English
Related papers

Related papers: Modeling Music as a Time-Frequency Image: A 2D Tok…

200 papers

While most music generation models use textual or parametric conditioning (e.g. tempo, harmony, musical genre), we propose to condition a language model based music generation system with audio input. Our exploration involves two distinct…

Sound · Computer Science 2024-07-31 Simon Rouard , Yossi Adi , Jade Copet , Axel Roebel , Alexandre Défossez

Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Qihang Rao , Borui Zhang , Wenzhao Zheng , Jie Zhou , Jiwen Lu

Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective -- reconstructing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Jiawei Yang , Tianhong Li , Lijie Fan , Yonglong Tian , Yue Wang

Efficiently representing audio signals in a compressed latent space is critical for latent generative modelling. However, existing autoencoders often force a choice between continuous embeddings and discrete tokens. Furthermore, achieving…

Sound · Computer Science 2025-09-15 Marco Pasini , Stefan Lattner , George Fazekas

We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for…

Computation and Language · Computer Science 2025-05-28 Lingwei Meng , Long Zhou , Shujie Liu , Sanyuan Chen , Bing Han , Shujie Hu , Yanqing Liu , Jinyu Li , Sheng Zhao , Xixin Wu , Helen Meng , Furu Wei

We introduce Cadenza, a new multi-stage generative framework for predicting expressive variations of symbolic musical ideas as well as unconditional generations. To accomplish this we propose a novel MIDI encoding method, PerTok…

Sound · Computer Science 2024-10-04 Julian Lenz , Anirudh Mani

Autoregressive (AR) language models rely on causal tokenization, but extending this paradigm to vision remains non-trivial. Current visual tokenizers either flatten 2D patches into non-causal sequences or enforce heuristic orderings that…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Yitong Chen , Zuxuan Wu , Xipeng Qiu , Yu-Gang Jiang

In audio processing applications, the generation of expressive sounds based on high-level representations demonstrates a high demand. These representations can be used to manipulate the timbre and influence the synthesis of creative…

Sound · Computer Science 2023-01-19 Anastasia Natsiou , Luca Longo , Sean O'Leary

Symbolic music generation faces a fundamental trade-off between efficiency and quality. Fine-grained tokenizations achieve strong coherence but incur long sequences and high complexity, while compact tokenizations improve efficiency at the…

Machine Learning · Computer Science 2025-09-30 Ting-Kang Wang , Chih-Pin Tan , Yi-Hsuan Yang

Recent years have witnessed the success of foundation models pre-trained with self-supervised learning (SSL) in various music informatics understanding tasks, including music tagging, instrument classification, key detection, and more. In…

Sound · Computer Science 2025-01-06 Haina Zhu , Yizhi Zhou , Hangting Chen , Jianwei Yu , Ziyang Ma , Rongzhi Gu , Yi Luo , Wei Tan , Xie Chen

Music generation schemes using language modeling rely on a vocabulary of audio tokens, generally provided as codes in a discrete latent space learnt by an auto-encoder. Multi-stage quantizers are often employed to produce these tokens,…

Sound · Computer Science 2024-06-11 Jean-Marie Lemercier , Simon Rouard , Jade Copet , Yossi Adi , Alexandre Défossez

Music generation introduces challenging complexities to large language models. Symbolic structures of music often include vertical harmonization as well as horizontal counterpoint, urging various adaptations and enhancements for large-scale…

Sound · Computer Science 2024-07-30 Seungyeon Rhyu , Kichang Yang , Sungjun Cho , Jaehyeon Kim , Kyogu Lee , Moontae Lee

VQ-based image generation typically follows a two-stage pipeline: a tokenizer encodes images into discrete tokens, and a generative model learns their dependencies for reconstruction. However, improved tokenization in the first stage does…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Bin Wu , Mengqi Huang , Weinan Jia , Zhendong Mao

Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the…

Sound · Computer Science 2024-12-18 Kai Qiu , Xiang Li , Hao Chen , Jie Sun , Jinglu Wang , Zhe Lin , Marios Savvides , Bhiksha Raj

Historically, most speech models in machine-learning have used the mel-spectrogram as a speech representation. Recently, discrete audio tokens produced by neural audio codecs have become a popular alternate speech representation for speech…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-05 Ryan Langman , Ante Jukić , Kunal Dhawan , Nithin Rao Koluguri , Jason Li

Controllable music generation plays a vital role in human-AI music co-creation. While Large Language Models (LLMs) have shown promise in generating high-quality music, their focus on autoregressive generation limits their utility in music…

Sound · Computer Science 2024-10-08 Liwei Lin , Gus Xia , Yixiao Zhang , Junyan Jiang

Neural audio codecs and autoencoders have emerged as versatile models for audio compression, transmission, feature-extraction, and latent-space generation. However, a key limitation is that most are trained to maximize reconstruction…

Sound · Computer Science 2025-09-10 Dimitrios Bralios , Jonah Casebeer , Paris Smaragdis

Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images. Tokenization, which transforms images into latent representations, reduces computational…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Qihang Yu , Mark Weber , Xueqing Deng , Xiaohui Shen , Daniel Cremers , Liang-Chieh Chen

Autoregressive (AR) models for image generation typically adopt a two-stage paradigm of vector quantization and raster-scan ``next-token prediction", inspired by its great success in language modeling. However, due to the huge modality gap,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Hu Yu , Hao Luo , Hangjie Yuan , Yu Rong , Jie Huang , Feng Zhao

Automatic generation of sequences has been a highly explored field in the last years. In particular, natural language processing and automatic music composition have gained importance due to the recent advances in machine learning and…

Sound · Computer Science 2020-12-03 Sebastian Garcia-Valencia , Alejandro Betancourt , Juan G. Lalinde-Pulido