English
Related papers

Related papers: Real-time Timbre Remapping with Differentiable DSP

200 papers

In this paper, we learn disentangled representations of timbre and pitch for musical instrument sounds. We adapt a framework based on variational autoencoders with Gaussian mixture latent distributions. Specifically, we use two separate…

Machine Learning · Computer Science 2019-07-02 Yin-Jyun Luo , Kat Agres , Dorien Herremans

In recent years, research on music transcription has focused mainly on architecture design and instrument-specific data acquisition. With the lack of availability of diverse datasets, progress is often limited to solo-instrument tasks such…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-25 Frank Cwitkowitz , Kin Wai Cheuk , Woosung Choi , Marco A. Martínez-Ramírez , Keisuke Toyama , Wei-Hsiang Liao , Yuki Mitsufuji

Disentanglement of a speaker's timbre and style is very important for style transfer in multi-speaker multi-style text-to-speech (TTS) scenarios. With the disentanglement of timbres and styles, TTS systems could synthesize expressive speech…

Sound · Computer Science 2022-11-23 Wei Song , Yanghao Yue , Ya-jie Zhang , Zhengchen Zhang , Youzheng Wu , Xiaodong He

We present the Latent Timbre Synthesis (LTS), a new audio synthesis method using Deep Learning. The synthesis method allows composers and sound designers to interpolate and extrapolate between the timbre of multiple sounds using the latent…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-03 K. Tatar , D. Bisig , P. Pasquier

In this paper, we present a novel audio synthesizer, CAESynth, based on a conditional autoencoder. CAESynth synthesizes timbre in real-time by interpolating the reference sounds in their shared latent feature space, while controlling a…

Sound · Computer Science 2021-11-10 Aaron Valero Puche , Sukhan Lee

Instrumental playing techniques such as vibratos, glissandos, and trills often denote musical expressivity, both in classical and folk contexts. However, most existing approaches to music similarity retrieval fail to describe timbre beyond…

Music creation involves not only composing the different parts (e.g., melody, chords) of a musical work but also arranging/selecting the instruments to play the different parts. While the former has received increasing attention, the latter…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-03 Yun-Ning Hung , I-Tung Chiang , Yi-An Chen , Yi-Hsuan Yang

Recent research in zero-shot speech synthesis has made significant progress in speaker similarity. However, current efforts focus on timbre generalization rather than prosody modeling, which results in limited naturalness and…

Sound · Computer Science 2024-06-12 Yuepeng Jiang , Tao Li , Fengyu Yang , Lei Xie , Meng Meng , Yujun Wang

Understanding and manipulating timbre is central to audio synthesis, yet this remains under-explored in machine learning due to a lack of annotated datasets linking perceptual timbre dimensions to semantic descriptors. We present the…

Sound · Computer Science 2026-03-18 Joseph Cameron , Alan Blackwell

Generating multi-instrument music from symbolic music representations is an important task in Music Information Retrieval (MIR). A central but still largely unsolved problem in this context is musically and acoustically informed control in…

Sound · Computer Science 2023-09-22 Ben Maman , Johannes Zeitler , Meinard Müller , Amit H. Bermano

This paper proposes a framework of explaining anomalous machine sounds in the context of anomalous sound detection~(ASD). While ASD has been extensively explored, identifying how anomalous sounds differ from normal sounds is also beneficial…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-30 Tomoya Nishida , Harsh Purohit , Kota Dohi , Takashi Endo , Yohei Kawaguchi

Musical expression requires control of both what notes are played, and how they are performed. Conventional audio synthesizers provide detailed expressive controls, but at the cost of realism. Black-box neural audio synthesis and…

Modern text-to-speech systems are able to produce natural and high-quality speech, but speech contains factors of variation (e.g. pitch, rhythm, loudness, timbre)\ that text alone cannot contain. In this work we move towards a speech…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Giorgio Fabbro , Vladimir Golkov , Thomas Kemp , Daniel Cremers

In this study, we define the identity of the singer with two independent concepts - timbre and singing style - and propose a multi-singer singing synthesis system that can model them separately. To this end, we extend our single-singer…

Sound · Computer Science 2019-10-30 Juheon Lee , Hyeong-Seok Choi , Junghyun Koo , Kyogu Lee

Modulations are a critical part of sound design and music production, enabling the creation of complex and evolving audio. Modern synthesizers provide envelopes, low frequency oscillators (LFOs), and more parameter automation tools that…

Sound · Computer Science 2025-10-08 Christopher Mitcheltree , Hao Hao Tan , Joshua D. Reiss

Psychoacoustical so-called "timbre spaces" map perceptual similarity ratings of instrument sounds onto low-dimensional embeddings via multidimensional scaling, but suffer from scalability issues and are incapable of generalization. Recent…

Sound · Computer Science 2025-07-11 Haokun Tian , Stefan Lattner , Charalampos Saitis

Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design. Each parameters configuration of a synthesizer produces a unique timbre and can be viewed as a unique instrument.…

Sound · Computer Science 2022-07-29 Zui Chen , Yansen Jing , Shengcheng Yuan , Yifei Xu , Jian Wu , Hang Zhao

Deep generative models are now able to synthesize high-quality audio signals, shifting the critical aspect in their development from audio quality to control capabilities. Although text-to-music generation is getting largely adopted by the…

Sound · Computer Science 2024-08-02 Nils Demerlé , Philippe Esling , Guillaume Doras , David Genova

A differentiable digital signal processing (DDSP) autoencoder is a musical sound synthesizer that combines a deep neural network (DNN) and spectral modeling synthesis. It allows us to flexibly edit sounds by changing the fundamental…

Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge of how sound is…

Machine Learning · Computer Science 2020-01-15 Jesse Engel , Lamtharn Hantrakul , Chenjie Gu , Adam Roberts