相关论文: Spectrogram Feature Losses for Music Source Separa…

Key for solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed specifically to learn part-level discriminate…

In the context of music information retrieval, similarity-based approaches are useful for a variety of tasks that benefit from a query-by-example scenario. Music however, naturally decomposes into a set of semantically meaningful factors of…

Musical (MSS) source separation of western popular music using non-causal deep learning can be very effective. In contrast, MSS for classical music is an unsolved problem. Classical ensembles are harder to separate than popular music…

Color image steganography based on deep learning is the art of hiding information in the color image. Among them, image hiding steganography(hiding image with image) has attracted much attention in recent years because of its great…

Separating an audio scene into isolated sources is a fundamental problem in computer audition, analogous to image segmentation in visual scene analysis. Source separation systems based on deep learning are currently the most successful…

In this paper, we propose a multi-channel speech source separation with a deep neural network (DNN) which is trained under the condition that no clean signal is available. As an alternative to a clean signal, the proposed method adopts an…

Disentangling and recovering physical attributes, such as shape and material, from a few waveform examples is a challenging inverse problem in audio signal processing, with numerous applications in musical acoustics as well as structural…

We present the Inverse Drum Machine, a novel approach to Drum Source Separation that leverages an analysis-by-synthesis framework combined with deep learning. Unlike recent supervised methods that require isolated stem recordings for…

This paper proposes a novel framework for unsupervised audio source separation using a deep autoencoder. The characteristics of unknown source signals mixed in the mixed input is automatically by properly configured autoencoders implemented…

We address the determined audio source separation problem in the time-frequency domain. In independent deeply learned matrix analysis (IDLMA), it is assumed that the inter-frequency correlation of each source spectrum is zero, which is…

Music recommendation systems have emerged as a vital component to enhance user experience and satisfaction for the music streaming services, which dominates music consumption. The key challenge in improving these recommender systems lies in…

In recent years, deep perceptual loss has been widely and successfully used to train machine learning models for many computer vision tasks, including image synthesis, segmentation, and autoencoding. Deep perceptual loss is a type of loss…

Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens. These codecs preserve high-quality sound and enable sophisticated sound generation through generative…

Edge detection is a fundamental task in computer vision. It has made great progress under the development of deep convolutional neural networks (DCNNs), some of which have achieved a beyond human-level performance. However, recent…

Extraction of the predominant pitch from polyphonic audio is one of the fundamental tasks in the field of music information retrieval and computational musicology. To accomplish this task using machine learning, a large amount of labeled…

Singing Voice Separation (SVS) tries to separate singing voice from a given mixed musical signal. Recently, many U-Net-based models have been proposed for the SVS task, but there were no existing works that evaluate and compare various…

In spite of the progress in music source separation research, the small amount of publicly-available clean source data remains a constant limiting factor for performance. Thus, recent advances in self-supervised learning present a…

We propose a unified model for three inter-related tasks: 1) to \textit{separate} individual sound sources from a mixed music audio, 2) to \textit{transcribe} each sound source to MIDI notes, and 3) to\textit{ synthesize} new pieces based…

Singing voice separation (SVS) is a task that separates singing voice audio from its mixture with instrumental audio. Previous SVS studies have mainly employed the spectrogram masking method which requires a large dimensionality in…

Traditionally source identification is solved using threshold based energy detection algorithms. These algorithms frequently sum up the activity in regions, and consider regions above a specific activity threshold to be sources. While these…