Language model parameter estimation using user transcriptions

In limited data domains, many effective language modeling techniques construct models with parameters to be estimated on an in-domain development set. However, in some domains, no such data exist beyond the unlabeled test corpus. In this work, we explore the iterative use of the recognition hypothes...

पूर्ण विवरण

ग्रंथसूची विवरण
मुख्य लेखकों: Hsu, Bo-June, Glass, James R.
अन्य लेखक: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
स्वरूप: लेख
भाषा:en_US
प्रकाशित: Institute of Electrical and Electronics Engineers 2010
विषय:
ऑनलाइन पहुंच:http://hdl.handle.net/1721.1/58944
https://orcid.org/0000-0002-3097-360X

समान संसाधन