MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data

• URL: http://arxiv.org/abs/2606.18485v1
• Date: Tue, 16 Jun 2026 20:58:26 GMT
• Title: MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data
• Abstract summary: We present an inference-time approach called MagpieTTS-LF that enables MagpieTTS to produce coherent long-form speech without model retraining.<n>Our method introduces three key innovations: (1) soft attention priors to guide monotonic alignment while preserving past and future context; (2) a stateful inference algorithm that maintains context across sentence chunks; and (3) history-aware text encoding that uses past text for discourse-level prosodic planning.
• Score: 13.076032296543032
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural Text-to-Speech (TTS) systems achieve remarkable quality on short utterances but long-form speech generation shows prosodic drift, speaker inconsistencies and sentence boundary artifacts. Existing approaches either compress sequences, increase context length or naively concatenate independently synthesized chunks. We present an inference-time approach called MagpieTTS-LF that enables MagpieTTS to produce coherent long-form speech without model retraining. Our method introduces three key innovations: (1) soft attention priors to guide monotonic alignment while preserving past and future context; (2) a stateful inference algorithm that maintains context across sentence chunks, ensuring prosodic continuity; (3) history-aware text encoding that uses past text for discourse-level prosodic planning. Experiments on long texts show significant improvements in long-range intelligibility, prosodic coherence, speaker consistency, and boundary naturalness compared to other baselines.

Related papers

• Borderless Long Speech Synthesis [30.36601404142387]
  We introduce the Borderless Long Speech Synthesis framework for agent-centric, borderless long audio synthesis.<n>Rather than targeting a single narrow task, the system is designed as a unified capability set spanning VoiceDesigner, multi-speaker synthesis, Instruct TTS, and long-form text synthesis.
  arXiv  Detail & Related papers  (2026-03-20T09:37:54Z)
• MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance [66.74042564585942]
  MOSS-Speech is a true speech-to-speech large language model that directly understands and generates speech without relying on text guidance.<n>Our work establishes a new paradigm for expressive and efficient end-to-end speech interaction.
  arXiv  Detail & Related papers  (2025-10-01T04:32:37Z)
• GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM [42.93855899824886]
  We propose a text-to-speech generation approach optimized via a novel dual-branch ArchiTecture (GOAT-TTS)<n>GOAT-TTS combines a speech encoder and projector to capture continuous acoustic embeddings, enabling bidirectional correlation between paralinguistic features (language, timbre, emotion) and semantic text representations without transcript dependency.<n> Experimental results demonstrate that our GOAT-TTS achieves performance comparable to state-of-the-art TTS models.
  arXiv  Detail & Related papers  (2025-04-15T01:44:56Z)
• A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation [48.84039953531355]
  We propose a novel non-autoregressive generation framework for simultaneous speech translation (NAST-S2X) NAST-S2X integrates speech-to-text and speech-to-speech tasks into a unified end-to-end framework. It achieves high-quality simultaneous interpretation within a delay of less than 3 seconds and provides a 28 times decoding speedup in offline generation.
  arXiv  Detail & Related papers  (2024-06-11T04:25:48Z)
• Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP [18.90593650641679]
  A two-stage automatic annotation pipeline is proposed in this paper. In the first stage, we use contrastive pretraining of Speech-Silence and Word-Punctuation pairs to enhance prosodic information in latent representations. In the second stage, we build a multi-modal prosody annotator, comprising pretrained encoders, a text-speech fusing scheme, and a sequence classifier. Experiments on English prosodic boundaries demonstrate that our method achieves state-of-the-art (SOTA) performance with 0.72 and 0.93 f1 score for Prosodic Word and Prosodic Phrase
  arXiv  Detail & Related papers  (2023-09-11T12:50:28Z)
• ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading [65.88161811719353]
  This work develops a lightweight yet effective Text-to-Speech system, ContextSpeech. We first design a memory-cached recurrence mechanism to incorporate global text and speech context into sentence encoding. We construct hierarchically-structured textual semantics to broaden the scope for global context enhancement. Experiments show that ContextSpeech significantly improves the voice quality and prosody in paragraph reading with competitive model efficiency.
  arXiv  Detail & Related papers  (2023-07-03T06:55:03Z)
• token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text [65.04385919645395]
  token2vec is a novel joint pre-training framework for unpaired speech and text based on discrete representations of speech. Experiments show that token2vec is significantly superior to various speech-only pre-training baselines, with up to 17.7% relative WER reduction.
  arXiv  Detail & Related papers  (2022-10-30T06:38:19Z)
• FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis [75.74906149219817]
  Conversational Text-to-Speech (TTS) aims to synthesis an utterance with the right linguistic and affective prosody in a conversational context. We propose a novel expressive conversational TTS model, as termed FCTalker, that learn the fine and coarse grained context dependency at the same time during speech generation.
  arXiv  Detail & Related papers  (2022-10-27T12:20:20Z)
• Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence [59.51720326054546]
  We propose a long text generation model, which can represent the prefix sentences at sentence level and discourse level in the decoding process. Our model can generate more coherent texts than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2021-05-19T07:29:08Z)

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.