Amazon Technologies, Inc.

Grant Hinkson

Michael James Hone

Jae Pum Park

Timothy Thomas Gray

Richard Leigh Mains

Shilpan Bhagat

Kwan Ting Lee

David Adrian Jara

Systems and methods for displaying an audio indicator including a main portion having a width proportional to a volume of a particular phoneme of an utterance is described herein. In some embodiments, audio data representing an utterance may be received at a speech-processing system from a user device. The speech-processing system may determine a maximum volume amplitude for the utterance, and using the maximum volume amplitude, may determine a normalized amplitude value between 0 and 1 associated with a volume that phoneme's of an utterance are spoken. The speech-processing system may then map the normalized amplitude value(s) to widths for a main portion of an audio indicator, where larger normalized amplitude values may correspond to smaller main portion widths. Display data representing a graphical user interface may then be generated and sent to the user device, where the graphical user interface includes the audio indicator having its main portion of a particular width representative of a volume of each phoneme from the utterance.

Speech-based audio indicators

Growing community of inventors

Seattle, WA, United States of America

Grant Hinkson