@inproceedings{5ce6b416ef8141b6adf98456cf455992,
title = "Show and speak: Directly synthesize spoken description of images",
abstract = "This paper proposes a new model, referred to as the show and speak (SAS) model that, for the first time, is able to directly synthesize spoken descriptions of images, bypassing the need for any text or phonemes. The basic structure of SAS is an encoder-decoder architecture that takes an image as input and predicts the spectrogram of speech that describes this image. The final speech audio is obtained from the predicted spectrogram via WaveNet. Extensive experiments on the public benchmark database Flickr8k demonstrate that the proposed SAS is able to synthesize natural spoken descriptions for images, indicating that synthesizing spoken descriptions for images while bypassing text and phonemes is feasible.",
keywords = "Encoder-decoder, Image captioning, Image-to-speech, Sequence-to-sequence, Speech synthesis",
author = "Xinsheng Wang and Siyuan Feng and Jihua Zhu and Mark Hasegawa-Johnson and Odette Scharenborg",
note = "Accepted author manuscript; ICASSP 2021 : The IEEE International Conference on Acoustics, Speech, and Signal Processing ; Conference date: 06-06-2021 Through 11-06-2021",
year = "2021",
doi = "10.1109/ICASSP39728.2021.9414021",
language = "English",
isbn = "978-1-7281-7606-2",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE ",
pages = "4190--4194",
booktitle = "ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
address = "United States",
}