首页|'Voice Modification' in Patent Application Approval Process (USPTO 20240355346)
'Voice Modification' in Patent Application Approval Process (USPTO 20240355346)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
This patent application has not been assigned to a company or institution.The following quote was obtained by the news editors from the background informa tion supplied bythe inventors: “Machine learning systems may use various techni ques to receive input features and outputmodified representation of the input f eatures. Autoencoders, for example, are an unsupervised learningtechnique, whic h use neural networks for representation learning. Autoencoders may receive inpu t featuresin the form of images, video or audio waveforms, among other signals. For example, using voice recognitiontechnology, computing systems can generate a transcript, which is a modified representation of the wordsuttered by a pres enter or participants in a meeting. A machine learning system may process an aud iorecording or live stream of an event and produce a modified representation of the audio recording or livestream, such as a transcript or a modified live str eam.”
NETL
NSTL
