Voice generator, method for generating voice, and navigation apparatus

• US 7,555,433 B2
• Filed: 07/07/2003
• Issued: 06/30/2009
• Est. Priority Date: 07/22/2002
• Status: Active Grant

• Current Assignee: Alpine Electronics Incorporated (Alps Alpine Co., Ltd.)
• Original Assignee: Alpine Electronics Incorporated (Alps Alpine Co., Ltd.)
• Inventors: Otani, Michiaki
• Primary Examiner(s): Han; Qi
• Application Number:
  US10/615,585
• Publication Number:
  US 20040098248A1
• Time in Patent Office: 2,185 Days
• Field of Search: 704/277, 704/258, 704/266, 704/2, 704/5
• US Class Current: 704/277
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

A main controller feeds a spelling translator with a text item representing a place name stored in a map database. The spelling translator translates the spelling of the text item according to rules described in a translation rule table. The spelling translator translates, e.g., a French character or string included in the text item and not included in the English alphabet into an English alphabet character or string having a pronunciation equivalent or similar to the pronunciation of the French character or string. The translated text item is fed into a TTS engine for English. The TTS engine converts the text item into voice, which is output from a speaker.

Claims

1. An automated voice generator for generating a voice output in the pronunciation of a second language corresponding to a text item in a different first language, comprising:

means for automatically translating a spelling of a place name of an original text item in the first language into a new text item in the second language by;

(i) identifying each character in the original text item that is not included in the alphabet of the second language, and

(ii) replacing only said each identified character in the original text item with a character or string in the alphabet of the second language having a pronunciation equivalent or similar to the pronunciation of the identified character in the first language; and

a text-to-speech engine that supports the second language and not the first language, for generating voice by pronouncing the new text item according to the pronunciation of the second language.

2. The voice generator according to claim 1, wherein the original text item comprises place name text items assigned to respective places.

3. The voice generator according to claim 1, wherein the first language character and the second language character or string are included in a place name text item representing a place name.

4. The voice generator according to claim 1, wherein the first language character is in French and the second language character or string is in English.

5. The voice generator according to claim 1, wherein the first language character is in Spanish and the second language character or string is in English.

6. The voice generator according to claim 1, wherein the first language character is in German and the second language character or string is in English.

7. An automated voice generator for generating a voice output in the pronunciation of a second language corresponding to a text item in a different first language, comprising:

means for automatically translating a spelling of a place name of an abbreviated original text item in the first language into a new text item in the second language by;

(i) replacing the abbreviated original text item with a full text item in the first language,

(ii) identifying each character in the full text item that is not included in the alphabet of the second language, and

(iii) replacing only said each identified character in the full text item with a character or string in the alphabet of the second language having a pronunciation equivalent or similar to the pronunciation of the identified character in the first language; and

a text-to-speech engine that supports the second language and not the first language, for generating voice by pronouncing the new text item according to the pronunciation of the second language.

8. The voice generator according to claim 7, wherein the first language character is in French and the second language character or string is in English.

9. The voice generator according to claim 7, wherein the first language character is in Spanish and the second language character or string is in English.

10. The voice generator according to claim 7, wherein the first language character is in German and the second language character or string is in English.

11. An automated method for generating a voice output in the pronunciation of a second language corresponding to a text item in a different first language, comprising:

automatically translating a spelling of a place name of an original text item in the first language into a new text item in the second language by;

(i) identifying each character in the original text item that is not included in the alphabet of the second language, and

(ii) replacing only said each identified character in the original text item with a character or string in the alphabet of the second language having a pronunciation equivalent or similar to the pronunciation of the identified character in the first language; and

generating voice by pronouncing the new text item according to the pronunciation of the second language, where the voice is generated by a text-to-speech engine that supports the second language and not the first language.

12. The method for generating voice according to claim 11, wherein the first language character and the second language character or string are included in a place name text item representing a place name.

13. The method for generating voice according to claim 12, wherein the first language character is in French and the second language character or string is in English.

14. The method for generating voice according to claim 12, wherein the first language character is in Spanish and the second language character or string is in English.

15. The method for generating voice according to claim 12, wherein the first language character is in German and the second language character or string is in English.

16. A navigation apparatus for guiding users, comprising:

a map database for storing geographic information containing a place name text item representing each place name;

means for reading out the place name text item from the map database;

means for automatically translating the spelling of the place name text item in a first language into a new text item in the second language by;

(i) identifying each character in the place name text item that is not included in the alphabet of the second language, and

(ii) replacing only said each identified character in the place name text item with a character or string in the alphabet of the second language having a pronunciation equivalent or similar to the pronunciation of the identified character in the first language; and

a text-to-speech engine that supports the second language and not the first language, for generating voice by pronouncing the new text item according to the pronunciation of the second language.

17. The navigation apparatus according to claim 16, wherein the means for translating refers to replacement rules identified in a rule table that associates a character in the first language that is not included in the alphabet of the second language with a character or string in the alphabet of the second language having an equivalent or similar pronunciation.

18. The navigation apparatus according to claim 16, wherein the means for translating operates between any of a plurality of first languages and the second language, and the text-to-speech engine supports the second language and not any of the plurality of first languages.