English
Related papers

Related papers: Discrete Token Modeling for Multi-Stem Music Sourc…

200 papers

We propose an end-to-end trainable approach to single-channel speech separation with unknown number of speakers. Our approach extends the MulCat source separation backbone with additional output heads: a count-head to infer the number of…

Sound · Computer Science 2020-12-01 Junzhe Zhu , Raymond Yeh , Mark Hasegawa-Johnson

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…

Sound · Computer Science 2025-11-26 Genís Plaja-Roglans , Yun-Ning Hung , Xavier Serra , Igor Pereira

Target audio source separation with natural language queries presents a promising paradigm for extracting arbitrary audio events through arbitrary text descriptions. Existing methods mainly face two challenges, the difficulty in jointly…

Sound · Computer Science 2025-12-03 Xinlei Yin , Xiulian Peng , Xue Jiang , Zhiwei Xiong , Yan Lu

Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of…

Sound · Computer Science 2024-01-17 Feiyu Shen , Yiwei Guo , Chenpeng Du , Xie Chen , Kai Yu

Audio tokenization bridges continuous waveforms and multi-track music language models. In dual-track modeling, tokens should preserve three properties at once: high-fidelity reconstruction, strong predictability under a language model, and…

Sound · Computer Science 2026-04-02 Rui Lin , Zhiyue Wu , Jiahe Le , Kangdi Wang , Weixiong Chen , Junyu Dai , Tao Jiang

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

Audio codecs are a critical component of modern speech generation systems. This paper introduces a low-bitrate, multi-scale residual codec that encodes speech into four distinct streams: semantic, timbre, prosody, and residual. This…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-25 Jingyu Li , Guangyan Zhang , Zhen Ye , Yiwen Guo

Generating sound effects that humans want is an important topic. However, there are few studies in this area for sound generation. In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound…

Sound · Computer Science 2023-05-01 Dongchao Yang , Jianwei Yu , Helin Wang , Wen Wang , Chao Weng , Yuexian Zou , Dong Yu

Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-30 Yang Yang , Yunpeng Li , George Sung , Shao-Fu Shih , Craig Dooley , Alessio Centazzo , Ramanan Rajeswaran

Most music source separation systems require large collections of isolated sources for training, which can be difficult to obtain. In this work, we use musical scores, which are comparatively easy to obtain, as a weak label for training a…

Sound · Computer Science 2020-10-23 Yun-Ning Hung , Gordon Wichern , Jonathan Le Roux

Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Although these models can generate speech with high quality and…

Sound · Computer Science 2024-08-30 Zehai Tu , Guangyan Zhang , Yiting Lu , Adaeze Adigwe , Simon King , Yiwen Guo

Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio…

Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a…

Sound · Computer Science 2025-11-27 Genís Plaja-Roglans , Yun-Ning Hung , Xavier Serra , Igor Pereira

In this work, we introduce the demonstration of symbolic music generation, focusing on providing short musical motifs that serve as the central theme of the narrative. For the generation, we adopt an autoregressive model which takes musical…

Supervised multi-channel audio source separation requires extracting useful spectral, temporal, and spatial features from the mixed signals. The success of many existing systems is therefore largely dependent on the choice of features used…

Sound · Computer Science 2018-03-05 Emad M. Grais , Dominic Ward , Mark D. Plumbley

Recent advancements in generative models have shown remarkable progress in music generation. However, most existing methods focus on generating monophonic or homophonic music, while the generation of polyphonic and multi-track music with…

Sound · Computer Science 2023-03-15 Hongfei Wang

Discrete representation learning has shown promising results across various domains, including generation and understanding in image, speech and language. Inspired by these advances, we propose MuseTok, a tokenization method for symbolic…

In this work, we propose a flexible method for generating variations of discrete sequences in which tokens can be grouped into basic units, like sentences in a text or bars in music. More precisely, given a template sequence, we aim at…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-22 Gaëtan Hadjeres , Léopold Crestel

Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely…

Existing symbolic music generation methods usually utilize discriminator to improve the quality of generated music via global perception of music. However, considering the complexity of information in music, such as rhythm and melody, a…

Sound · Computer Science 2024-08-06 Zhedong Zhang , Liang Li , Jiehua Zhang , Zhenghui Hu , Hongkui Wang , Chenggang Yan , Jian Yang , Yuankai Qi