Text-to-Speech on VCTK 30m budget v0.92 (train)
10WERK=7 SPARCLE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| K=7 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=7, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 10 | 1.19 | |
| K=3 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=3, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 11.5 | 1.56 | |
| K=3 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=3, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 12.3 | 1.54 | |
| K=7 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=7, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 12.3 | 1.52 | |
| Unfrozen SPARCLEInput representation=SPARCLE, Timbre embeddings=with (+T), TTS Backend=ParrotTTS, Adaptation=Fully unfrozen2026.05 | 12.8 | 1.59 | |
| K=1 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=1, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 14.7 | 1.71 | |
| Unfrozen SPARCLEInput representation=SPARCLE, Timbre embeddings=without (-T), TTS Backend=ParrotTTS, Adaptation=Fully unfrozen2026.05 | 14.9 | 1.52 | |
| Frozen SPARCLEInput representation=SPARCLE, Timbre embeddings=without (-T), TTS Backend=ParrotTTS, Adaptation=Frozen2026.05 | 16.3 | 1.37 | |
| K=1 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=1, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 17.8 | 1.56 | |
| Frozen SPARCLEInput representation=SPARCLE, Timbre embeddings=with (+T), TTS Backend=ParrotTTS, Adaptation=Frozen2026.05 | 20.7 | 1.56 | |
| Phone EmbeddingsInput representation=Phoneme, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 32.6 | 1.76 | |
| Char EmbeddingsInput representation=Character, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 35.3 | 1.95 |