The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We measure the effects of a weak language model, estimated from as little as 100k words of text, on unsupervised acoustic model training and then explore the best method of using word confidences to estimate n-gram counts for unsupervised language model training. Even with 100k words of text and 10 hours of training data, unsupervised acoustic modeling is robust, with 50% of the gain recovered when...
Discriminative re-ranking has been able to significantly improve parsing performance, and co-training has proven to be an effective weakly supervised learning algorithm to bootstrap parsers from a small in-domain seed labeled corpus using a large amount of unlabeled in-domain data. In this paper, we present systematic investigations on combining discriminative re-ranking and co-training, including...
For effective training of acoustic and language models for spontaneous speech such as meetings, it is significant to exploit the texts available in a large scale, which may not be faithful transcripts of the utterances. We have proposed a language model transformation scheme to cope with the differences between verbatim transcripts of spontaneous utterances and human-made transcripts such as those...
Automatic phone segmentation techniques based on model selection criteria are studied. We investigate the phone boundary detection efficiency of entropy- and Bayesian- based model selection criteria in continuous speech based on the DISTBIC hybrid segmentation algorithm. DISTBIC is a text-independent bottom-up approach that identifies sequential model changes by combining metric distances with statistical...
The baseline system PRLM has the best performance on NIST language recognition evaluation tasks. But this system needs orthographically or phonetically transcribed utterances which can not be easily obtained from Chinese dialects and minority languages. So, the PRLM system is not used to these languages. To overcome this limitation, we present the Gaussian mixture model recognizer followed by language-dependent...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.