Related papers: Learning Spatially-Aware Language and Audio Embedd…

Embeddings are an important tool for the representation of word meaning. Their effectiveness rests on the distributional hypothesis: words that occur in the same context carry similar semantic information. Here, we adapt this approach to…

We study the domain adaptation problem with label shift in this work. Under the label shift context, the marginal distribution of the label varies across the training and testing datasets, while the conditional distribution of features…

Latent representations learned by neural networks often exhibit semantic structure, where concept similarity is reflected by geometric proximity in embedding space. However, comparing such spaces across models remains difficult: changes in…

Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services. Typical SID systems use a symmetric enrollment-verification framework with a single model to derive embeddings both…

In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem…

We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual…

Detecting sound source objects within visual observation is important for autonomous robots to comprehend surrounding environments. Since sounding objects have a large variety with different appearances in our living environments, labeling…

Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models…

Unsupervised domain adaptation for semantic segmentation (DASS) aims to transfer knowledge from a label-rich source domain to a target domain with no labels. Two key approaches in DASS are (1) vision-only approaches using masking or…

To be able to interact better with humans, it is crucial for machines to understand sound - a primary modality of human perception. Previous works have used sound to learn embeddings for improved generic textual similarity assessment. In…

As embodied agents become central to VR, telepresence, and digital human applications, their motion must go beyond speech-aligned gestures: agents should turn toward users, respond to their movement, and maintain natural gaze. Current…

Sound Event Localization and Detection (SELD) combines the Sound Event Detection (SED) with the corresponding Direction Of Arrival (DOA). Recently, adopted event oriented multi-track methods affect the generality in polyphonic environments…

Recently, Large Audio Language Models (LALMs) have progressed rapidly, demonstrating their strong efficacy in universal audio understanding through cross-modal integration. To evaluate LALMs' audio understanding performance, researchers…

The sound of crashing waves, the roar of fast-moving cars -- sound conveys important information about the objects in our surroundings. In this work, we show that ambient sounds can be used as a supervisory signal for learning visual…

Spatial perception is central to auditory intelligence, enabling accurate understanding of real-world acoustic scenes and advancing human-level perception of the world around us. While recent large audio-language models (LALMs) show strong…

Sound source localization (SSL) is the task of locating the source of sound within an image. Due to the lack of localization labels, the de facto standard in SSL has been to represent an image and audio as a single embedding vector each,…

As we interact with the world, for example when we communicate with our colleagues in a large open space or meeting room, we continuously analyse the surrounding environment and, in particular, localise and recognise acoustic events. While…

Human brain employs perceptual information about the head and eye movements to update the spatial relationship between the individual and the surrounding environment. Based on this cognitive process known as spatial updating, we introduce…

Inspired by the behavior of humans talking in noisy environments, we propose an embodied embedded cognition approach to improve automatic speech recognition (ASR) systems for robots in challenging environments, such as with ego noise, using…

A fundamental characteristic of audio is its compositional nature. Audio-language models (ALMs) trained using a contrastive approach (e.g., CLAP) that learns a shared representation between audio and language modalities have improved…