29.5 | |
| VARSTokSetting=τ=0.8, |C|=4,0962026.06 | 27.43 | 24.01 | 27.21 | 21.39 | 60.42 | 60.18 | 7.62 | 1.13 | 30.67 | 26.68 | |
| WavTokenizerSetting=75Hz, |C|=4,0962026.06 | 27.43 | 22.5 | 20.41 | 15.8 | 56.62 | 56.18 | 7.12 | 0.82 | 27.9 | 23.82 | |
| VARSTokSetting=τ=0.7, |C|=4,0962026.06 | 27.08 | 23.74 | 25.68 | 20.27 | 61.35 | 61.09 | 7.49 | 1.07 | 30.4 | 26.54 | |
| WavTokenizerSetting=40Hz, |C|=4,0962026.06 | 24.65 | 21.8 | 26.19 | 18.69 | 50.12 | 49 | 6.69 | 0.53 | 26.91 | 22.5 | |
| VARSTokSetting=τ=0.6, |C|=4,0962026.06 | 24.31 | 21.03 | 24.83 | 19.34 | 62.36 | 62.1 | 7.28 | 1 | 29.69 | 25.87 |