Amazon Technologies, Inc.

Simon Peter Reavely

Spyridon Matsoukas

Shiv Naga Prasad Vitaladevuni

Avnish Sikka

Francois Mairesse

Thomas Kollar

Cengiz Erbas

Paul Frederick Raccuglia

Ruhi Sarikaya

Rohit Prasad

Manoj Sindhwani

Imre Attila Kiss

Kerry Hammil

Huinan Ren

Zheng Ma

Bradford Jason Snow

Jerrin Thomas Elanjikal

A system capable of performing natural language understanding (NLU) on utterances including complex command structures such as sequential commands (e.g., multiple commands in a single utterance), conditional commands (e.g., commands that are only executed if a condition is satisfied), and/or repetitive commands (e.g., commands that are executed until a condition is satisfied). Audio data may be processed using automatic speech recognition (ASR) techniques to obtain text. The text may then be processed using machine learning models that are trained to parse text of incoming utterances. The models may identify complex utterance structures and may identify what command portions of an utterance go with what conditional statements. Machine learning models may also identify what data is needed to determine when the conditionals are true so the system may cause the commands to be executed (and stopped) at the appropriate times.

Processing complex utterances for natural language understanding

Techniques for performing command processing are described. A system receives, from a device, input data corresponding to a command. The input data may originate as audio data, as text data, or as other data. The system determines NLU processing results corresponding to the input data. The NLU processing results may be associated with multiple speechlets. The system also determines NLU confidences for the NLU processing results for each speechlet. The system sends NLU processing results and an indication to provide potential results to a portion of the multiple speechlets, and receives potential results from the portion of the speechlets. The system also receives indications whether the speechlets need to be re-called if the speechlets are selected to execute with respect to the command. The system ranks the portion of the speechlets based at least in part on the NLU processing results as well as the potential results provided by the portion of the speechlets. The system may also rank the portion of the applications using other data. The system causes content provided by the highest ranked speechlet to be output to a user.

System command processing

A system capable of performing natural language understanding (NLU) using different application domains in parallel. A model takes incoming query text and determines a list of potential supplemental intent categories corresponding to the text. Supplemental applications within those categories are then identified as likely candidates for responding to the query. Application specific domains, including NLU components for the particular supplemental applications, are then activated and process the query text in parallel. Further, certain system default domains may also process incoming queries substantially in parallel with the supplemental applications. The different results are scored and ranked to determine highest scoring NLU results.

Determining domains for natural language understanding

Automatic speech recognition (ASR) processing including a feedback configuration to allow for improved disambiguation between ASR hypotheses. After ASR processing of an incoming utterance where the ASR outputs an N-best list including multiple hypotheses, the multiple hypotheses are passed downstream for further processing. The downstream further processing may include natural language understanding (NLU) or other processing to determine a command result for each hypothesis. The command results are compared to determine if any hypotheses of the N-best list would yield similar command results. If so, the hypothesis(es) with similar results are removed from the N-best list so that only one hypothesis of the similar results remains in the N-best list. The remaining non-similar hypotheses are sent for disambiguation, or, if only one hypothesis remains, it is sent for execution.

Disambiguation in speech recognition

Growing community of inventors

Lexington, MA, United States of America

Simon Peter Reavely