SYSTEMS AND METHODS FOR BUILDING A NATIVE LANGUAGE PHONEME LEXICON HAVING NATIVE PRONUNCIATIONS OF NON-NATIE WORDS DERIVED FROM NON-NATIVE PRONUNCIATONS

• US 20090248395A1
• Filed: 10/01/2008
• Published: 10/01/2009
• Est. Priority Date: 03/31/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Janke, Eric, Sicconi, Roberto, Alewine, Neal, Sharp, Paul
• Granted Patent: US 7,957,969 B2
• Time in Patent Office: Days
• US Class Current: 704/7
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams

Abstract

Systems and methods are provided for automatically building a native phonetic lexicon for a speech-based application trained to process a native (base) language, wherein the native phonetic lexicon includes native phonetic transcriptions (base forms) for non-native (foreign) words which are automatically derived from non-native phonetic transcriptions of the non-native words.

Claims

1. A system for generating base forms for non-native language in a speech-based system trained for processing a native language, the system comprising:

a text processing system configured to receive input textual data containing both native language and non-native language words, the text processing system configured to identify the native language and non-native language words within the textual data, to generate a native phonetic transcription of the native language word using phonetic units of the native language, and to generate a non-native phonetic transcription of the non-native language word using phonetic units of the non-native language;

a pronunciation generator configured to generate a native pronunciation of the non-native language word using phonetic units of the native language by mapping the phonetic units of the non-native phonetic transcription to acoustically similar phonetic units of the native language; and

a memory configured to store the input textual data with the corresponding native phonetic transcription of the native language word and the mapped native pronunciation of the non-native language word in a native phonetic lexicon.