14th International Congress of Phonetic Sciences (ICPhS-14)

San Francisco, CA, USA
August 1-7, 1999


Narrow Phonetic Transcription for Development of a Large Vocabulary Isolated Word Recognizer

Lex Olorenshaw, Mariscela Amador, Ruxin Chen, Xavier Menendez-Pidal

Sony U.S. Research Laboratories, USA

To build a very large vocabulary (50K) isolated word speech recognizer, speech data from over 200 native speakers of American English was recorded and manually transcribed. This paper explains the transcription method used, the motivation, and preliminary results implemented in the recognizer.
   The symbol set was expanded to allow for narrow phonetic transcriptions, similar to the level of detail allowed by the International Phonetic Alphabet (IPA). By expanding the symbol set, the following was expected:

Full Paper

Bibliographic reference.  Olorenshaw, Lex / Amador, Mariscela / Chen, Ruxin / Menendez-Pidal, Xavier (1999): "Narrow phonetic transcription for development of a large vocabulary isolated word recognizer", In ICPhS-14, 1693-1696.