Invention Grant
- Patent Title: Generating sounds for detectability by neural networks
- Patent Title (中): 通过神经网络产生可检测的声音
-
Application No.: US14709745Application Date: 2015-05-12
-
Publication No.: US09443517B1Publication Date: 2016-09-13
- Inventor: Jakob Nicolaus Foerster , Christopher Walter George Thornton , Rohit Prakash Prabhavalkar
- Applicant: Google Inc.
- Applicant Address: US CA Mountain View
- Assignee: Google Inc.
- Current Assignee: Google Inc.
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G10L15/16
- IPC: G10L15/16 ; G10L15/22 ; G10L15/08 ; G10L15/06 ; G10L15/32 ; G10L25/30

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes accessing a first neural network that was trained to recognize a given keyword or keyphrase using a set of hotword training data, wherein the hotword training data includes positive hotword training data that correspond to utterances of the keyword or keyphrase, and negative hotword training data that corresponds to utterances of words or phrases that are other than the keyword or keyphrase, selecting a seed hotsound, mapping, to a feature space, (i) the positive hotword training data, (ii) the negative hotword training data, and (iii) the seed hotsound, performing an optimization of a position of the seed hotsound within the feature space to generate a modified seed hotsound, generating a set of hotsound training data using the modified seed hotsound, training a second neural network to recognize the modified seed hotsound using the generated set of hotsound training data, and using the trained second neural network to recognize the modified hotsound.
Information query