| 主权项 |
1. A method comprising:
receiving digital representations of audio signals, wherein the audio signals are produced by a suitable device; producing phonetic indexes of the audio signals based on said digital representations thereof; producing phonetic N-gram sequences from the phonetic indexes by segmenting the phonetic indexes into a plurality of phonetic N-grams; producing inverted indexes of the plurality of phonetic N-grams; obtaining a textual search term; converting the textual search term into a phonetic search term; searching the phonetic search term on the inverted indexes; ranking the digital representations of the audio signals based on matching between the search query and detected events of the search in the inverted indexes such that a rank reflects the probability that the textual search term is found within any of the audio signals, wherein the ranking is according to the following formula:Rankj=100*(1-a*log2(1+1∑i=0N-1Ci)) where the rank is the rank level, j denotes the audio signal, Cj is the confidence score of i-th detected event that satisfy a query in the j-th signal, N is the number of detected events within the j-th signal that satisfy the search query, and a is a constant; and based on the ranking, determining whether or not to automatically perform on each signal of the audio signals a second slower and more accurate phonetic search based on non-inverted indexing, in case a determination to perform the second search is satisfied then the second slower and more accurate phonetic search based on non-inverted indexing is carried out; responsive to performing the second slower and more accurate search, determining search results with respect to the textual search term; and playing back, via a media player, the search results with respect to said digital representations of the audio signals. |
