Automated language translation system

• US 5,615,301 A
• Filed: 09/28/1994
• Issued: 03/25/1997
• Est. Priority Date: 09/28/1994
• Status: Expired due to Fees

• Current Assignee: W. L. Rivers
• Original Assignee: W. L. Rivers
• Inventors: Rivers, W. L.
• Primary Examiner(s): Tung, Kee M.
• Application Number:
  US08/313,785
• Time in Patent Office: 909 Days
• Field of Search: 395/2.86, 395/2.79, 395/2.69, 395/2.6, 395/2.63, 395/2.44, 381/43, 381/44, 381/52, 364/419.02, 364/419.01, 364/419.03, 364/419.08, 364/419.16
• US Class Current: 704/277
• CPC Class Codes: G06F 40/55 Rule-based translation
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A language translation system receives audio output from a television, a radio, or some other electronic device designed to present a program to a user, so as to identify any speech signal contained within the audio output. The speech signals are broken down into recognizable phonemes which make up the most basic elements of speech in spoken languages. The sequentially generated phonemes identified from the speech signals are then regrouped so as to form recognizable words in one of a predetermined number of recognizable languages. Sentences are then formed using the grammatical rules of the recognized language so that each sentence may be translated into a universal language, such as Esperanto. The translation system then translates the sentences from Esperanto to the native language of the user as identified by the user.

Claims

1. A language translation system connectable to an audio output of an electronic device for presenting an audible program to a user, said language translation system translating the program audibly in the user selected language, said language translation system comprising:

an audio input connectable to the audio output of the electronic device selected from a television set, a radio, a video cassette recorder, a compact audio disc player, and a movie projector;

speech recognition circuitry connected to said audio input for converting any speech within the audio output of the electronic device into recognizable phonemes;

universal translation circuitry connected to said speech recognition circuitry for grouping the recognized phonemes into recognizable words and sentences in a recognizable natural language so as to translate said recognizable sentences from said natural language into a universal language;

target language translation circuitry connected to said universal translation circuitry for receiving said sentences translated into said universal language so as to translate each of said sentences previously translated into said universal language into a particular one of a plurality of target languages, said target language translation circuitry further having an output;

a target language selection switch connected to said target language translation circuitry for allowing the user to select said particular one of said plurality of target languages; and

a voice synthesizer connected to said output of said target language translation circuitry so as to broadcast audible speech which is the translation of said program in said one target language.

2. The language translation system according to claim 1, wherein the electronic device is a television set.

3. The language translation system according to claim 1, wherein the electronic device is a radio.

4. The language translation system according to claim 1, wherein the electronic device is a video cassette recorder.

5. The language translation system according to claim 1, wherein the electronic device is a compact audio disc player.

6. The language translation system according to claim 1, wherein the electronic device is a movie projector.

7. A method of translating an audio signal of a broadcast speech from a natural language of the speech into an audible speech of a user'"'"'s target language, wherein said natural language belongs to a set of recognizable natural languages, said method comprising the steps of:

identifying speech elements by generating a consecutive number of recognizable phonemes of the speech contained within the audio signal from an electronic device selected from a television set, a radio, a video cassette recorder, a compact audio disc player, and a movie projector;

forming consecutive words by grouping the consecutive number of recognizable phonemes into recognizable consecutive words;

identifying the natural language of the speech by identifying the natural language of the consecutive words formed in said step of forming consecutive words, the natural language of the consecutive words being the natural language of the speech;

forming consecutive sentences by grouping the recognizable consecutive words formed in said step of identifying the natural language, and forming said consecutive words into sentences in accordance with grammatical rules of the natural language of the speech identified;

translating into a universal language each consecutive sentence formed in said step of forming consecutive sentences;

identifying a user selected language;

translating into the selected language each consecutive sentence translated into the universal language; and

broadcasting said each selected language sentence with a voice synthesizer to the user in the tarqet language.

8. The method according to claim 7, wherein the electronic device is a television set.

9. The method according to claim 7, wherein the electronic device is a radio.

10. The method according to claim 7, wherein the electronic device is a video cassette recorder.

11. The method according to claim 7, wherein the electronic device is a compact audio disc player.

12. The language translation system according to claim 7, wherein the electronic device is a movie projector.