Method of determining database entries

• US 20020169751A1
• Filed: 04/18/2002
• Published: 11/14/2002
• Est. Priority Date: 04/20/2001
• 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: Krass, Stefanie, Hodam, Henrik
• Granted Patent: US 7,496,508 B2
• Time in Patent Office: Days
• US Class Current: 707/1
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/142 Hidden Markov Models [HMMs]
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 2015/228 of application context

Abstract

The invention relates to a method of determining database entries of a database (9) by means of an automatic dialog system (1) in which the following steps are provided:

1.1 temporary storage of a speech input,

1.2 processing of the speech utterance by means of an automatic speech recognition device (4) and generation of a speech recognition result using a first lexicon (6) which has a first set of lexicon entries, where a lexicon entry contains at least one acoustic reference,

1.3 search for a database entry corresponding to the speech recognition result,

1.4 for the case where no database entry is found in step 1.3,

adaptation of the first lexicon (6) so that the first lexicon (6) has a second set of lexicon entries which differs from the first set of lexicon entries by at least one lexicon entry,

repetition of steps 1.2 and 1.3 using the temporarily stored speech utterance and the adapted first lexicon (6).

Claims

1. A method of determining database entries of a database (9) by means of an automatic dialog system (1) in which the following steps are provided:

1.1 temporary storage of speech input,

1.2 processing of the speech input by means of an automatic speech recognition device (4) and generation of a speech recognition result using a first lexicon (6) which has a first set of lexicon entries, where a lexicon entry contains at least one acoustic reference,

1.3 search for a database entry corresponding to the speech recognition result,

1.4 for the case where no database entry is found in step 1.3,

adaptation of the first lexicon (6) so that the first lexicon (6) has a second set of lexicon entries which differs from the first set of lexicon entries by at least one lexicon entry,

repetition of steps 1.2 and 1.3 using the temporarily stored speech utterance and the adapted first lexicon (6).

2. A method as claimed in claim 1, characterized in that the lexicon entries are taken from a second lexicon (7) which serves as an overall lexicon.

3. A method as claimed in claim 1 or 2, characterized in that the steps 1.2 to 1.4 are repeated until an interrupt criterion is fulfilled.

4. A method as claimed in any one of claims 1 to 3, characterized in that categories of lexicon entries are provided which correspond to categories of database entries and in that the first lexicon after adaptation with respect to a category of lexicon entries deviates from its form before adaptation in at least one lexicon entry.

5. A method as claimed in any one of claims 1 to 4, characterized in that categories of lexicon entries are provided which correspond to categories of database entries, and in that allocated to at least one category of lexicon entries, of which entries the first lexicon before adaptation contains at least a subset, a second category of lexicon entries is allocated of which entries the first lexicon after adaptation contains at least a subset.

6. A method as claimed in any one of claims 1 to 5, characterized in that a speech recognition result supplied by a speech recognition device contains a number N of best recognition result alternatives with N≧

1, and in that the adaptation of the lexicon depends on at least one recognition result alternative.

7. A method as claimed in any one of claims 1 to 6, characterized in that the database entries are parts of a Yellow Pages data collection.

8. A method as claimed in any one of claims 1 to 7, characterized in that the dialog system has a telephone interface (2) via which speech inputs and speech outputs are transmitted.

9. An automatic dialog system (1) for determining database entries of a database (9) with system components for carrying out the followings steps:

9.1 temporary storage of speech utterance to be input,

9.2 processing of the speech utterance by means of an automatic speech recognition device (4) and generation of a speech recognition result using a first lexicon (6) which has a first set of lexicon entries, where a lexicon entry contains at least one acoustic reference,

9.3 search for a database entry corresponding to the speech recognition result,

9.4 for the case where no database entry is found in step 9.3,

adaptation of the first lexicon (6) so that the first lexicon (6) has a second set of lexicon entries which differ from the first set of lexicon entries by at least one lexicon entry,

repetition of steps 9.2 and 9.3 using the temporarily stored speech utterance and the adapted first lexicon (6).