| 摘要 |
A system, system, and program for facilitating navigation of voice data are provided. Tokens are added to voice data based on predefined content criteria. Then, bidirectional scanning of the voice data to a next token within the voice data is enabled, such that navigation to pertinent locations within the voice data during playback is facilitated. When adding tokens to voice data, the voice data may be scanned to detect pauses, changes in voice inflection, and other vocal characteristics. Based on the detected vocal characteristics, tokens identifying ends of sentences, separations between words, and other structures are marked. In addition, when adding tokens to voice data, the voice data may be first converted to text. The text is then scanned for keywords, phrases, and types of information. Tokens are added in the voice data at locations identified within the text as meeting the predefined content criteria.
|
