Speech-to-Text for Broadcasters, From Research to Implementation

Haynes, M. K.; Norton, Alexander; McParland, Andrew; Cooper, R.

doi:10.5594/jmi.2018.2790658

Cited by 3 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the need for subtitles in production systems for issues of accessibility, transcription of media has been an annotation task done by media organisations since a long time, first manually but now automatically. Speech-to-text methods have become very effective to automatically create transcripts from audio (and can be built from open-source tools such as done by the BBC [74]), but language support is variable (YLE responded to the lack of Finnish support by collecting speech samples from Finnish speakers to train its own model) and modern frameworks do not immediately address issues like use of dialects or background noise [75]. Broadcasters need to be aware of the challenges in automatic transcription for their content, e.g.…”

Section: Instance-level Annotationmentioning

confidence: 99%

Data-driven personalisation of television content: a survey

et al. 2022

View full text Add to dashboard Cite

show abstract

Section: Instance-level Annotationmentioning

confidence: 99%

Data-driven personalisation of television content: a survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Much like text-to-speech and speech-to-text conversion, there exists a wide variety of problems that text-to-image synthesis could solve in the computer vision field specifically (Haynes, Norton, McParland, & Cooper, 2018;Reed, Akata, Yan, et al, 2016). Nowadays, researchers are attempting to solve a plethora of computer vision problems with the aid of deep convolutional networks, GANs, and a combination of multiple methods, often called multimodal F I G U R E 1 Early research on text-to-image synthesis (Zhu et al, 2007).…”

Section: Gan-based Text-to-image Synthesismentioning

confidence: 99%

A survey and taxonomy of adversarial neural networks for text‐to‐image synthesis

Agnese

Herrera

Tao

et al. 2020

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Text-to-image synthesis refers to computational methods which translate human written textual descriptions, in the form of keywords or sentences, into images with similar semantic meaning to the text. In earlier research, image synthesis relied mainly on word to image correlation analysis combined with supervised methods to find best alignment of the visual content matching to the text. Recent progress in deep learning (DL) has brought a new set of unsupervised deep learning methods, particularly deep generative models which are able to generate realistic visual images using suitably trained neural network models. The change of direction from the computer vision based approaches to artificial intelligence (AI) driven methods ignited the intense interest in industry, such as virtual reality, recreational & professional (eSports) gaming, and computer-aided design etc., to automatically generate compelling images from text-based natural language descriptions. In this paper, we review the most recent development in the text-to-image synthesis research domain. Our goal is to provide value by delivering a comparative review of the state-of-the-art models in terms of their architecture and design. Our survey first introduces image synthesis and its challenges, and then reviews key concepts such as generative adversarial networks (GANs) and deep convolutional encoderdecoder neural networks (DCNN). After that, we propose a taxonomy to summarize GAN based text-toimage synthesis into four major categories: Semantic Enhancement GANs, Resolution Enhancement GANs, Diversity Enhancement GANS, and Motion Enhancement GANs. We elaborate the main objective of each group, and further review typical GAN architectures in each group. The taxonomy and the review outline the techniques and the evolution of different approaches, and eventually provide a clear roadmap to summarize the list of contemporaneous solutions that utilize GANs and DCNNs to generate enthralling results in categories such as human faces, birds, flowers, room interiors, object reconstruction from edge maps (games) etc. The survey will conclude with a comparison of the proposed solutions, challenges that remain unresolved, and future developments in the text-to-image synthesis domain.

show abstract

The Studs Terkel Radio Archive: A Journey to Enhanced Usability for Audio

Holmes¹

2020

Journal of Archival Organization

View full text Add to dashboard Cite

Speech-to-Text for Broadcasters, From Research to Implementation

Cited by 3 publications

References 2 publications

Data-driven personalisation of television content: a survey

Data-driven personalisation of television content: a survey

A survey and taxonomy of adversarial neural networks for text‐to‐image synthesis

The Studs Terkel Radio Archive: A Journey to Enhanced Usability for Audio

Contact Info

Product

Resources

About