Audio segmentation with energy-weighted bandwidth bias
US7243062B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Oct 25, 2002 |
| Grant date | Jul 10, 2007 |
| Priority date | — |
| Expiry date | Mar 30, 2025 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L25/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method (200) and apparatus (100) for segmenting a sequence of audio samples into homogeneous segments (550 and 555) are disclosed. The method (200) forms a sequence of frames (701 to 704) along the sequence of audio samples, and extracts, for each frame, a data feature. The data features form a sequence of data features. Transition points in the sequence of data features are thin detected by applying the Bayesian Information Criterion to the sequence of data features. The transition points define the homogeneous segments (550 and 555). Preferably the data feature is single-dimensional and a leptokurtic distribution is used as an event model in the Bayesian Information Criterion.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.