Collaborating Authors

Now we're talking! Dictating texts is faster than typing


Modern smartphones might be several sizes larger than their forebears but those tiny touchscreen buttons still make for painful texting. At best, words are garbled; at worst, they are automatically changed to something unintentionally rude. Perhaps the time has come to let a robot do the hard work. Researchers have discovered that speech recognition software on smartphones is not only three times faster than human typists, but more accurate too.

Exploring Apple's Machine Learning API's


The Natural Language framework provides a variety of natural language processing (NLP) functionality with support for many different languages and scripts. Use the Speech framework to recognize spoken words in recorded or live audio. The keyboard's dictation support uses speech recognition to translate audio content into text. This framework provides a similar behavior, except that you can use it without the presence of the keyboard. For example, you might use speech recognition to recognize verbal commands or handle text dictation in other parts of your app.

How Mozilla is crowdsourcing speech to diversify voice recognition


Today's speech recognition technologies are largely tied up in a few products: think Amazon's Alexa and Google's own assistant. These major voice assistants are driven by commercial interests and only serve the majority languages, mainly English. "Most speech databases are trained with an overrepresentation of certain demographics which results in a bias towards male and white and middle class," Davis added. "Accents and dialects that tend to be under-represented in training datasets.

Transcribe speech input to text - Learn


Speech-to-text from the speech service, known as speech recognition, enables real time transcription of audio streams into text. Your applications, tools, or devices can consume, display, and take action on this text as command input.