Pith. sign in

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

arxiv 2501.17790 v1 pith:MFHSSBTW submitted 2025-01-29 cs.CL cs.AI

classification cs.CLcs.AI
keywords breezyvoicechallengesdisambiguationmodelpolyphoneaddresshighlightinginsights
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation

    eess.AS 2026-04 unverdicted novelty 6.0 of 10

    Emotion embedding similarities are unsuitable for zero-shot evaluation of emotional expressiveness in speech generation due to confounding by non-emotional acoustic features.

  2. On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation

    cs.CL 2026-01 conditional novelty 6.0 of 10

    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.

  3. Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternative

    eess.AS 2025-08 unverdicted novelty 5.0 of 10

    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.

  4. A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data

    cs.CL 2025-06 conditional novelty 5.0 of 10

    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.

Pith tools