VoxCanvas-41M: A Large-Scale Bilingual Dataset for Instruction-Based Speech Editing and Its Learning Dynamics
cs.SD, eess.AS
Submitted: 2026-11-05
Updated: 2026-11-06
Code: https://github.com/ZhikangNiu/VoxCanvas
Terminology
Sources
- Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
- NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech
- CosyEdit2: Speech-Editing-Oriented Reinforcement Learning Unlocks Better Zero-Shot TTS
- CosyEdit: Unlocking End-to-End Speech Editing Capability from Zero-Shot Text-to-Speech Models
- ISSE: An Instruction-Guided Speech Style Editing Dataset And Benchmark
- Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
- Fish Audio Drama 3 Technical Report
- LoRA: Low-Rank Adaptation of Large Language Models
- NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations
- AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing
- MMAE: A Massive Multitask Audio Editing Benchmark
- LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models
- Learning Dynamics of LLM Finetuning
- Qwen3-ASR Technical Report
- dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model
- SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
- Paint by Inpaint: Learning to Add Image Objects by Removing Them First
- ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion
- Qwen2.5-Omni Technical Report
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- 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