mlsanityData to 14 Oct 2026

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech

arXiv 2607.06054 ↗First posted 7 Jul 2026cs.SD cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Off-the-shelf TTS systems are poorly adapted to Taiwanese Mandarin. Their accent defaults to other Mandarin variants, their tokenizers over-segment common Taiwanese text, and their pronunciation degrades at code-switching boundaries where Chinese and English alternate within one utterance. These problems share one root: the text side lacks adaptation to the Taiwanese context. We address the text side from the bottom up. PangolinTokenizer, a byte-level BPE tokenizer trained on Taiwan-context data, reaches the lowest token rate (0.485 tokens/character) with the smallest vocabulary among nine tokenizers. Barbet, a billion-parameter Traditional-Chinese language model trained on PangolinTokenizer, serves as the text-semantic frontend and ranks first among comparable public models on a 14-task evaluation. BlueMagpie-TTS attaches Barbet to the pretrained acoustic stack of VoxCPM2 through a learned bridge, keeping the acoustic stack fixed. On a 1000-sentence Taiwan-localized test set, it lowers CER from 11.45% to 4.81% and WER from 14.83% to 5.36%, relative reductions of 58.0% and 63.9%. In a blind listening study on 500 of these sentences with ten listeners, 65.6% of majority votes prefer BlueMagpie-TTS.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 35 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

30 of 35 references.

References · 30

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2024Qwen2.5 Technical Reportcited by 4,942
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  5. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  6. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  7. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  8. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  9. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  10. 2025Gemma 3 Technical Reportcited by 1,824
  11. 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,346
  12. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
18 more
  1. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  2. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 723
  3. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
  4. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
  5. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  6. 2021ByT5: Towards a token-free future with pre-trained byte-to-byte modelscited by 509
  7. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  8. 2020How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Modelscited by 318
  9. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 300
  10. 2021CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representationcited by 232
  11. 2023Language Model Tokenizers Introduce Unfairness Between Languagescited by 214
  12. 2023Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Modelscited by 192
  13. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  14. 2023Tokenization and the Noiseless Channelcited by 59
  15. 2025VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloningcited by 42
  16. 2023Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Modelcited by 29
  17. 2026VoxCPM2 Technical Reportcited by 17
  18. 2024Measuring Taiwanese Mandarin Language Understandingcited by 2

Built on by

Not cited yet.