METHOD AND DEVICE FOR GENERATING VOCABULARY ENTRY FROM ACOUSTIC DATA

• US 20110093259A1
• Filed: 06/17/2009
• Published: 04/21/2011
• Est. Priority Date: 06/27/2008
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Saffer, Zsolt
• Granted Patent: US 8,751,230 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/16 using artificial neural networks
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams

Abstract

A method and a device (1) for automatically generating vocabulary entry from input acoustic data (3), comprising a vocabulary entry type-specific acoustic phonetic transcription module (2; T) and a classifier module (6; 6′) for the classification of vocabulary entry types on the basis of the phonetic structure, wherein the classification of vocabulary entries is carried out in accordance with a number of predetermined types; and vocabulary entry type-specific phoneme-to-grapheme conversion means (28), to derive the respective vocabulary entries comprising a pair of a phonetic transcription and its grapheme form.

Claims

1. A method for automatically generating vocabulary entry from input acoustic data, said method comprising the steps of:

performing a vocabulary entry type-specific acoustic phonetic transcription and a classification of vocabulary entry types based on phonetic structure, wherein the classification of vocabulary entries is carried out in accordance with a number of predetermined types; and

performing a vocabulary entry type-specific phoneme-to-grapheme conversion, to derive the respective vocabulary entries comprising a pair of a phonetic transcription and its grapheme form.

2. The method according to claim 1, wherein syllable language modeling is applied during vocabulary entry type-specific acoustic phonetic transcription.

3. The method according to claim 1, wherein the classification of vocabulary entries is carried out together with the vocabulary entry type-specific acoustic phonetic transcription in a combined step.

4. The method according to claim 3, wherein the vocabulary entry types are hypothesized during acoustic phonetic transcription, with separate acoustic phonetic transcription being applied for each hypothesized vocabulary entry type.

5. The method according to claim 1, wherein for automatic vocabulary entry type classification a neural network based language identification is applied.

6. The method according to claim 5, wherein at first, the neural network based classification is carried out, whereafter the acoustic phonetic transcription is performed on the basis of the vocabulary entry type information.

7. The method according to claim 1, wherein the vocabulary entries are classified according to four types, namely vocabulary entries fitting to a given language morphology;

vocabulary entries fitting to morphology of at least one other supported language;

vocabulary entries which do not fit to any supported language morphology but are normally pronounced; and

vocabulary entries which do not fit to any supported language morphology and are pronounced by spelling.

8. The method according to claim 7, wherein a standard acoustic model is applied together with syllable language models with respect to vocabulary entries which fit to one of the supplied language morphologies, whereas a high resolution acoustic model is applied with respect to normal abbreviation type and a spelling acoustic model is applied with respect to spelled abbreviations.

16. A computer program product that can be loaded directly into a memory of a computer and comprises sections of a software code for performing the method according to claim 1 when the computer program product is on the computer.

9. A device for automatically generating vocabulary entry from input acoustic data and comprising

vocabulary entry type classifier means functioning based on phonetic structure and vocabulary entry type-specific acoustic phonetic transcription means,

vocabulary entry compositor means,

wherein the vocabulary entry type classifier means are arranged to classify the vocabulary entries in accordance with a number of predetermined types, and

wherein the vocabulary entry compositor means comprise vocabulary entry type-specific statistical phoneme-to-grapheme converter means.

10. The device according to claim 9, wherein the acoustic phonetic transcription means comprise syllable language model means.

11. The device according to claim 9, wherein the acoustic phonetic transcription means comprise standard, high resolution and spelling acoustic model means.

12. The device according to claim 9, wherein the vocabulary entry type classifier means comprise gate means for respective vocabulary entry types, said gate means being arranged to output a respective vocabulary entry type information together with the phonetic transcription.

13. The device according to claim 9, wherein the vocabulary entry type classifier means comprise neural network means arranged to output probability information for every predetermined vocabulary entry type together with the input acoustic data.

14. The device according to claim 13, wherein the vocabulary entry type information and the input acoustic data are supplied to the vocabulary entry type-specific acoustic phonetic transcription means which are arranged to output the vocabulary entry type information together with the phonetic transcription.

15. The device according to claim 14, wherein the acoustic phonetic transcription means comprise an acoustic model selector associated with given acoustic model means as well as a syllable language model selector associated with given syllable language model means, both selectors being connected to the vocabulary entry type information.