Amazon Technologies, Inc.

Athanasios Mouchtaris

Siegfried Kunzmann

Maurizio Omologo

Feng-Ju Chang

Eli Joshua Fidler

Brian John King

Grant Strimel

Nathan Anthony Susanj

Sunwoo Kim

Martin Radfar

Jing Liu

Srikanth Subramaniam

Benjamin Li

Markus Mueller

Pavlo Stelmakh

Pavel Kveton

Systems and methods for speech processing utilizing customized embeddings include receiving a first textual representation of first audio data and intent data indicating an intent of a first voice command. A first embedding may be generated from the textual representation and stored on the device. Second audio data representing a second voice command may be received and a second embedding may be generated therefrom. The first embedding may be determined to have at least a threshold similarity to the second embedding, and an intent may be determined that is associated with the second voice command. An action may be performed utilizing the intent.

Speech processing utilizing customized embeddings

Techniques for performing automatic speech recognition (ASR) are described. In some embodiments, an ASR component integrates contextual information from user profile data into audio encoding data to predict a token(s) corresponding to a spoken input. The user profile data may include personalized words, such as, contact names, device names, etc. The ASR component determines word embedding data using the personalized words. The ASR component is configured to apply attention to audio frames that are relevant to the personalized words based on processing the audio encoding data and the word embedding data.

Automatic speech recognition

A multi-channel transformer acoustic model that processes a plurality of audio signals output by microphones of a microphone array and outputs probabilities for acoustic units of an utterance represented in the audio signals. The audio signals represent the individual microphones' respective capturing of the utterance. The multi-channel model may perform self-attention on embeddings of the audio signals and then cross-channel attention across the attended audio signals. The cross-channel attention may involve processing of signals relative to each other to model the relationships across channels within and across time frames. The multi-channel model may include a transducer to perform processing frame-by-frame.

Growing community of inventors

Pittsburgh, PA, United States of America

Athanasios Mouchtaris