Hi! On 01:13 Tue 18 Mar , sampriti neog wrote: > To, > Kernelnewbies > I would like to participate in GOOGLE SUMMER OF CODE 2014 with your > prestigious organization. I want to propose an idea regarding music files. > My idea is to make a song to lyrics converter using voice separation and > then speech recognition idea so that any ongoing music can be converted to > their wordings instantaneously without accessing internet for the lyrics. This sounds very hard. Speech recognition is hard enough on its own. Background "noise" (instruments), dialect and lack of training to the speaker's voice will make it even harder. Besides, people here will probably not be able to help you much. You may want to send this request to a speech recognition project: http://en.wikipedia.org/wiki/List_of_speech_recognition_software#Open_source_acoustic_models_and_speech_corpus > This project will be really helpful in our country because most of the > people over here don't have access to internet and lyrics of all the songs > aren't available. Why don't you do something about the lack of internet access instead? I guess that causes a lot more problems than the one you described. -Michi -- programing a layer 3+4 network protocol for mesh networks see http://michaelblizek.twilightparadox.com _______________________________________________ Kernelnewbies mailing list Kernelnewbies@xxxxxxxxxxxxxxxxx http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
