Spoken Term Detection on TIMIT OOV
69MAPwav2tok 2.0
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| wav2tok 2.0Tokens=2562026.06 | 69 | — | — | — | — | — | — | 74 | 62 | |
| wav2tok 2.0Tokens=5122026.06 | 69 | — | — | — | — | — | — | 75 | 65 | |
| wav2tokTokens=2562026.06 | 67 | — | — | — | — | — | — | 71 | 60 | |
| wav2tok 2.0Tokens=10242026.06 | 66 | — | — | — | — | — | — | 71 | 70 | |
| wav2tokTokens=5122026.06 | 65 | — | — | — | — | — | — | 70 | 60 | |
| wav2tokTokens=10242026.06 | 60 | — | — | — | — | — | — | 65 | 64 | |
| BEST-STDTokens=5122026.06 | 59 | — | — | — | — | — | — | 64 | 55 | |
| BEST-STDTokens=2562026.06 | 58 | — | — | — | — | — | — | 62 | 52 | |
| BEST-STDTokens=10242026.06 | 55 | — | — | — | — | — | — | 59 | 58 | |
| MFCC2026.06 | 43 | — | — | — | — | — | — | 44 | 42 | |
| Phone Posteriors2026.06 | 41 | — | — | — | — | — | — | 43 | 47 | |
| Speech TokenizerTokens=10242026.06 | 37 | — | — | — | — | — | — | 38 | 37 | |
| WavLM-BaseTokens=5122026.06 | 32 | — | — | — | — | — | — | 33 | 35 | |
| WavLM-BaseTokens=10002026.06 | 29 | — | — | — | — | — | — | 29 | 31 | |
| HuBERT-BaseTokens=5122026.06 | 25 | — | — | — | — | — | — | 26 | 31 | |
| HuBERT-BaseTokens=10002026.06 | 22 | — | — | — | — | — | — | 22 | 16 | |
| BNF2026.06 | 20 | — | — | — | — | — | — | 23 | 22 | |
| EncodecTokens=10242026.06 | 3 | — | — | — | — | — | — | 2 | 16 | |
| BEST-STDDistortion=Noise, Representation=SpeechTokens2025.12 | — | 0.25 | 0.33 | 0.4 | 0.49 | 0.5 | 0.56 | — | — | |
| BEST-STDDistortion=Noise + Reverberation, Representation=SpeechTokens2025.12 | — | 0.17 | 0.26 | 0.33 | 0.34 | 0.42 | 0.48 | — | — | |
| BEST-STD 2.0Distortion=Noise, Representation=SpeechTokens2025.12 | — | 0.53 | 0.63 | 0.67 | 0.69 | 0.7 | 0.71 | — | — | |
| BEST-STD 2.0Distortion=Noise + Reverberation, Representation=SpeechTokens2025.12 | — | 0.43 | 0.54 | 0.6 | 0.61 | 0.65 | 0.66 | — | — | |
| HuBERT-LargeDistortion=Noise, Representation=ASR Posteriors2025.12 | — | 0.16 | 0.28 | 0.37 | 0.43 | 0.44 | 0.46 | — | — | |
| HuBERT-LargeDistortion=Noise + Reverberation, Representation=ASR Posteriors2025.12 | — | 0.08 | 0.15 | 0.24 | 0.26 | 0.28 | 0.3 | — | — | |
| Ours-TransformerDistortion=Noise, Representation=SpeechTokens2025.12 | — | 0.52 | 0.6 | 0.64 | 0.66 | 0.68 | 0.69 | — | — | |
| Ours-TransformerDistortion=Noise + Reverberation, Representation=SpeechTokens2025.12 | — | 0.41 | 0.51 | 0.55 | 0.56 | 0.58 | 0.59 | — | — | |
| SpeechTokenizerDistortion=Noise, Representation=SpeechTokens2025.12 | — | 0.15 | 0.26 | 0.34 | 0.43 | 0.48 | 0.52 | — | — | |
| SpeechTokenizerDistortion=Noise + Reverberation, Representation=SpeechTokens2025.12 | — | 0.07 | 0.11 | 0.14 | 0.18 | 0.21 | 0.23 | — | — | |
| WavLM-LargeDistortion=Noise, Representation=ASR Posteriors2025.12 | — | 0.33 | 0.41 | 0.46 | 0.47 | 0.49 | 0.5 | — | — | |
| WavLM-LargeDistortion=Noise, Representation=SpeechTokens2025.12 | — | 0.19 | 0.29 | 0.35 | 0.46 | 0.47 | 0.51 | — | — | |
| WavLM-LargeDistortion=Noise + Reverberation, Representation=ASR Posteriors2025.12 | — | 0.18 | 0.24 | 0.31 | 0.35 | 0.39 | 0.41 | — | — | |
| WavLM-LargeDistortion=Noise + Reverberation, Representation=SpeechTokens2025.12 | — | 0.1 | 0.17 | 0.23 | 0.25 | 0.29 | 0.3 | — | — |