机译:Sequence-Based Pronunciation Variation Modeling for Spontaneous ASR Using a Noisy Channel Approach
National Institute of Information and Communications Technology, Kyoto-fu, 619-0289 Japan Department of Information Technology,University of Ulm, Germany;
National Institute of Information and Communications Technology, Kyoto-fu, 619-0289 Japan Institute of Science and Technology,Nara, Japan;
National Institute of Information and Communications Technology, Kyoto-fu, 619-0289 JapanNational Institute of Information and Communications Technology, Kyoto-fu, 619-0289 Japan Presently, with Nara Institute of Science and Technology,Nara, JapanDepartment of Information Technol-ogy, University of Ulm, Germany;
spontaneous speech; noisy channel approach; joint-sequence models; statistical machine translation;