Machine learning

This month, Amazon announced the 11 focus areas of the 2019 Amazon Research Awards.

Many of today’s most useful AI systems are multilabel classifiers: they map input data into multiple categories at once. An object recognizer, for instance, might classify a given image as containing sky, sea, and boats but not desert or clouds.

Alexa’s ability to respond to customer requests is largely the result of machine learning models trained on annotated data. The models are fed sample texts such as “Play the Prince song 1999” or “Play River by Joni Mitchell”. In each text, labels are attached to particular words — SongName for “1999” and “River”, for instance, and ArtistName for Prince and Joni Mitchell. By analyzing annotated data, the system learns to classify unannotated data on its own.

Using cosine similarity rather than dot product to compare vectors helps prevent "catastrophic forgetting".

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 improving Alexa’s speech recognition system. Increasingly, keeping pace with Alexa’s expanding capabilities will require automating the learning process, through techniques such as semi-supervised learning, which leverages a small amount of annotated data to extract information from a much larger store of unannotated data.

The idea of using arrays of microphones to improve automatic speech recognition (ASR) is decades old. The acoustic signal generated by a sound source reaches multiple microphones with different time delays. This information can be used to create virtual directivity, emphasizing a sound arriving from a direction of interest and diminishing signals coming from other directions. In voice recognition, one of the more popular methods for doing this is known as “beamforming”.