I read the FAQ and found sphinx4 doesn't support word-spotting yet. My question is about the definition of word-spotting. Does that mean to detect the word out of the vacabulary or the capability to do the time alignment between transcipt and the real audio file. Thank you very much!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Word Spotting
The identification of pre-defined words or phrases in a stream of speech utterances. These words or phrases are called keywords. Typically the rest of the speech is ignored. For instance, if an interactive schedule program prompted the user for his destination city, and he responded, "I would like to visit London." then the task of the word spotting program is to isolate "London" from the remainder of the digitized input.
Paul
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Anonymous
-
2004-08-05
Hi, Paul:
Thanks a lot for your reply. So, if I am right, Sphinx4 currently can not do the job to locate the word in the input speech, right? For example, there is a two minutes long input audio. This audio file contains the word "London". Can Sphinx4 locate the exact time slot where the word "London" shows up? Thanks again!
--Larry
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I read the FAQ and found sphinx4 doesn't support word-spotting yet. My question is about the definition of word-spotting. Does that mean to detect the word out of the vacabulary or the capability to do the time alignment between transcipt and the real audio file. Thank you very much!
There's a good definition from
http://www.techonline.com/community/ed_resource/feature_article/20043
Word Spotting
The identification of pre-defined words or phrases in a stream of speech utterances. These words or phrases are called keywords. Typically the rest of the speech is ignored. For instance, if an interactive schedule program prompted the user for his destination city, and he responded, "I would like to visit London." then the task of the word spotting program is to isolate "London" from the remainder of the digitized input.
Paul
Hi, Paul:
Thanks a lot for your reply. So, if I am right, Sphinx4 currently can not do the job to locate the word in the input speech, right? For example, there is a two minutes long input audio. This audio file contains the word "London". Can Sphinx4 locate the exact time slot where the word "London" shows up? Thanks again!
--Larry