Related papers: iMagLS: Interaural Level Difference with Magnitude…
In this work, we propose a deep beamforming framework for speech enhancement in dynamic acoustic environments. The framework learns time-varying beamformer weights from noisy multichannel signals via a deep neural network, guided by a…
End-to-end neural TTS training has shown improved performance in speech style transfer. However, the improvement is still limited by the training data in both target styles and speakers. Inadequate style transfer performance occurs when the…
Ambisonics is a method for capturing and rendering a sound field accurately, assuming that the acoustics of the playback room does not significantly influence the sound field. However, in practice, the acoustics of the playback room may…
Hallucination remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While Direct Preference Optimization (DPO) is a key alignment framework, existing approaches often rely heavily on costly external evaluators for…
As spatial audio is enjoying a surge in popularity, data-driven machine learning techniques that have been proven successful in other domains are increasingly used to process head-related transfer function measurements. However, these…
Hearing loss (HL) simulators, which allow normal hearing (NH) listeners to experience HL, have been used in speech intelligibility experiments, but not in sound quality experiments due to perceptible distortion. If they produced less…
In this work, we propose a two-dimensional Head-Related Transfer Function (HRTF)-based robust beamformer design for robot audition, which allows for explicit control of the beamformer response for the entire three-dimensional sound field…
Remote sensing imagery suffers from clouds, haze, noise, resolution limits, and sensor heterogeneity. Existing restoration and fusion approaches train separate models per degradation type. In this work, we present Language-conditioned…
The multichannel Wiener filter (MWF) and its variations have been extensively applied to binaural hearing aids. However, its major drawback is the distortion of the binaural cues of the residual noise, changing the original acoustic…
Many efforts have been devoted to designing sampling, mining, and weighting strategies in high-level deep metric learning (DML) loss objectives. However, little attention has been paid to low-level but essential data transformation. In this…
Several individualization methods have recently been proposed to estimate a subject's Head-Related Transfer Function (HRTF) using convenient input modalities such as anthropometric measurements or pinnae photographs. There exists a need for…
Conventional automatic speech recognition (ASR) system uses second-order minkowski loss during inference time which is suboptimal as it incorporates only first order statistics in posterior estimation [2]. In this paper we have proposed…
Auditory large language models (ALLMs) have demonstrated strong general capabilities in audio understanding and reasoning tasks. However, their reliability is still undermined by hallucination issues. Existing hallucination evaluation…
AI-based neural decoding reconstructs visual perception by leveraging generative models to map brain activity, measured through functional MRI (fMRI), into latent hierarchical representations. Traditionally, ridge linear models transform…
We introduce HiFi-HARP, a large-scale dataset of 7th-order Higher-Order Ambisonic Room Impulse Responses (HOA-RIRs) consisting of more than 100,000 RIRs generated via a hybrid acoustic simulation in realistic indoor scenes. HiFi-HARP…
Spatial audio formats like Ambisonics are playback device layout-agnostic and well-suited for applications such as teleconferencing and virtual reality. Conventional Ambisonic encoding methods often rely on spherical microphone arrays for…
Implicit Neural Representations (INRs) are nowadays used to represent multimedia signals across various real-life applications, including image super-resolution, image compression, or 3D rendering. Existing methods that leverage INRs are…
In this work, we present a new multi-view depth estimation method that utilizes both conventional reconstruction and learning-based priors over the recently proposed neural radiance fields (NeRF). Unlike existing neural network based…
Retrospective MRI harmonization is limited by poor scalability across modalities and reliance on traveling subject datasets. To address these challenges, we introduce IHF-Harmony, a unified invertible hierarchy flow framework for…
Many purely neural network based speech separation approaches have been proposed to improve objective assessment scores, but they often introduce nonlinear distortions that are harmful to modern automatic speech recognition (ASR) systems.…