Related papers: Learning Spatially-Aware Language and Audio Embedd…
A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains. This work proposes a supervised contrastive learning…
Sign language recognition (SLR) has long been plagued by insufficient model representation capabilities. Although current pre-training approaches have alleviated this dilemma to some extent and yielded promising performance by employing…
In deep learning for drug discovery, chemical data are often represented as simplified molecular-input line-entry system (SMILES) sequences which allow for straightforward implementation of natural language processing methodologies, one…
In this paper, we introduce a novel framework for spatial audio understanding of first-order ambisonic (FOA) signals through a question answering (QA) paradigm, aiming to extend the scope of sound event localization and detection (SELD)…
Visual events are usually accompanied by sounds in our daily lives. However, can the machines learn to correlate the visual scene and sound, as well as localize the sound source only by observing them like humans? To investigate its…
Speech emotion recognition (SER) systems often struggle in real-world environments, where ambient noise severely degrades their performance. This paper explores a novel approach that exploits prior knowledge of testing environments to…
Spatial audio understanding aims to enable machines to interpret complex auditory scenes, particularly when sound sources move over time. In this work, we study Spatial Audio Question Answering (Spatial AQA) with a focus on movement…
Audiovisual scenes are pervasive in our daily life. It is commonplace for humans to discriminatively localize different sounding objects but quite challenging for machines to achieve class-aware sounding objects localization without…
End-to-end Automatic Speech Recognition (ASR) models are usually trained to optimize the loss of the whole token sequence, while neglecting explicit phonemic-granularity supervision. This could result in recognition errors due to…
Current speech encoding pipelines often rely on an additional text-based LM to get robust representations of human communication, even though SotA speech-to-text models often have a LM within. This work proposes an approach to improve the…
Behavioral patterns captured in embeddings learned from interaction data are pivotal across various stages of production recommender systems. However, in the initial retrieval stage, practitioners face an inherent tradeoff between embedding…
Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and…
Reasoning about spatial audio with large language models requires a spatial audio encoder as an acoustic front-end to obtain audio embeddings for further processing. Such an encoder needs to capture all information required to detect the…
Audio-driven video generation aims to synthesize realistic videos that align with input audio recordings, akin to the human ability to visualize scenes from auditory input. However, existing approaches predominantly focus on exploring…
Spatial reasoning is fundamental to auditory perception, yet current audio large language models (ALLMs) largely rely on unstructured binaural cues and single step inference. This limits both perceptual accuracy in direction and distance…
Humans can robustly recognize and localize objects by integrating visual and auditory cues. While machines are able to do the same now with images, less work has been done with sounds. This work develops an approach for dense semantic…
Much recent work on Spoken Language Understanding (SLU) falls short in at least one of three ways: models were trained on oracle text input and neglected the Automatics Speech Recognition (ASR) outputs, models were trained to predict only…
In this study, we address the multimodal task of stereo sound event localization and detection with source distance estimation (3D SELD) in regular video content. 3D SELD is a complex task that combines temporal event classification with…
Several animal species (e.g., bats, dolphins, and whales) and even visually impaired humans have the remarkable ability to perform echolocation: a biological sonar used to perceive spatial layout and locate objects in the world. We explore…
Large audio-language models have made rapid progress in recognizing what is present in an audio clip, but spatial audio-language understanding still lacks a clear task interface. A model must also decide where sound events occur, which…