SEmoEdit: Probing and Harnessing the Editability of Pre-trained Speech Flows
cs.SD, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/imxtx/SEmoEdit
Sources
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- Bagpiper-Edit: Zero-Shot Open-Ended Audio Editing via Rich-Caption
- Qwen3-TTS Technical Report
- AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing
- MMAE: A Massive Multitask Audio Editing Benchmark
- A Unified Neural Codec Language Model for Selective Editable Text to Speech Generation
- dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model
- EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation Steering
- Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation
- Step-Audio-EditX Technical Report
- SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
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