Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder

• URL: http://arxiv.org/abs/2608.11650v1
• Date: Wed, 12 Aug 2026 04:48:29 GMT
• Title: Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder
• Abstract summary: We present Confucius4-TTS, a zero-shot text-to-speech system that supports 14 languages.<n>It performs both intra-lingual and cross-lingual reference cloning without requiring transcripts of audio prompts.<n>It achieves high intelligibility and speaker similarity on public benchmarks.
• Score: 14.769480661437774
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time. This dependency limits cross-lingual voice cloning, since in-the-wild reference audio is often untranscribed. In this technical report, we present Confucius4-TTS, a multilingual zero-shot TTS system that supports 14 languages and performs both intra-lingual and cross-lingual reference cloning without requiring transcripts of audio prompts. Confucius4-TTS follows a two-stage architecture, consisting of text-to-semantic (T2S) and semantic-to-acoustic (S2A) modules. The LLM-based T2S module uses a learnable speaker encoder to extract timbre features from self-supervised speech representations, and the conditional flow-matching S2A module converts the predicted semantic tokens into mel-spectrograms. The same model also supports continuation cloning when a reference transcript is available. Confucius4-TTS is trained on large-scale multilingual speech data. It achieves high intelligibility and speaker similarity on public benchmarks. On the CV3-Eval cross-lingual benchmark, Confucius4-TTS obtains an average WER of 3.73% across six directions. On our internal cross-lingual set, it achieves the best average overall rank in human evaluation among recent open-source and commercial systems. We release code, model checkpoints, and demos at https://github.com/netease-youdao/Confucius4-TTS.

Related papers

• X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning [62.740127542449166]
  X-Voice is a multilingual zero-shot voice cloning model that clones arbitrary voices and enables everyone to speak 30 languages.<n>X-Voice is trained on a 420K-hour multilingual corpus using the International Phonetic Alphabet (IPA) as a unified representation.
  arXiv  Detail & Related papers  (2026-05-07T02:57:53Z)
• Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens [31.575335190916995]
  We introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech that decomposes speech into two complementary token types.<n>To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations.
  arXiv  Detail & Related papers  (2025-03-03T16:23:10Z)
• IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System [6.686126079510178]
  We introduce the IndexTTS system, which is mainly based on the XTTS and Tortoise model.<n>Specifically, in Chinese scenarios, we adopt a hybrid modeling method that combines characters and pinyin.<n>Compared with XTTS, it has achieved significant improvements in naturalness, content consistency, and zero-shot voice cloning.
  arXiv  Detail & Related papers  (2025-02-08T10:23:20Z)
• Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias [71.94109664001952]
  Mega-TTS is a novel zero-shot TTS system that is trained with large-scale wild data. We show that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS speech editing, and cross-lingual TTS tasks.
  arXiv  Detail & Related papers  (2023-06-06T08:54:49Z)
• UnifySpeech: A Unified Framework for Zero-shot Text-to-Speech and Voice Conversion [63.346825713704625]
  Text-to-speech (TTS) and voice conversion (VC) are two different tasks aiming at generating high quality speaking voice according to different input modality. This paper proposes UnifySpeech, which brings TTS and VC into a unified framework for the first time.
  arXiv  Detail & Related papers  (2023-01-10T06:06:57Z)
• ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech [58.93395189153713]
  We extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes. Our model shows great improvements over speaker-embedding-based multi-speaker TTS methods.
  arXiv  Detail & Related papers  (2022-11-07T13:35:16Z)
• Textless Speech-to-Speech Translation on Real Data [49.134208897722246]
  We present a textless speech-to-speech translation (S2ST) system that can translate speech from one language into another language. We tackle the challenge in modeling multi-speaker target speech and train the systems with real-world S2ST data.
  arXiv  Detail & Related papers  (2021-12-15T18:56:35Z)
• AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data [115.38309338462588]
  We develop AdaSpeech 2, an adaptive TTS system that only leverages untranscribed speech data for adaptation. Specifically, we introduce a mel-spectrogram encoder to a well-trained TTS model to conduct speech reconstruction. In adaptation, we use untranscribed speech data for speech reconstruction and only fine-tune the TTS decoder.
  arXiv  Detail & Related papers  (2021-04-20T01:53:30Z)
• Towards Natural and Controllable Cross-Lingual Voice Conversion Based on Neural TTS Model and Phonetic Posteriorgram [21.652906261475533]
  Cross-lingual voice conversion is a challenging problem due to significant mismatches of the phonetic set and the speech prosody of different languages. We build upon the neural text-to-speech (TTS) model to design a new cross-lingual VC framework named FastSpeech-VC.
  arXiv  Detail & Related papers  (2021-02-03T10:28:07Z)
• Towards Natural Bilingual and Code-Switched Speech Synthesis Based on Mix of Monolingual Recordings and Cross-Lingual Voice Conversion [28.830575877307176]
  It is not easy to obtain a bilingual corpus from a speaker who achieves native-level fluency in both languages. A Tacotron2-based cross-lingual voice conversion system is employed to generate the Mandarin speaker's English speech and the English speaker's Mandarin speech. The obtained bilingual data are then augmented with code-switched utterances synthesized using a Transformer model.
  arXiv  Detail & Related papers  (2020-10-16T03:51:00Z)
• Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion [0.0]
  Cross-lingual voice conversion is a task that aims to synthesize target voices with the same content while source and target speakers speak in different languages. In this paper, we focus on knowledge transfer from monolin-gual ASR to cross-lingual VC. We successfully address cross-lingual VC without any transcription or language-specific knowledge for foreign speech.
  arXiv  Detail & Related papers  (2020-09-30T13:44:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.