相关论文: Distortion Recovery: A Two-Stage Method for Guitar…

We explore the use of neural synthesis for acoustic guitar from string-wise MIDI input. We propose four different systems and compare them with both objective metrics and subjective evaluation against natural audio and a sample-based…

We propose a speech enhancement system that combines speaker-agnostic speech restoration with voice conversion (VC) to obtain a studio-level quality speech signal. While voice conversion models are typically used to change speaker…

Current ML models for music emotion recognition, while generally working quite well, do not give meaningful or intuitive explanations for their predictions. In this work, we propose a 2-step procedure to arrive at spectrogram-level…

Generally, wave field reconstructions obtained by phase-retrieval algorithms are noisy, blurred and corrupted by various artifacts such as irregular waves, spots, etc. These disturbances, arising due to many factors such as non-idealities…

We study the problem of stereo singing voice cancellation, a subtask of music source separation, whose goal is to estimate an instrumental background from a stereo mix. We explore how to achieve performance similar to large state-of-the-art…

Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing methods rely on pretrained diffusion models by involving…

Digital audio signal reconstruction of a lost or corrupt segment using deep learning algorithms has been explored intensively in recent years. Nevertheless, prior traditional methods with linear interpolation, phase coding and tone…

In this paper we study deep learning-based music source separation, and explore using an alternative loss to the standard spectrogram pixel-level L2 loss for model training. Our main contribution is in demonstrating that adding a high-level…

With the rise of video production and social media, speech editing has become crucial for creators to address issues like mispronunciations, missing words, or stuttering in audio recordings. This paper explores text-based speech editing…

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…

This paper introduces Open-Amp, a synthetic data framework for generating large-scale and diverse audio effects data. Audio effects are relevant to many musical audio processing and Music Information Retrieval (MIR) tasks, such as modelling…

This work aims to tackle the all-in-one image restoration task, which seeks to handle multiple types of degradation with a single model. The primary challenge is to extract degradation representations from the input degraded images and use…

Musical acoustics is an interesting sub-field of physics which is usually able to engage students in a dual perspective, by combining science and art together. The physics principles involved in most musical instruments can be easily…

This paper aims to apply a new deep learning approach to the task of generating raw audio files. It is based on diffusion models, a recent type of deep generative model. This new type of method has recently shown outstanding results with…

Deep neural networks have shown promise for music audio signal processing applications, often surpassing prior approaches, particularly as end-to-end models in the waveform domain. Yet results to date have tended to be constrained by low…

We propose a three-dimensional holographic reconstruction procedure applicable with no a priori knowledge about the recording conditions enabling distortion-free three-dimensional object reconstruction.

We introduce an audio texture synthesis algorithm based on scattering moments. A scattering transform is computed by iteratively decomposing a signal with complex wavelet filter banks and computing their amplitude envelop. Scattering…

This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources. Driven by input data and audio contents, the proposed dual-stage speech enhancement…

Acoustic echo cancellation (AEC) remains challenging in real-world environments due to nonlinear distortions caused by low-cost loudspeakers and complex room acoustics. To mitigate these issues, we introduce a dual-microphone configuration,…

This paper presents a novel two-phase method for audio representation, Discriminative and Compact Audio Representation (DCAR), and evaluates its performance at detecting events in consumer-produced videos. In the first phase of DCAR, each…