- Patent Title: Mask estimation apparatus, model learning apparatus, sound source separation apparatus, mask estimation method, model learning method, sound source separation method, and program
-
Application No.: US16971656Application Date: 2019-02-19
-
Publication No.: US11562765B2Publication Date: 2023-01-24
- Inventor: Takuya Higuchi , Tomohiro Nakatani , Keisuke Kinoshita
- Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
- Applicant Address: JP Tokyo
- Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
- Current Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
- Current Assignee Address: JP Tokyo
- Priority: JPJP2018-029969 20180222
- International Application: PCT/JP2019/005976 WO 20190219
- International Announcement: WO2019/163736 WO 20190829
- Main IPC: G10L25/00
- IPC: G10L25/00 ; G10L25/30 ; G06N3/08 ; G06N7/00 ; G10L25/03
Abstract:
A mask estimation apparatus for estimating mask information for specifying a mask used to extract a signal of a specific sound source from an input audio signal includes a converter which converts the input audio signal into embedded vectors of a predetermined dimension using a trained neural network model and a mask calculator which calculates the mask information by fitting the embedded vectors to a mixed Gaussian model.
Information query
