Amazon Technologies, Inc.

Anubhav Mishra

Sravan Babu Bodapati

Katrin Kirchhoff

John Baker

Harshal Pimpalkhute

Ashish Vishwanath Shenoy

Ankur Gandhe

Ganesh Kumar Gella

Monica Lakshmi Sunkara

Ravi Teja Gadde

Bangrui Liu

Saket Saurabh

Chengshun Zhang

Kuai Hu

Saket Dingliwal

Fnu Don Manuel

Christopher Michael Hittner

Yilai Su

Anuj Gautam Surana

Brandon Louis Mendez

Techniques for at least the generation of a chatbot built from a custom vocabulary and to use runtime hints during inference are described. In some examples, the generation of the chatbot includes receiving a request to build a chatbot using a bot definition and a custom vocabulary, wherein the chatbot is to use runtime hints during usage; building the chatbot from the bot definition and custom vocabulary by at least: generating automatic speech recognition (ASR) artifacts to be used in decoding audio input into the chatbot into text for at least one other component of the chatbot to use in determining a next act to be performed, the ASR artifacts including artifacts that use the custom vocabulary and artifacts that do not use the custom vocabulary, and storing the ASR artifacts.

Dynamically selectable automated speech recognition using a custom vocabulary

Techniques for updating a chatbot definition are described. In some examples, this updating includes receiving an edit to intent characteristics for a stage of a plurality of stages in a chatbot flow, identifying a stage to modify based on at least the received edit, identifying, for the stage, a default update rule based on the chatbot definition, and updating the stage in the chatbot definition by inferring a next step according to one or more rules for the stage including the identified default update rule.

Chatbot conversation flow designer

A set of alternative vocal input styles for specifying a parameter of a dialog-driven application is determined. During execution of the application, an audio prompt requesting input in one of the styles is presented. A value of the parameter is determined by applying a collection of analysis tools to vocal input obtained after the prompt is presented. A task of the application is initiated using the value.

Dialog-driven applications supporting alternative vocal input styles

Domain-specific parameters may be used for tuning speech processing. A pre-trained transformer-based language model may train domain-specific parameters using domain-specific unlabeled text data. This domain-specific parameters can then be appended to candidate texts produced by a speech model on received speech data and input to the transformer-based language model to score the candidate texts. The scores of the candidate texts determined using the pre-trained transformer-based language model can then be used to select a candidate text for further speech processing.

Domain-specific parameter pre-fixes for tuning automatic speech recognition

Growing community of inventors

Seattle, WA, United States of America

Anubhav Mishra