In this paper we present the first model for directly synthesizing fluent, natural-sounding
spoken audio captions for images that does not require natural language text as an …

An unsupervised text-to-speech synthesis (TTS) system learns to generate speech
waveforms corresponding to any written sentence in a language by observing: 1) a …

This novel approach is to enhance accessibility for visually impaired individuals by
integrating object detection and speech generation using YOLOv5 model on the COCO …

Voice conversion is the art of mimicking different speaker voices and styles. In this paper, we
present a cross-lingual speaker style adaptation based on a multi-scale loss function, using …

Deep neural network based speech processing systems have found widespread
applications in daily life, being employed for tasks such as automatic speech recognition …

Natural speech-dialogue generation has been achieved with cascade systems combining
automatic speech recog-nition, text-dialogue, and text-to-speech models. However, it is still …

딥러닝의 발전과 함께 주목받고 있는 이미지 묘사 기술은 이미지 속 내용을 파악하는 컴퓨터
비전 분야와 문장으로 번역하는 자연어 처리 분야의 기술이 복합적으로 사용된다. 본 …

In recent years, deep learning methods allowed the creation of neural models that are able
to process several modalities at once. Neural models of Visually Grounded Speech (VGS) …

Résumé Ces dernieres années, les méthodes d'apprentissage profond ont permis de créer
des mod-eles neuronaux capables de traiter plusieurs modalitésa la fois. Les modeles …