REVIEW 4 cited by
BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
We present BreezyVoice, a Text-to-Speech (TTS) system specifically adapted for Taiwanese Mandarin, highlighting phonetic control abilities to address the unique challenges of polyphone disambiguation in the language. Building upon CosyVoice, we incorporate a $S^{3}$ tokenizer, a large language model (LLM), an optimal-transport conditional flow matching model (OT-CFM), and a grapheme to phoneme prediction model, to generate realistic speech that closely mimics human utterances. Our evaluation demonstrates BreezyVoice's superior performance in both general and code-switching contexts, highlighting its robustness and effectiveness in generating high-fidelity speech. Additionally, we address the challenges of generalizability in modeling long-tail speakers and polyphone disambiguation. Our approach significantly enhances performance and offers valuable insights into the workings of neural codec TTS systems.
Forward citations
Cited by 4 Pith papers
-
The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation
Emotion embedding similarities are unsuitable for zero-shot evaluation of emotional expressiveness in speech generation due to confounding by non-emotional acoustic features.
-
On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
Global token perplexity mis-ranks spoken language models; localized/normalized likelihood scores and an embedding judge track human MOS better and make the best model look much closer to human.
-
Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternative
Fake-Mamba reports EERs of 0.97%, 1.74%, and 5.85% on three speech deepfake benchmarks, but the provided full text is an unrelated paper, so the claims cannot be verified.
-
A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data
Fine-tuning Whisper-large-v2 on 10,000 hours of synthesized Mandarin plus small real English/code-switching sets yields Twister, cutting mixed error rate by up to 56% on code-switching and 19% on Taiwanese Mandarin.
Discussion (0). Continue with ORCID to comment.