Google Introduces All-neural, On-device Speech Recognizer to Power Speech Input in Gboard
In a post on its AI Blog, Google revealed that it has made spoken to written text translation available offline for Gboard users. In the early days of speech recognition, the post says, “latency remained a prime focus—an automated assistant feels a lot more helpful when it responds quickly to requests.” With that in mind, it has announced the rollout of an end-to-end, all-neural, on-device speech recognizer to power speech input in Gboard.
According to Google’s blog post, “This means no more network latency or spottiness — the new recognizer is always available, even when you are offline. The model works at the character level, so that as you speak, it outputs words character-by-character, just as if someone was typing out what you say in real-time, and exactly as you'd expect from a keyboard dictation system.”
In a post on its Alexa blog, Amazon says it has developed a different acoustic modeling framework. Amazon says it can boosts performance by unifying speech enhancement and speech recognition.