相关论文: HEAR: Holistic Evaluation of Audio Representations

We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among which, 7 are newly proposed datasets. The evaluation targets three main…

Recent years have seen immense progress in 3D computer vision and computer graphics, with emerging tools that can virtualize real-world 3D environments for numerous Mixed Reality (XR) applications. However, alongside immersive visual…

Clinical AI systems require not just point-in-time evaluation but continuous governance: the ongoing practice of monitoring, evaluating, iterating, and re-evaluating performance throughout deployment. We present an end-to-end framework of…

Inspired by the recent progress in self-supervised learning for computer vision, in this paper we introduce DeLoRes, a new general-purpose audio representation learning approach. Our main objective is to make our network learn…

In this paper we present the results of the Unconstrained Ear Recognition Challenge (UERC), a group benchmarking effort centered around the problem of person recognition from ear images captured in uncontrolled conditions. The goal of the…

As multimodal content continues to expand at a rapid pace, audio retrieval has emerged as a key enabling technology for media search, content organization, and intelligent assistants. However, most existing benchmarks concentrate on…

While visual augmentation dominates the augmented reality landscape, devices like Meta Ray-Ban audio smart glasses signal growing industry movement toward audio augmented reality (AAR). Hearing is a primary channel for sensing context,…

General perception systems such as Perceivers can process arbitrary modalities in any combination and are able to handle up to a few hundred thousand inputs. They achieve this generality by using exclusively global attention operations.…

Recent years have seen a rapid increase in digital medicine research in an attempt to transform traditional healthcare systems to their modern, intelligent, and versatile equivalents that are adequately equipped to tackle contemporary…

This paper provides an overview of recent progress in non-intrusive speech intelligibility prediction for hearing aids (HA). We summarize developments in robust acoustic feature extraction, hearing loss modeling, and the use of emerging…

Speaker embedding extractors significantly influence the performance of clustering-based speaker diarisation systems. Conventionally, only one embedding is extracted from each speech segment. However, because of the sliding window approach,…

We release the EARS (Expressive Anechoic Recordings of Speech) dataset, a high-quality speech dataset comprising 107 speakers from diverse backgrounds, totaling in 100 hours of clean, anechoic speech data. The dataset covers a large range…

This paper addresses the problem of self-supervised general-purpose audio representation learning. We explore the use of Joint-Embedding Predictive Architectures (JEPA) for this task, which consists of splitting an input mel-spectrogram…

Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the…

Current text-to-speech algorithms produce realistic fakes of human voices, making deepfake detection a much-needed area of research. While researchers have presented various techniques for detecting audio spoofs, it is often unclear exactly…

Neural speaker embeddings trained using classification objectives have demonstrated state-of-the-art performance in multiple applications. Typically, such embeddings are trained on an out-of-domain corpus on a single task e.g., speaker…

Artificial intelligence (AI) models trained on audio data may have the potential to rapidly perform clinical tasks, enhancing medical decision-making and potentially improving outcomes through early detection. Existing technologies depend…

The ability to comprehend audio--which includes speech, non-speech sounds, and music--is crucial for AI agents to interact effectively with the world. We present MMAU, a novel benchmark designed to evaluate multimodal audio understanding…

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module,…

Multimodal foundation models that can holistically process text alongside images, video, audio, and other sensory modalities are increasingly used in a variety of real-world applications. However, it is challenging to characterize and study…