| US 7,522,967 B2 | ||
| Audio summary based audio processing | ||
| Tong Zhang, San Jose, Calif. (US); Ramin Samadani, Menlo Park, Calif. (US); Yining Deng, Sunnyvale, Calif. (US); and Ken K. Lin, Redwood City, Calif. (US) | ||
| Assigned to Hewlett-Packard Development Company, L.P., Houston, Tex. (US) | ||
| Filed on Jul. 01, 2003, as Appl. No. 10/611,449. | ||
| Prior Publication US 2005/0004690 A1, Jan. 06, 2005 | ||
| Int. Cl. G06F 17/00 (2006.01) | ||
| U.S. Cl. 700—94 | 41 Claims |
| 1. An audio processing method, comprising:
identifying audio summaries of respective audio pieces, wherein each of the audio summaries comprises digital content summarizing
at least a portion of the respective audio piece, and the identifying comprises for each of the audio pieces
selecting constituent segments of the audio piece as its respective ones of the audio summaries and
ranking its audio summaries into different levels of a respective audio summary hierarchy;
determining transition audio segments each comprising a form of audio content that is different from the audio summaries and
distinguishes the transition audio segment from the audio summaries;
concatenating the transition audio segments and ones of the audio summaries ranked at a selected level of the audio summary
hierarchies into a sequence in which at least one of the transition audio segments is between successive ones of the audio
summaries; and
rendering the sequence.
|