Speech recognition method and device

• US 6,721,702 B2
• Filed: 12/10/2001
• Issued: 04/13/2004
• Est. Priority Date: 06/10/1999
• Status: Expired due to Term

• Current Assignee: Maxlinear Incorporated
• Original Assignee: Infineon Technologies AG
• Inventors: Schneider, Peter
• Primary Examiner(s): CHAWAN, VIJAY B
• Application Number:
  US10/013,231
• Publication Number:
  US 20020087324A1
• Time in Patent Office: 855 Days
• Field of Search: 704/270-275, 704/251, 704/240, 704/231, 704/243, 704/235, 704/260, 704/239, 704/256, 434/167, 434/156, 434/112
• US Class Current: 704/251
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

In a method for interactive voice recognition, a word spoken by a user is analyzed. If no definite assignment to a word of a predetermined vocabulary is possible, the word is assigned a number of possible words from the vocabulary. For each word of the preselection of words, a decisive letter that makes the word distinguishable from the other words of the preselection of words is determined. The user is prompted to say the decisive letter for the word being sought. The word being sought is ascertained by voice recognition of the decisive letter.

Claims

1. A method for interactive voice recognition of a word by a voice recognition system, which comprises the steps of:

performing a word recognition mode by the steps of;

converting a spoken word into an electrical word voice signal;

analyzing the electrical word voice signal for recognizing the spoken word front a vocabulary of predetermined words;

performing the following steps if a definite assignment of the electrical word voice signal to a word from the vocabulary of predetermined words cannot be made;

compiling a preselection of words from the vocabulary of predetermined words which have a sufficient probability of being the spoken word;

determining for each word forming the preselection of words, at least one decisive letter which makes the word distinguishable from other words in the preselection of words;

inquiring which of the decisive letters for the words of the preselection of words is appropriate during a spelling recognition mode;

converting a spelling voice input into an assigned electrical spelling voice signal; and

analyzing the assigned electrical spelling voice signal for recognizing the decisive letter.

2. The method according to claim 1, which comprises during the inquiring step, suggesting the decisive letters previously determined to a user using the voice recognition system.

3. The method according to claim 2, which comprises performing the suggesting step acoustically.

4. The method according to claim 1, which comprises prompting a user to repeat the spoken word it a number of words contained in the preselection of words exceeds a predetermined limit value.

5. The method according to claim 1, which comprises performing the spelling recognition mode as an alphabet-word recognition mode.

6. The method according to claim 5, which comprises using at least one of user defined alphabet words and a number of alphabet words for identifying the letters.

7. The method according to claim 1, which comprises using the spelling recognition mode as a letter recognition mode.

8. A device for voice recognition, comprising:

a word recognition unit for converting a spoken word into an electrical word voice signal and analyzing the electrical word voice signal for recognizing a word from a vocabulary of predetermined words;

a selection logic, which, if a definite assignment of the electrical word voice signal to the word of the vocabulary of predetermined words cannot be made, compiles a preselection of words from the vocabulary of predetermined words among which the spoken word is located, said selection circuit coupled to said word recognition unit;

a logic circuit for determining for each word of the preselection of words, at least one decisive letter which makes the word distinguishable from other words of the preselection of words, said logic circuit coupled to said word recognition unit;

an output unit for outputting the decisive letter for each of the words of the preselection of words, said output unit coupled to said word recognition unit; and

a spelling recognition unit for converting a spelling voice input into an associated electrical spelling voice signal, and for analyzing the associated electrical spelling voice signal for recognizing of the decisive letter, said spelling recognition unit connected to said word recognition unit.

9. A navigation system, comprising:

a device for voice recognition, including;

a word recognition unit for converting a spoken word into an electrical word voice signal and analyzing the electrical word voice signal for recognizing a word from a vocabulary of predetermined words;

a selection logic, which, it a definite assignment of the electrical word voice signal to the word of the vocabulary of predetermined words cannot be made, compiles a preselection of words from the vocabulary of predetermined words among which the spoken word is located, said selection circuit coupled to said word recognition unit;

a logic circuit for determining for each word of the preselection of words, at least one decisive letter which makes the word distinguishable from other words of the preselection of word, said logic circuit coupled to said word recognition unit;

an output unit for outputting the decisive letter for each of the words of the preselection of words, said output unit coupled to said word recognition unit; and

a spelling recognition unit for converting a spelling voice input into an associated electrical spelling voice signal, and for analyzing the associated electrical spelling voice signal for recognizing of the decisive letter, said spelling recognition unit connected to said word recognition unit.