Bill Byrne Associate Research Professor Center for Language and Speech Processing and Department of Electrical and Computer Engineering The Johns Hopkins University

Current Research

• MALACH: Multilingual Access to Large Spoken Archives
  I am a co-PI on this NSF ITR project which is developing speech and language technology to search and index large oral history collections. I'm currently focused on ASR for heavily accented and elderly speech, unsupervised language modeling, long-term unsupervised speaker adaptation, and integration of ASR into spoken document retrieval.

• Models and Algorithms for Statistical Machine Translation
  • Weighted Finite State Transducer Implementation of Phrase Template Translation Models
  • Minimum Risk Translation and Bitext Word Alignment