So this is pretty cool. Speech interfaces for educational technology are advancing rapidly (as I guess shopuld not be surprising in the age of voice assistants such as Siri and Alexa and Google). This interview of Patricia Scanlon from SoapBox Labs "focuses on their new cloud-based API to improve children's aural/oral interactions with their smart toys and gadgets via voice recognition and behavior." This is what developers like: "use our technology by simply sending an audio file to our API and our systems responds in near real-time." The bad news? The API is proprietary so it can only be used with the one engine. What we will need is a standard (and open!) speech interface API, something Mozilla is working on.
Today: 8 Total: 1120 [Direct link] [Share]
