相关论文: How Much Does Audio Matter to Recognize Egocentric…

Speech emotion recognition (SER) is vital for obtaining emotional intelligence and understanding the contextual meaning of speech. Variations of consonant-vowel (CV) phonemic boundaries can enrich acoustic context with linguistic cues,…

Audio captioning aims to generate text descriptions of audio clips. In the real world, many objects produce similar sounds. How to accurately recognize ambiguous sounds is a major challenge for audio captioning. In this work, inspired by…

Sense of hearing is crucial for autonomous vehicles (AVs) to better perceive its surrounding environment. Although visual sensors of an AV, such as camera, lidar, and radar, help to see its surrounding environment, an AV cannot see beyond…

In this paper we present a research on identification of audio recording devices from background noise, thus providing a method for forensics. The audio signal is the sum of speech signal and noise signal. Usually, people pay more attention…

Modern perception models, particularly those designed for multisensory egocentric tasks, have achieved remarkable performance but often come with substantial computational costs. These high demands pose challenges for real-world deployment,…

Teaching is one of the most important factors affecting any education system. Many research efforts have been conducted to facilitate the presentation modes used by instructors in classrooms as well as provide means for students to review…

Many animals emit vocal sounds which, independently from the sounds' function, embed some individually-distinctive signature. Thus the automatic recognition of individuals by sound is a potentially powerful tool for zoology and ecology…

In this abstract we describe recent [4,7] and latest work on the determination of affordances in visually perceived 3D scenes. Our method builds on the hypothesis that geometry on its own provides enough information to enable the detection…

Unlike traditional third-person cameras mounted on robots, a first-person camera, captures a person's visual sensorimotor object interactions from up close. In this paper, we study the tight interplay between our momentary visual attention…

Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. The classification performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds.…

Learning to infer labels in an open world, i.e., in an environment where the target "labels" are unknown, is an important characteristic for achieving autonomy. Foundation models pre-trained on enormous amounts of data have shown remarkable…

Analysis and interpretation of egocentric video data is becoming more and more important with the increasing availability and use of wearable cameras. Exploring and fully understanding affinities and differences between ego and allo (or…

[Purpose] To understand the meaning of a sentence, humans can focus on important words in the sentence, which reflects our eyes staying on each word in different gaze time or times. Thus, some studies utilize eye-tracking values to optimize…

Understanding emotion from speech requires sensitivity to both lexical and acoustic cues. However, it remains unclear whether large audio language models (LALMs) genuinely process acoustic information or rely primarily on lexical content.…

Predicting when to initiate speech in real-world environments remains a fundamental challenge for conversational agents. We introduce EgoSpeak, a novel framework for real-time speech initiation prediction in egocentric streaming video. By…

Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations. In this paper, we study the compositionality of action by looking into the…

Objects make unique sounds under different perturbations, environment conditions, and poses relative to the listener. While prior works have modeled impact sounds and sound propagation in simulation, we lack a standard dataset of impact…

Machine learning techniques have proved useful for classifying and analyzing audio content. However, recent methods typically rely on abstract and high-dimensional representations that are difficult to interpret. Inspired by…

Speaker identity plays a significant role in human communication and is being increasingly used in societal applications, many through advances in machine learning. Speaker identity perception is an essential cognitive phenomenon that can…

Large audio-language models (LALMs) exhibit strong zero-shot capabilities in multiple downstream tasks, such as audio question answering (AQA) and abstract reasoning; however, these models still lag behind specialized models for certain…