Automatic language identification
Yeshwant K. Muthusamy, Andreas Spitz · 1997
The importance of spoken language ID in the global community cannot be ignored. Telephone companies would like to quickly identify the language of foreign callers and route their calls to operators who can speak the language. A multilanguage translation system dealing with more than two or three languages needs a language identification front-end that will route the speech to the appropriate translation system. And, of course, governments around the world have long been interested in spoken language ID for monitoring purposes. Despite twenty-odd years of research, the field of spoken language ID has suffered from the lack of (i) a common, public-domain multilingual speech corpus that could be used to evaluate different approaches to the problem, and (ii) basic research. The recent public availability of the OGI Multilanguage Telephone Speech Cor-pus (OGI TS) (Muthusamy, Cole, et al., 1992), designed specifically for language ID, has led to renewed interest in the field and fueled a proliferation of different approaches to the problem. This corpus currently contains sponta-neous and fixed vocabulary speech from 11 languages. The National Institute of Standards and Technology (NIST) 1Automatic language identification (language ID for short) can be defined as the problem of identifying the language from a sample of speech or text. Researchers have been working on spoken and written language ID for the past two decades. 1