63 citations · 364 across the 60 of their papers we have counts for
22 papers · 1 filter
VRDMG: Vocal Restoration via Diffusion Posterior Sampling with Multiple Guidance
Carlos Hernandez-Olivan, Koichi Saito, Naoki Murata +4
Restoring degraded music signals is essential to enhance audio quality for downstream music manipulation. Recent diffusion-based music restoration methods have demonstrated impress…
Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription
Frank Cwitkowitz, Kin Wai Cheuk, Woosung Choi +4
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 datase…
The Sound Demixing Challenge 2023 $\unicode{x2013}$ Cinematic Demixing Track
Stefan Uhlich, Giorgio Fabbro, Masato Hirano +14
This paper summarizes the cinematic demixing (CDX) track of the Sound Demixing Challenge 2023 (SDX'23). We provide a comprehensive summary of the challenge setup, detailing the str…
The Sound Demixing Challenge 2023 $\unicode{x2013}$ Music Demixing Track
Giorgio Fabbro, Stefan Uhlich, Chieh-Hsin Lai +24
This paper summarizes the music demixing (MDX) track of the Sound Demixing Challenge (SDX'23). We provide a summary of the challenge setup and introduce the task of robust music so…
The Whole Is Greater than the Sum of Its Parts: Improving Music Source Separation by Bridging Network
Ryosuke Sawata, Naoya Takahashi, Stefan Uhlich +2
This paper presents the crossing scheme (X-scheme) for improving the performance of deep neural network (DNN)-based music source separation (MSS) with almost no increasing calculat…
Diffusion-based Signal Refiner for Speech Enhancement and Separation
Masato Hirano, Ryosuke Sawata, Naoki Murata +2
Although recent speech processing technologies have achieved significant improvements in objective metrics, there still remains a gap in human perceptual quality. This paper propos…
Unsupervised vocal dereverberation with diffusion-based generative models
Koichi Saito, Naoki Murata, Toshimitsu Uesaka +4
Removing reverb from reverberant music is a necessary technique to clean up audio for downstream music manipulations. Reverberation of music contains two categories, natural reverb…
Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects
Junghyun Koo, Marco A. Martínez-Ramírez, Wei-Hsiang Liao +3
We propose an end-to-end music mixing style transfer system that converts the mixing style of an input multitrack to that of a reference song. This is achieved with an encoder pre-…
Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement
Ryosuke Sawata, Naoki Murata, Yuhta Takida +4
Although deep neural network (DNN)-based speech enhancement (SE) methods outperform the previous non-DNN-based ones, they often degrade the perceptual quality of generated outputs.…
Automatic music mixing with deep learning and out-of-domain data
Marco A. Martínez-Ramírez, Wei-Hsiang Liao, Giorgio Fabbro +3
Music mixing traditionally involves recording instruments in the form of clean, individual tracks and blending them into a final mixture using audio effects and expert knowledge (e…
STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events
Archontis Politis, Kazuki Shimada, Parthasaarathy Sudarsanam +7
This report presents the Sony-TAu Realistic Spatial Soundscapes 2022 (STARS22) dataset for sound event localization and detection, comprised of spatial recordings of real scenes co…
Distortion Audio Effects: Learning How to Recover the Clean Signal
Johannes Imort, Giorgio Fabbro, Marco A. Martínez Ramírez +3
Given the recent advances in music source separation and automatic mixing, removing audio effects in music tracks is a meaningful step toward developing an automated remixing syste…
Spatial mixup: Directional loudness modification as data augmentation for sound event localization and detection
Ricardo Falcon-Perez, Kazuki Shimada, Yuichiro Koyama +2
Data augmentation methods have shown great importance in diverse supervised learning problems where labeled data is scarce or costly to obtain. For sound event localization and det…
Multi-ACCDOA: Localizing and Detecting Overlapping Sounds from the Same Class with Auxiliary Duplicating Permutation Invariant Training
Kazuki Shimada, Yuichiro Koyama, Shusuke Takahashi +3
Sound event localization and detection (SELD) involves identifying the direction-of-arrival (DOA) and the event class. The SELD methods with a class-wise output format make the mod…
Music Demixing Challenge 2021
Yuki Mitsufuji, Giorgio Fabbro, Stefan Uhlich +6
Music source separation has been intensively studied in the last decade and tremendous progress with the advent of deep learning could be observed. Evaluation campaigns such as MIR…
Ensemble of ACCDOA- and EINV2-based Systems with D3Nets and Impulse Response Simulation for Sound Event Localization and Detection
Kazuki Shimada, Naoya Takahashi, Yuichiro Koyama +4
This report describes our systems submitted to the DCASE2021 challenge task 3: sound event localization and detection (SELD) with directional interference. Our previous system base…
Training Speech Enhancement Systems with Noisy Speech Datasets
Koichi Saito, Stefan Uhlich, Giorgio Fabbro +1
Recently, deep neural network (DNN)-based speech enhancement (SE) systems have been used with great success. During training, such systems require clean speech data - ideally, in l…
ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detection
Kazuki Shimada, Yuichiro Koyama, Naoya Takahashi +2
Neural-network (NN)-based methods show high performance in sound event localization and detection (SELD). Conventional NN-based methods use two branches for a sound event detection…
All for One and One for All: Improving Music Separation by Bridging Networks
Ryosuke Sawata, Stefan Uhlich, Shusuke Takahashi +1
This paper proposes several improvements for music separation with deep neural networks (DNNs), namely a multi-domain loss (MDL) and two combination schemes. First, by using MDL we…
D3Net: Densely connected multidilated DenseNet for music source separation
Naoya Takahashi, Yuki Mitsufuji
Music source separation involves a large input field to model a long-term dependence of an audio signal. Previous convolutional neural network (CNN)-based approaches address the la…
Sound Event Localization and Detection Using Activity-Coupled Cartesian DOA Vector and RD3net
Kazuki Shimada, Naoya Takahashi, Shusuke Takahashi +1
Our systems submitted to the DCASE2020 task~3: Sound Event Localization and Detection (SELD) are described in this report. We consider two systems: a single-stage system that solve…
Closing the Training/Inference Gap for Deep Attractor Networks
Cyril Cadoux, Stefan Uhlich, Marc Ferras +1
This paper improves the deep attractor network (DANet) approach by closing its gap between training and inference. During training, DANet relies on attractors, which are computed f…