Operating method for an automated language recognizer intended for the speaker-independent language recognition of words in different languages and automated language recognizer

• US 20050033575A1
• Filed: 01/02/2003
• Published: 02/10/2005
• Est. Priority Date: 01/17/2002
• Status: Active Grant

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Schneider, Tobias
• Granted Patent: US 7,974,843 B2
• Time in Patent Office: Days
• US Class Current: 704/254
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/142 Hidden Markov Models [HMMs]
• CPC Class Codes: G10L 15/16 using artificial neural networks
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

The invention relates to an operating method for an automated language recognizer intended for the speaker-independent language recognition of words from different languages, particularly for recognizing names from different languages. The method is based on a language defined as the mother tongue and has an input phase for establishing a language recognizer vocabulary. Phonetic transcripts are determined for words in various languages in order to obtain phoneme sequences for pronunciation variants The phonemes of each relevant phoneme set of the mother tongue are then specifically mapped to determine phoneme sequences that correspond to pronunciation variants.

Claims

1-11. -11. (canceled).

12. A method for automated language recognition of words from different languages said method comprising the steps of:

(a) loading a phoneme set associated with a language specified as a mother tongue into a mother tongue language recognizer;

(b) determining the phonetic transcripts of each word for N various languages not specified as the mother tongue to obtain N first phoneme sequences for each word corresponding to N first pronunciation variants;

(c) calculating a phoneme map by mapping the first phoneme sequences of each of said N languages to a relevant phoneme set of the mother tongue;

(d) determining N second phoneme sequences corresponding to N second pronunciation variants from said phoneme map for each word; and

(e) processing said N second phoneme sequences with the phoneme set associated with the language specified as a mother tongue to identify matching or similar words.

13. The method according to claim 12, further comprising a step of adding the N second phoneme sequences for each word in a language recognition vocabulary located in the mother tongue language recognizer.

14. The method according to claim 12, further comprising the step of processing the N second phoneme sequences to determine distances to the N second pronunciation variants.

15. The method according to claim 14, further comprising a step of classifying each N second phoneme sequences to identify respective distances.

16. The method according to claim 15, further comprising a step of eliminating any N second phoneme sequences that do not meet or exceed a predetermined threshold.

17. The method according to claim 16, wherein the distances are Leveshtein distances.

18. The method according to claim 12, further comprising the step of determining the probabilities that each word for N various languages not specified as the mother tongue belong to a specified set of languages, said step of determining probabilities occurring before step (a).

19. The method according to claim 18, further comprising the step of eliminating languages from said specified set that do not meet or exceed a predetermined threshold.

20. The method according to claim 12, wherein the step of determining the phonetic transcripts of each word for N various languages not specified as the mother tongue is performed by at least one neural network.

21. The method according to claim 12, wherein processing said N second phoneme sequences with the phoneme set associated with the language specified as a mother tongue is performed via a Hidden Markov Model.

22. An automatic language recognizing apparatus, receiving words from various languages, comprising:

a mother tongue language recognizer, said recognizer storing a phoneme set of a predetermined mother tongue;

a first processing module for determining the phonetic transcripts of words from N various languages in order to obtain N first phoneme sequences for each word corresponding to N first pronunciation variants;

a second processing module for implementing a mapping of the phonemes of each of N language to a particular phoneme set of the mother tongue;

a third processing module for applying the mapping, implemented by means of the second processing module, to the N first phoneme sequences for each word determined by means of the first processing module, with N second phoneme sequences corresponding to N second pronunciation variants being obtained per word, that can be recognized by means of the mother tongue language recognizer; and

a fourth processing module for creating a language recognizable vocabulary with the N second phoneme sequences per word, obtained by the third processing module, for the mother tongue language recognizer.

23. The automatic language recognizing apparatus according to claim 22, further comprising a fifth processing module for processing the N second phoneme sequences corresponding to the N second pronunciation variants of each word to obtain distances for each N second phoneme sequence.

24. The automatic language recognizing apparatus according to claim 23, wherein said distances are Levenshtein distances.

25. The automatic language recognizing apparatus according to claim 24, wherein the N second phoneme sequence distances not meeting or exceeding a predetermined threshold are eliminated from further processing.

26. The automatic language recognizing apparatus according to claim 22, further comprising a language identifier, coupled to the first processing module, wherein the language identifier determines a probability of each word belonging to each of the N different languages.

27. The automatic language recognizing apparatus according to claim 26, further comprising a language reducer that reduces the number of languages from the first processing module to be processed if said probability does not meet or exceed a predetermined thresholds.

28. The automatic language recognizing apparatus according to claim 22, wherein the first processing module comprises at least one neural network for determining the phonetic transcripts.

29. The automatic language recognizing apparatus according to claim 22, wherein the mother tongue language recognizer comprises a Hidden Markov model that has been created for the language defined as the mother tongue.