Text-to-Speech on VCTK 10m budget v0.92 (train)
42.2WERK=3 SPARCLE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| K=3 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=3, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 42.2 | 1.99 | |
| K=7 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=7, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 42.2 | 2 | |
| K=7 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=7, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 42.4 | 1.95 | |
| K=3 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=3, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 43.5 | 1.95 | |
| K=1 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=1, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 47.1 | 2.34 | |
| Unfrozen SPARCLEInput representation=SPARCLE, Timbre embeddings=with (+T), TTS Backend=ParrotTTS, Adaptation=Fully unfrozen2026.05 | 49.3 | 2.14 | |
| Unfrozen SPARCLEInput representation=SPARCLE, Timbre embeddings=without (-T), TTS Backend=ParrotTTS, Adaptation=Fully unfrozen2026.05 | 52.1 | 2.19 | |
| Frozen SPARCLEInput representation=SPARCLE, Timbre embeddings=without (-T), TTS Backend=ParrotTTS, Adaptation=Frozen2026.05 | 53.4 | 2.1 | |
| K=1 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=1, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 58.7 | 2.39 | |
| Frozen SPARCLEInput representation=SPARCLE, Timbre embeddings=with (+T), TTS Backend=ParrotTTS, Adaptation=Frozen2026.05 | 69.2 | 2.15 | |
| Char EmbeddingsInput representation=Character, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 85.7 | 2.93 | |
| Phone EmbeddingsInput representation=Phoneme, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 96 | 3.32 |