A Taiwan-specific tokenizer, language model, and bridge to a reused acoustic stack cut code-switching TTS CER from 11.45% to 4.81%, with 65.6% listener preference.
HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SD 2years
2026 2verdicts
CONDITIONAL 2representative citing papers
Four-step SR-FD fine-tuning cuts VoxCPM2's Seed-TTS English WER from 2.23% to 1.41%, beating the ten-step baseline at 1.74% with no inference-time cost.
citing papers explorer
-
BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech
A Taiwan-specific tokenizer, language model, and bridge to a reused acoustic stack cut code-switching TTS CER from 11.45% to 4.81%, with 65.6% listener preference.
-
Fr\'echet Distance Loss on Speech Representations for Text-to-Speech Synthesis
Four-step SR-FD fine-tuning cuts VoxCPM2's Seed-TTS English WER from 2.23% to 1.41%, beating the ten-step baseline at 1.74% with no inference-time cost.