N06-1053 literature for indexing spoken words in audio recordings . The TREC ( Text REtrieval Conference
H94-1073 retrieval of speech documents , i.e. audio recordings containing spoken text . The
H05-1119 problem of indexing spoken words in audio recordings . The TREC ( Text REtrieval Conference
H94-1073 retrieval of speech documents , i.e. audio recordings containing spoken text \ -LSB-
P03-1071 automatically divide text documents , audio recordings , or video segments , into topically
H05-1119 searching the spoken content of the audio recording . Several approaches have been
H05-1119 system to search directly the audio recordings by key phrases . We have identified
N09-3009 persuasive dialog corpus consisting of audio recordings of 10 interactions averaging
A00-2025 Table 1 ) . Looking at the four audio recordings individually , we see that the
P06-2042 transcriptions of the speeches as well as audio recordings of them . Approximately one tenth
C04-1159 transcriptions of speeches as well as audio recordings . Approximately one tenth of
C02-2003 the voice search system using audio recordings that we collected for this purpose
H05-1119 phrases users want to use . Third , audio recordings will accumulate . When the audio
E12-1052 corpus . Unfor - tunately , the audio recordings of the first recording day were
E09-1039 subjects , 11 women and 10 men . All audio recordings , interviews and discus - sions
H05-1119 1997 ) . She has shown that the audio recordings are valuable to users if portions
N09-5003 use a web interface to play the audio recording and create phonetic transcriptions
J02-4003 transcripts in tandem with the original audio recording . Although their interface helps
P05-2021 which are expected to appear in audio recordings might be collected and added
N09-1072 shoulder sash , thus resulting in two audio recordings of the approximately 1100 4-minute
hide detail