Apple patent filing involves multi-microphone speech recognition systems for Siri

Apple has filed for a patent (number 20180137864) for “multi-microphone speech recognition systems and related techniques.” The goal seems to be to improve the accuracy of Siri, it’s personal digital assistant.

Unlike conventional systems, Apple’s proposed speech recognition systems would use multiple microphones and concurrent processing of various signals from the microphones to improve speech recognition accuracy in challenging acoustic environments (e.g., where large distances separate a user from a microphone transducer, in reverberant rooms, and/or where substantial background noise impairs the speech signal, or utterance).

Siri patent.jpeg

More particularly, those systems exploit the availability of multiple microphones to obtain several different versions of a given utterance. Finally, the systems could exploit concurrent processing of those several different versions to derive accurate transcriptions of the utterance. 

Here’s Apple’s summary of the invention: “A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. 

“The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.”

Of course, Apple files for — and is granted — lots of patents by the U.S. Patent & Trademark Office. Many are for inventions that never see the light of day. However, you never can tell which ones will materialize in a real product.