paper-with-me

Papers

InstructAudio: Unified speech and music generation with natural language instruction

2025-11-23 · Chunyu Qiang, Kang Yin, Xiaopeng Wang, Yuzhe Liang, Jiahui Zhao, Ruibo Fu, Tianrui Wang, Cheng Gong, Chen Zhang, Longbiao Wang, Jianwu Dang arxiv

Text-to-speech (TTS) and text-to-music (TTM) models face significant limitations in instruction-based control. TTS systems usually depend on reference audio for timbre, offer only limited text-level attribute control, and rarely support dialogue generation. TTM systems are constrained by input conditioning requirements that depend on expert knowledge annotations. The high heterogeneity of these input control conditions makes them difficult to joint modeling with speech synthesis. Despite sharing common acoustic modeling characteristics, these two tasks have long been developed independently, leaving open the challenge of achieving unified modeling through natural language instructions. We introduce InstructAudio, a unified framework that enables instruction-based (natural language descriptions) control of acoustic attributes including timbre (gender, age), paralinguistic (emotion, style, accent), and musical (genre, instrument, rhythm, atmosphere). It supports expressive speech, music, and dialogue generation in English and Chinese. The model employs joint and single diffusion transformer layers with a standardized instruction-phoneme input format, trained on 50K hours of speech and 20K hours of music data, enabling multi-task learning and cross-modal alignment. Fig. 1 visualizes performance comparisons with mainstream TTS and TTM models, demonstrating that InstructAudio achieves optimal results on most metrics. To our best knowledge, InstructAudio represents the first instruction-controlled framework unifying speech and music generation. Audio samples are available at: https://qiangchunyu.github.io/InstructAudio/

📄 PDF Abstract BibTeX arXiv:2511.18487

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task LearningDialogue GenerationMusic GenerationSpeech Synthesis

Similar Papers 제목 키워드 기반

AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining

2023-08-10 · Haohe Liu, Yi Yuan, Xubo Liu, Xinhao Mei 외

Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases th…

Audio GenerationIn-Context LearningRepresentation LearningText-to-Music Generation+2

Transferring neural speech waveform synthesizers to musical instrument sounds generation

2019-10-27 · Yi Zhao, Xin Wang, Lauri Juvela, Junichi Yamagishi

Recent neural waveform synthesizers such as WaveNet, WaveGlow, and the neural-source-filter (NSF) model have shown good performance in speech synthesis despite their different methods of waveform generation. The similari…

Audio GenerationAudio SynthesisSpeech SynthesisZero-Shot Learning

UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions

2026-04-24 · Chunyu Qiang, Xiaopeng Wang, Kang Yin, Yuzhe Liang 외 arxiv

Generative audio modeling has largely been fragmented into specialized tasks, text-to-speech (TTS), text-to-music (TTM), and text-to-audio (TTA), each operating under heterogeneous control paradigms. Unifying these modal…

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE

2025-10-15 · Zhenyu Liu, Yunxin Li, Xuanyu Zhang, Qixun Teng 외 arxiv

Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. However, the auditory domain remains a significant challenge, with music and speech often developed in isolati…

Audio GenerationMusic Generation

A correlation-permutation approach for speech-music encoders model merging

2025-06-13 · Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jeremy H. M Wong, Hung-Yi Lee 외

Creating a unified speech and music model requires expensive pre-training. Model merging can instead create an unified audio model with minimal computational expense. However, direct merging is challenging when the model…

Re-basin