相关论文: Perceiving Music Quality with GANs

Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images. While L1 and L2 losses are perhaps the most widely used functions for this purpose, they do not necessarily lead…

Collecting large, aligned cross-modal datasets for music-flavor research is difficult because perceptual experiments are costly and small by design. We address this bottleneck through two complementary experiments. The first tests whether…

The rapid proliferation of AI-Generated Content (AIGC) has necessitated robust metrics for perceptual quality assessment. However, automatic Mean Opinion Score (MOS) prediction models are often compromised by data scarcity, predisposing…

This paper addresses the problem of global tempo estimation in musical audio. Given that annotating tempo is time-consuming and requires certain musical expertise, few publicly available data sources exist to train machine learning models…

The standard practice in Generative Adversarial Networks (GANs) discards the discriminator during sampling. However, this sampling method loses valuable information learned by the discriminator regarding the data distribution. In this work,…

This paper studies the quality of multimedia content focusing on 360 video and ambisonic spatial audio reproduced using a head-mounted display and a multichannel loudspeaker setup. Encoding parameters following basic video quality test…

Automatic Music Transcription (AMT) is a vital technology in the field of music information processing. Despite recent enhancements in performance due to machine learning techniques, current methods typically attain high accuracy in domains…

In recent years, AI-generated music has made significant progress, with several models performing well in multimodal and complex musical genres and scenes. While objective metrics can be used to evaluate generative music, they often lack…

In this paper, we propose NU-GAN, a new method for resampling audio from lower to higher sampling rates (upsampling). Audio upsampling is an important problem since productionizing generative speech technology requires operating at high…

Classic public switched telephone networks (PSTN) are often a black box for VoIP network providers, as they have no access to performance indicators, such as delay or packet loss. Only the degraded output speech signal can be used to…

Autoregressive models based on Transformers have become the prevailing approach for generating music compositions that exhibit comprehensive musical structure. These models are typically trained by minimizing the negative log-likelihood…

Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we…

Generative adversarial network (GAN) models can synthesize highquality audio signals while ensuring fast sample generation. However, they are difficult to train and are prone to several issues including mode collapse and divergence. In this…

This study introduces a novel no-reference image quality metric aimed at assessing image sharpness. Designed to be robust against variations in noise, exposure, contrast, and image content, it measures the normalized decay rate of gradients…

Speech enhancement is an essential task of improving speech quality in noise scenario. Several state-of-the-art approaches have introduced visual information for speech enhancement,since the visual aspect of speech is essentially unaffected…

Generative adversarial networks (GANs)successfully generate high quality data by learning amapping from a latent vector to the data. Various studies assert that the latent space of a GAN is semanticallymeaningful and can be utilized for…

Neural network based approaches to speech enhancement have shown to be particularly powerful, being able to leverage a data-driven approach to result in a significant performance gain versus other approaches. Such approaches are reliant on…

Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results. Incorporating psychoacoustically motivated speech perception metrics as part of model training…

This paper observes that there is an issue of high frequencies missing in the discriminator of standard GAN, and we reveal it stems from downsampling layers employed in the network architecture. This issue makes the generator lack the…

The performance of speech processing models trained on clean speech drops significantly in noisy conditions. Training with noisy datasets alleviates the problem, but procuring such datasets is not always feasible. Noisy speech simulation…