http://www.isca-students.org/taxonomy/term/92/0 en http://www.isca-students.org/standard_english_database_req <p>hello.<br /> my name is sarwat nasir and i m working on a speaker recognition project.the underlaying idea is that humans can recognise speakers by the diff in there pronounciations even if they dont understand what he is speaking about. for that purpose i need a presegmented speech(segmented into phonemes).<br /> any information to this ll b highly appreciated<br /> regards<br /> sarwat</p> http://www.isca-students.org/standard_english_database_req#comment Speech and multimodal resources Mon, 05 Mar 2007 11:47:36 +0100 sarwat 5314 at http://www.isca-students.org http://www.isca-students.org/looking_for_best_practices_for_collecting_speech_for_a_free_gpl_speech_corpus <p>This is a cross-post from comp.speech.research. My apologies if you have already seen this.</p> <p>Hi,</p> <p>I am the admin for the VoxForge project. We are collecting user<br /> submitted speech for incorporation into a GPL Acoustic Model ('AM').<br /> Currently we have a Julius/HTK AM being created daily, incorporating<br /> newly submitted audio on a nightly basis.</p> <p>I am confused as to which approach to take in the creation of the<br /> VoxForge speech corpora. Up until now, we have been asking users to<br /> submit 'clean' speech - i.e. record their submission to ensure that all<br /> noise (i.e. non-speech noise such as echo, hiss, ...) is kept to an</p> <p><a href="http://www.isca-students.org/looking_for_best_practices_for_collecting_speech_for_a_free_gpl_speech_corpus">read more</a></p> http://www.isca-students.org/looking_for_best_practices_for_collecting_speech_for_a_free_gpl_speech_corpus#comment Speech and multimodal resources Tue, 13 Feb 2007 04:16:07 +0100 kmaclean 4965 at http://www.isca-students.org