mlsanityData to 14 Oct 2026

Comparative Evaluation of Expressive Japanese Character Text-to-Speech with VITS and Style-BERT-VITS2

arXiv 2505.17320 ↗First posted 22 May 2025cs.CL cs.SD eess.AScited by 1

Not on the map. Why?

Abstract (arXiv)

Synthesizing expressive Japanese character speech poses unique challenges due to pitch-accent sensitivity and stylistic variability. This paper empirically evaluates two open-source text-to-speech models--VITS and Style-BERT-VITS2 JP Extra (SBV2JE)--on in-domain, character-driven Japanese speech. Using three character-specific datasets, we evaluate models across naturalness (mean opinion and comparative mean opinion score), intelligibility (word error rate), and speaker consistency. SBV2JE matches human ground truth in naturalness (MOS 4.37 vs. 4.38), achieves lower WER, and shows slight preference in CMOS. Enhanced by pitch-accent controls and a WavLM-based discriminator, SBV2JE proves effective for applications like language learning and character dialogue generation, despite higher computational demands.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 28 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

14 of 28 references.

References · 14

  1. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
  2. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  3. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 490
  4. 2022Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkitcited by 97
  5. 2021PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTScited by 52
  6. 2023VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Designcited by 25
  7. 2020End-to-End Text-to-Speech using Latent Duration based on VQ-VAEcited by 7
  8. 2020Learning Speaker Embedding from Text-to-Speechcited by 7
  9. 2022Improving Speech Prosody of Audiobook Text-to-Speech Synthesis with Acoustic and Textual Contextscited by 6
  10. 2022Polyphone disambiguation and accent prediction using pre-trained language models in Japanese TTS front-endcited by 5
  11. 2022Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text datacited by 3
  12. 2024Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Promptingcited by 3
2 more
  1. 2022Adversarial Speaker-Consistency Learning Using Untranscribed Speech Data for Zero-Shot Multi-Speaker Text-to-Speechcited by 2
  2. 2022Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent languagecited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Re:Member: Emotional Question Generation from Personal Memoriescited by 0