Загрузка видео...
Не удалось загрузить видео
Cboard is an open source AAC web app that helps people with speech and language disabilities communicate using symbols and text-to-speech. Thanks to its global community of developers, educators, translators, and contributors, Cboard supports accessible communication for people of all ages.
81,658 просмотров • 2 месяцев назад •via X (Twitter)
Комментарии: 9
assistive systems make uncertainty operational: a wrong prediction can interrupt communication. optimize for correction cost, personalization, and portable user state, not only accuracy. open source helps when a user’s vocabulary can outlive any one app.
Open source is at its best when the software directly expands who gets to communicate.
this is the kind of open source project that never trends but quietly changes someone's life. would love to see GitHub spotlight more accessibility tools like Cboard in the trending page, most devs never even know these exist
Great example of open source creating real-world impact. 👏 Accessibility-focused tools like this show how thoughtful web development can make technology genuinely more inclusive.
This is a beautiful use of open source Such an Important project.
aac is a brutal ui benchmark because every extra tap sits between a thought and another person
Pretty cool seeing educators and translators involved alongside the developers. Getting the words and symbols right for the person using it matters just as much as getting the app working.
Really impressive work. Love seeing open source used for something that genuinely helps people communicate.
Cboard sounds like a game-changer for accessible communication! 🌟 What are some other accessible tech tools that have made a positive impact on people with speech and language disabilities?
![Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.](https://image.24vids.com/tw-1672048076469698561/ext_tw_video_thumb/1672047839378300928/pu/img/MuoOBsAyUd-HAI7D.jpg)
