March 4 marked the kickoff of the third Alexa Prize Socialbot Grand Challenge, in which university teams build socialbots capable of conversing on a wide ...

Most modern machine learning systems are classifiers. They take input data and sort it into categories: pictures of particular animals, vocalizations of ...

Although deep neural networks have enabled accurate large-vocabulary speech recognition, training them requires thousands of hours of transcribed data, ...

Sentiment analysis is the attempt, computationally, to determine from someone’s words how he or she feels about something. It has a host of applications, in ...

Audio watermarking is the process of adding a distinctive sound pattern — undetectable to the human ear — to an audio signal to make it identifiable to a ...

The idea of using arrays of microphones to improve automatic speech recognition (ASR) is decades old. The acoustic signal generated by a sound source ...

Customer interactions with Alexa are constantly growing more complex, and on the Alexa science team, we strive to stay ahead of the curve by continuously ...

Transfer learning is the technique of adapting a machine learning model trained on abundant data to a new context in which training data is sparse.On the ...

Multiband dynamics processing, which separately modifies volume in different frequency bands of an audio signal, is known to improve listeners’ audio ...

Last year, Amazon announced the beta release of Alexa Guard, a new service that lets customers who are leaving the house instruct their Echo devices to ...

One of the ways that we’re always trying to improve Alexa’s performance is by teaching her to ignore speech that isn’t intended for her.At this year’s ...

When a customer asks Alexa to play “Hey Jude”, and Alexa responds, “Playing 'Hey Jude' by the Beatles,” that response is generated by a text-to-speech (TTS) ...