Find all the TopAudio papers. Links to pdf, code repos and demos are provided.
How is information processed in the brain during perception? Mechanistic insight is achieved only when experiments are employed to test formal or comp...
see more
Introduces LLMVoX, a lightweight, autoregressive streaming text-to-speech (TTS) system designed to enhance speech-enabled dialogue systems without com...
see more
Introduces EgoLife, an innovative project aimed at developing an egocentric AI life assistant using wearable AI-powered glasses. A comprehensive datas...
see more
Audio Flamingo 2 (AF2) is an advanced Audio-Language Model designed to enhance understanding and reasoning over non-speech sounds and music. By integr...
see more
Presents a novel approach to enhance audio-visual speech separation by isolating individual speakers in multi-talker scenarios. The proposed method em...
see more
WhisperX is a speech transcription system designed to accurately transcribe long-form audio with word-level timestamps, addressing issues such as drif...
see more
Addresses the challenging problem of speaker diarization, specifically segmenting audio recordings from meetings into segments that correspond to indi...
see more
We present our ongoing work on developing a system, called DashCam Pay, that enables in-vehicle payments in a seamless and secure manner using face an...
see more
Individuals with Autism Spectrum Conditions (ASC) have marked difficulties
using verbal and non-verbal communication for social interaction. The runni...
see more
Introduces speech-based visual question answering (VQA), the task
of generating an answer given an image and a spoken question. Two methods are
studie...
see more
Humans can robustly recognize and localize objects by using visual and/or auditory cues. While machines are able to do the same with visual data alrea...
see more
Details a novel approach to action recognition in untrimmed videos presented as a submission to the ActivityNet Challenge 2016. By leveraging advancem...
see more
