Published on May 23rd, 2019 📆 | 6231 Views ⚑
0Amazon Filed A Patent To Record Audio Before You Say “Alexa”
Amazon has filed a patent application with the US Patent and Trademark Office describing a technology that would allow Echo and other Alexa-enabled devices to capture what you say before a wakeword, like âAlexaâ is uttered. Currently, Alexa devices only record and send audio to Amazon servers if a wakeword is detected. Should Amazon decide to develop or implement the technology, an Alexa-enabled device would constantly record and delete what you say using the deviceâs local memory storage.
The patent application, which was made public today, offers insight into Amazonâs ambitions to expand the capabilities of its voice recognition technology. Alexa devices currently canât understand commands where the wakeword comes after, or is in the middle of a sentence. But images in the patent application offer âPlay some music, Alexaâ and âPlay some music, Alexa. The Beatles, pleaseâ as examples.
âWhile such phrasings may be natural for a user, current speech processing systems are not configured to handle commands that are not preceded by a wakeword,â wrote the patent applicationâs authors Kurt Wesley Piersol and Gabriel Beddingfield. âOffered is a system to correct this problem.â
In a statement, an Amazon spokesperson told BuzzFeed News that, âThe technology in this patent is not in use, and referring to the potential use of patents is highly speculative.â The spokesperson added that Amazon files many patent applications that are not ultimately implemented into consumer-facing products, and that patents do not necessarily reflect âcurrent or near-future states of products and services.â
According to the patent application, after a wakeword is detected, Alexa may âlook backwardsâ to determine if the command came before the wakeword, and use pauses in speech to identify the beginning of the command. At that point, the audio would be sent from the device to Amazon servers for full processing. The idea is similar to Appleâs Live Photos technology, which captures 1.5 seconds before and after the camera shutter is pressed.
This process, the patent application states, is designed so that all captured speech doesnât need to be sent to Amazon, âthus addressing privacy concerns associated with an âalways-onâ speech processing system.â Additionally, the device may be configured to store only 10 to 30 seconds of audio at a time âto avoid capturing too much speech and causing privacy concerns.â
Still, the potential technology means that Alexa devices will be recording more conversations and more audio, including speech it thinks are commands. While Amazonâs speech recognition software is constantly being improved, Echo and third-party Alexa devices still accidentally record plenty of audio snippets triggered by false wake words. This could expose more customer recordings to Amazon employees and contracts tasked with reviewing and annotating audio files to improve Alexaâs technology, as well as others. In May 2018, an Amazon Echo inadvertently shared portions of a womanâs private conversation as a voice message to one of her husbandâs employees. Itâs also unclear whether customers would be able to turn off pre-wakeword recording.
Privacy concerns aside, the patent application is just a part of Amazonâs attempt to make voice computing more natural, and more human. But in order for Amazon to do so, it appears that weâll have to let Alexa listen in on more of our conversations.
You can review and delete voice recordings captured by Echo and third party Alexa devices by going to Settings > Alexa Account > Alexa Privacy in the Alexa app or https://www.amazon.com/alexaprivacy.
Gloss