Drax, an open source speech model released by Israeli AI lab Aiola employs Flow Matching -- a technique previously used in image models.

Meta Platforms Inc.’s artificial intelligence research team today said it has open-sourced a new project called Massively Multilingual Speech, which aims to overcome the challenges of creating ...

Q. Is there any way to improve the voice-recognition capability of my Windows 10 computer? A. I’m not sure this is actually true, but a friend told me his neighbor ...

The MLCommons Association, a nonprofit consortium that aims to improve machine learning for the public good, today announced the release of two key new datasets that it says can be leverage by ...

A new generative AI feature brings voice recognition to tiny devices with a text-to-speech (TTS) synthetic dataset generation capability. It enables developers to generate synthetic speech data with ...

Speech recognition systems from major tech companies have a harder time understanding words spoken by black people than the same ones spoken by whites, a new study finds. These types of systems are ...

The accuracy of automatic speech recognition has made significant gains in the last few years thanks to the advent of deep neural networks. But there’s one area that has thwarted researchers: telling ...

AppTek’s sophisticated multilingual TTS model ensures that prosodic patterns are accurately generated, resulting in human-like emotional speech range with granular control over every voice parameter.

Windows 11 Voice Access is a major update to Microsoft's accessibility tools, allowing users to control their desktop entirely with voice commands — no hands or Internet connection required. The ...