English
Related papers

Related papers: SAME: A Semantically-Aligned Music Autoencoder

200 papers

We present the Score-based Autoencoder for Multiscale Inference (SAMI), a method for unsupervised representation learning that combines the theoretical frameworks of diffusion models and VAEs. By unifying their respective evidence lower…

Machine Learning · Statistics 2025-12-23 Benjamin S. H. Lyo , Eero P. Simoncelli , Cristina Savin

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Shilong Zhang , He Zhang , Zhifei Zhang , Chongjian Ge , Shuchen Xue , Shaoteng Liu , Mengwei Ren , Soo Ye Kim , Yuqian Zhou , Qing Liu , Daniil Pakhomov , Kai Zhang , Zhe Lin , Ping Luo

Lead sheets have become commonplace in generative music research, being used as an initial compressed representation for downstream tasks like multitrack music generation and automatic arrangement. Despite this, researchers have often…

Sound · Computer Science 2023-10-18 Zachary Novack , Nikita Srivatsan , Taylor Berg-Kirkpatrick , Julian McAuley

Speech enhancement remains challenging due to the trade-off between efficiency and perceptual quality. In this paper, we introduce MAGE, a Masked Audio Generative Enhancer that advances generative speech enhancement through a compact and…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-16 The Hieu Pham , Tan Dat Nguyen , Phuong Thanh Tran , Joon Son Chung , Duc Dung Nguyen

Research on audio generation has progressively developed along both waveform-based and spectrogram-based directions, giving rise to diverse strategies for representing and generating audio. At the same time, advances in image synthesis have…

Sound · Computer Science 2026-04-17 Eleonora Ristori , Luca Bindini , Paolo Frasconi

Music recordings often suffer from audio quality issues such as excessive reverberation, distortion, clipping, tonal imbalances, and a narrowed stereo image, especially when created in non-professional settings without specialized equipment…

Sound · Computer Science 2026-05-06 Jan Melechovsky , Ambuj Mehrish , Abhinaba Roy , Dorien Herremans

Audio tokenizers are fundamental to unifying audio understanding and generation. Understanding requires high-level semantics, while generation demands semantic and acoustic details. Existing unified tokenizers jointly encode both in…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-28 Zhisheng Zhang , Xiang Li , Yixuan Zhou , Jing Peng , Guoyang Zeng , Zhiyong Wu

Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce. Addressing this issue, we introduce…

Machine Learning · Computer Science 2024-02-19 Mohammad Hossein Amani , Nicolas Mario Baldwin , Amin Mansouri , Martin Josifoski , Maxime Peyrard , Robert West

Recently, denoising diffusion models have demonstrated remarkable performance among generative models in various domains. However, in the speech domain, the application of diffusion models for synthesizing time-varying audio faces…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-13 Ji-Sang Hwang , Sang-Hoon Lee , Seong-Whan Lee

Existing state-of-the-art symbolic music generation models predominantly adopt autoregressive or hierarchical autoregressive architectures, modelling symbolic music as a sequence of attribute tokens with unidirectional temporal…

Sound · Computer Science 2025-08-29 Hongju Su , Ke Li , Lan Yang , Honggang Zhang , Yi-Zhe Song

Sound can convey significant information for spatial reasoning in our daily lives. To endow deep networks with such ability, we address the challenge of dense indoor prediction with sound in both 2D and 3D via cross-modal knowledge…

Computer Vision and Pattern Recognition · Computer Science 2023-09-21 Heeseung Yun , Joonil Na , Gunhee Kim

The aim of latent variable disentanglement is to infer the multiple informative latent representations that lie behind a data generation process and is a key factor in controllable data generation. In this paper, we propose a deep neural…

Sound · Computer Science 2023-09-07 Yiming Wu

Respiratory sound classification is hindered by the limited size, high noise levels, and severe class imbalance of benchmark datasets like ICBHI 2017. While Transformer-based models offer powerful feature extraction capabilities, they are…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-30 Atakan Işık , Selin Vulga Işık , Ahmet Feridun Işık , Mahşuk Taylan

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Machine Learning · Computer Science 2025-07-30 Viktoria Schuster

In recent years, artificial neural networks (ANNs) have become a universal tool for tackling real-world problems. ANNs have also shown great success in music-related tasks including music summarization and classification, similarity…

Sound · Computer Science 2020-01-08 Stefan Lattner

Audio-based generative models for music have seen great strides recently, but so far have not managed to produce full-length music tracks with coherent musical structure from text prompts. We show that by training a generative model on long…

Sound · Computer Science 2024-07-30 Zach Evans , Julian D. Parker , CJ Carr , Zack Zukowski , Josiah Taylor , Jordi Pons

Binaural stereo audio is recorded by imitating the way the human ear receives sound, which provides people with an immersive listening experience. Existing approaches leverage autoencoders and directly exploit visual spatial information to…

Sound · Computer Science 2023-11-15 Zhaojian Li , Bin Zhao , Yuan Yuan

Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks, but they often suffer from common issues such as semantic misalignment and poor temporal consistency due to limited natural language understanding and data…

The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data. However, it has thus far seen limited application to sequential data, and, as we…

Machine Learning · Computer Science 2019-11-12 Adam Roberts , Jesse Engel , Colin Raffel , Curtis Hawthorne , Douglas Eck

Neural audio codecs, neural networks which compress a waveform into discrete tokens, play a crucial role in the recent development of audio generative models. State-of-the-art codecs rely on the end-to-end training of an autoencoder and a…

Sound · Computer Science 2025-03-26 Zineb Lahrichi , Gaëtan Hadjeres , Gael Richard , Geoffroy Peeters