Amazon Technologies, Inc.

Jie Liang

James G Droppo

Oguz Hasan Elibol

Roberto Barra Chicote

Zeya Chen

Yixiong Meng

Avani Deshpande

Grzegorz Beringer

Chia-Hao Chang

A speech-processing system receives input data representing text. A first encoder processes segments of the text to determine embedding data representing the text, and a second encoder processes corresponding audio data to determine prosodic data corresponding to the text. The embedding and prosodic data is processed to create output data including a representation of speech corresponding to the text and prosody.

Synthetic speech processing

A system is provided for using voice characteristics in determining a user intent corresponding to an utterance. The system processes a NLU hypothesis and voice characteristics data, using a trained model, to determine an alternate NLU hypothesis based on the voice characteristics data. The voice characteristics data may indicate if a user's level of uncertainty when speaking the utterance, an age group of the user, a sentiment of the user when speaking the utterance, and other data.

Natural language understanding using voice characteristics

Growing community of inventors

Bothell, WA, United States of America

Jie Liang