dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model

arXiv:2608.02673 · cs.SD, cs.AI, cs.CL, eess.AS · Submitted 2026-08-02 · Read on arXiv

cs.SD, cs.AI, cs.CL, eess.AS

Submitted: 2026-08-02

Updated: 2026-09-28

Code: https://github.com/studio-dots-ai/dots.tts

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Editor — 14× in this paper · explained in 2 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Benchmark — 8× in this paper · explained in 2 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Foundation Model — 5× in this paper · explained in 3 episodes
• Flow Matching — 4× in this paper · explained in 15 episodes
• Generator — 3× in this paper · explained in 2 episodes
• Planner — 3× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Evaluation Dimensions — 2× in this paper · explained in 3 episodes
• Provenance — 2× in this paper · explained in 5 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Weight Decay — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Decoder — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 10 episodes
• Diffusion Models — 1× in this paper · explained in 9 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Papers — 1× in this paper · explained in 3 episodes
• Positional Bias — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Training Objective — 1× in this paper · explained in 2 episodes
• Transformers — 1× in this paper · explained in 2 episodes

Sources

• EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion
• CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing
• MMAE: A Massive Multitask Audio Editing Benchmark
• dots.tts Technical Report
• FluentEditor: Text-based Speech Editing by Considering Acoustic and Prosody Consistency
• UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding
• Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
• SpeechX: Neural Codec Language Model as a Versatile Speech Transformer
• Step-Audio-EditX Technical Report
• A Unified Neural Codec Language Model for Selective Editable Text to Speech Generation
• Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation
• UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling
• Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
• SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
• Qwen3-ASR Technical Report
• Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
• F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
• IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
• HoliTok: A Continuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding
• Flow Matching for Generative Modeling

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs