mlsanityData to 7 Oct 2026

Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input

arXiv 2603.06444 ↗First posted 6 Mar 2026cs.SD cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to unbounded context. We propose a prosodic-boundary-aware post-training strategy, adapting a pretrained LLM-based TTS model using weakly time-aligned data. Specifically, the model is adapted to learn early stopping at specified content boundaries when provided with limited future text. During inference, a sliding-window prompt carries forward previous text and speech tokens, ensuring bounded context and seamless concatenation. Evaluations show our method outperforms CosyVoice-Style interleaved baseline in both short and long-form scenarios. In long-text synthesis, especially, it achieves a 66.2% absolute reduction in word error rate (from 71.0% to 4.8%) and increases speaker and emotion similarity by 16.1% and 1.5% relatively, offering a robust solution for streaming TTS with incremental text.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 26 references that are in the map. First posted on arXiv 6 Mar 2026.

Builds on

22 of 26 references.

References · 22

  1. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  2. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  3. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
  4. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
  5. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 536
  6. 2023WhisperX: Time-Accurate Speech Transcription of Long-Form Audiocited by 320
  7. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 293
  8. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 282
  9. 2023emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representationcited by 196
  10. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 142
  11. 2024Spirit LM: Interleaved Spoken and Written Language Modelcited by 123
  12. 2026Qwen3-TTS Technical Reportcited by 106
10 more
  1. 2022A3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editingcited by 40
  2. 2024LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codescited by 13
  3. 2023Speak While You Think: Streaming Speech Synthesis During Text Generationcited by 8
  4. 2025SpeakStream: Streaming Text-to-Speech with Interleaved Datacited by 8
  5. 2023Transduce and Speak: Neural Transducer for Text-to-Speech with Semantic Token Predictioncited by 7
  6. 2024Zero-Shot Text-to-Speech from Continuous Text Streamscited by 7
  7. 2025Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesiscited by 7
  8. 2024Interleaved Speech-Text Language Models for Simple Streaming Text-to-Speech Synthesiscited by 6
  9. 2025Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modelingcited by 3
  10. 2025StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modelingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026X2Streaming-TTS: Causal Token-Level Text-to-Speech from Streaming Text with Speech-State Inheritancecited by 0