公开(公告)号：US20230237980A1

公开(公告)日：2023-07-27

申请号：US18151359

申请日：2023-01-06

申请人： Amazon Technologies, Inc.

发明人： Ambika Pajjuri ,  Nagajyothi Nookula ,  Rahul Suresh ,  Sunil Mallya Kasaragod ,  Richard Lee ,  Hsin Chieh Chen

IPC分类号： G10H1/00 ,  G06N3/088 ,  G06N3/045

CPC分类号： G10H1/0025 ,  G06N3/088 ,  G06N3/045 ,  G10H2220/221 ,  G10H2220/116 ,  G10H2210/111

摘要： Indications of sample machine learning models which create synthetic content items are provided via programmatic interfaces. A representation of a synthetic content item produced by one of the sample models in response to input obtained from a client of a provider network is presented. In response to a request from the client, a machine learning model is trained to produce additional synthetic content items.

公开(公告)号：US11551652B1

公开(公告)日：2023-01-10

申请号：US16897094

申请日：2020-06-09

申请人： Amazon Technologies, Inc.

发明人： Ambika Pajjuri ,  Nagajyothi Nookula ,  Rahul Suresh ,  Sunil Mallya Kasaragod ,  Richard Lee ,  Hsin Chieh Chen

IPC分类号： G10H1/00 ,  G06N3/04 ,  G06N3/08

摘要： Indications of sample machine learning models which create synthetic content items are provided via programmatic interfaces. A representation of a synthetic content item produced by one of the sample models in response to input obtained from a client of a provider network is presented. In response to a request from the client, a machine learning model is trained to produce additional synthetic content items.

公开(公告)号：US11049481B1

公开(公告)日：2021-06-29

申请号：US16698801

申请日：2019-11-27

申请人： Amazon Technologies, Inc.

发明人： Liang Li ,  Wayne Chi ,  Rahul Suresh ,  Dylan Jackson ,  Haoting Li

IPC分类号： G10H1/18 ,  G10H1/00 ,  G06F16/61 ,  G06F16/11 ,  G06F16/638 ,  G06N3/04 ,  G06N3/08

摘要： Methods and apparatus for providing metrics for the quality, attributes, and relationships of music including AI-generated music. Music classification and visualization methods are described that involve transforming music files into graphical representations, generating a similarity matrix for the music files using structural similarity techniques, and generating visualizations of the relationships among the music files using multidimensional scaling techniques. Qualitative scoring methods for AI-generated music are described that involve classifying the AI-generated music using a multi-genre classifier, generating a similarity metric for the AI-generated music to other genres using structural similarity techniques and multidimensional scaling techniques, and generating a qualitative score for the music using confidence in the classification in combination with the similarity metric.