公开(公告)号：US10409552B1

公开(公告)日：2019-09-10

申请号：US15269755

申请日：2016-09-19

Applicant: Amazon Technologies, Inc.

Inventor： David Adrian Jara ,  Timothy Thomas Gray ,  Kwan Ting Lee ,  Jae Pum Park ,  Michael Hone ,  Grant Hinkson ,  Richard Leigh Mains ,  Shilpan Bhagat

IPC: G06F3/16 ,  G10L15/05 ,  G10L15/02

Abstract: 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.

公开(公告)号：US12165645B1

公开(公告)日：2024-12-10

申请号：US16886426

申请日：2020-05-28

Applicant: Amazon Technologies, Inc.

Inventor： Blair Harold Beebe ,  Peter Chin ,  Maksim Surguy ,  Chris Aaron Edmonds ,  Christina Siegfried ,  Kwan Ting Lee ,  Darvin Vida

IPC: G10L15/26 ,  G06F40/284 ,  G06F40/289 ,  G10L15/16 ,  G10L25/63

Abstract: Systems, methods, and computer-readable media are disclosed for annotating content data such as video data with annotation data (e.g., images, emoji, memes, stylized text, sounds) in near real time. Example methods may include determining transcribed text from the content data, associated annotation data with the transcribed text, and annotating the content data with some or all transcribed text and annotation data. Example methods may further include editing the annotated content data to generate modified annotated content data and sending the annotated content data and/or modified annotated content data to a device.