Language acquisition aide

• US 20020029146A1
• Filed: 09/06/2001
• Published: 03/07/2002
• Est. Priority Date: 09/05/2000
• Status: Active Grant

• Current Assignee: UO! IP of Delaware LLC (IPNav)
• Original Assignee: Einat H. Nir
• Inventors: Nir, Einat H.
• Granted Patent: US 6,704,699 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory
• 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
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: G09B 15/023 Electrically operated
• CPC Class Codes: G09B 15/04 with sound emitters
• CPC Class Codes: G09B 19/04 Speaking with audible presentation of the material to be studied G09B5/04
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04
• CPC Class Codes: G09B 21/006 using audible presentation of the information
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems

Abstract

The present invention relates to stand-alone, hand-held, scanning apparatus, which provides a user with exposures to a spoken form and an interpretation of a portion of text, simultaneously, or in sequence. Preferably, the apparatus provides a text-to-speech synthesis of a portion of text, for example, a sentence, followed by an audible, automatic translation to a second language, of the same portion of text. Alternatively, the automatic translation may be displayed in parallel with the text-to-speech synthesis. Interpretation may include translation only of difficult words and phrases, in context, upon request, or rephrasing of difficult words and phrases, in context, upon request. These may be audible or displayed.

Alternatively, or additionally, the stand-alone, hand-held apparatus may be used for teaching correct pronunciation of a portion of text. Preferably, teaching correct pronunciation includes the steps of providing a text-to-speech synthesis of the portion of text, recording the user'"'"'s pronunciation of the portion of text, and playing back the user'"'"'s pronunciation, for the user to hear any differences between his pronunciation and that of the text-to-speech synthesis. The user, who may be preparing to give a lecture in a language that is foreign to him, may thus practice his pronunciation of it.

Additionally, in accordance with the present invention, the stand-alone, hand-held apparatus may be used for synthesizing written notes of a piece of music. Preferably, the music is synthesized in the sound of a desired instrument, for exarnple, a cello. The user, who may be preparing to play the piece of music, may maintain visual contact with the written notes, as they are being synthesized.

Claims

1. Stand-alone, hand-held apparatus, which includes:

a sheath, having a proximal end with respect to a portion of text, in a first language;

a scanner, located within said sheath, near said proximal end, arranged for scanning the portion of text;

a computerized system, located within said sheath, in communication with said scanner, arranged for performing OCR conversion and text-to-speech synthesis of the scanned text and automatic translation to a second language;

an audio-output system, in communication with said computerized system, for producing an audio output of said text-to-speech synthesis; and

an interface system, for enabling a user to communicate with said apparatus.

2. Apparatus according to claim 1, wherein said apparatus may be further arranged for performing OCR conversion and text-to-speech synthesis of a portion of text in the second language, and automatic translation to the first language.

3. Apparatus according to claim 1, wherein said computerized system is further arranged for producing an audio output of said automatic translation, wherein said audio outputs of said text-to-speech synthesis and said automatic translation are produced in sequence.

4. Apparatus according to claim 1, wherein said interface system further includes a display panel.

5. Apparatus according to claim 4, wherein said computerized system is further arranged for performing automatic translation, in parallel with said text-to-speech synthesis.

6. Apparatus according to claim 5 and further including a continuous written display of said automatic translation, in parallel with said audio output of said text-to-speech synthesis.

7. Apparatus according to claim 1, and further including a microphone, wherein said computerized system is further arranged for recording speech, for teaching correct pronunciation, via said audio-output system.

8. Apparatus according to claim 1 and further including a writing tip, which may be selectably deployed and retracted by a user.

9. Stand-alone, hand-held apparatus for teaching correct pronunciation, which includes:

a sheath, having a proximal end with respect to a portion of text;

a scanner, located within said sheath, near said proximal end, arranged for scanning the portion of text;

a computerized system, located within said sheath, in communication with said scanner, arranged for performing OCR conversion and text-to-speech synthesis of the scanned text;

a microphone and an audio storage system, for recording a user'"'"'s pronunciation of the scanned text; and

an audio-output system, in communication with said computerized and audio storage systems, for producing audio outputs of said text-to-speech synthesis and of the user'"'"'s pronunciation of the scanned text.

10. Apparatus according to claim 9, and further including a signal evaluator for evaluating the audio signals produced by the user, comparing them with said text-to-speech synthesis, and correcting them as needed.

11. A method of providing simultaneous exposures to a language in its written and spoken forms, and to their interpretation, which includes the following steps:

scanning a portion of text;

performing OCR conversion to the scanned text;

performing text-to-speech synthesis of the scanned text;

producing an audio output of the text-to-speech synthesis;

performing automatic translation of the scanned text; and

producing an output of the automatic translation.

12. A method according to claim 11 and further including a step of selecting a rate for the audio output of the text-to-speech synthesis.

13. A method according to claim 11 and further including a step of selecting a voice for the audio output of the text-to-speech synthesis, from a library of voices.

14. A method according to claim 11, wherein said step of producing an output of the automatic translation includes producing an audio output of the automatic translation.

15. A method according to claim 14 and further including a step of selecting a rate for the audio output of the automatic translation.

16. A method according to claim 14 and further including a step of selecting a voice for the audio output of the automatic translation, from a library of voices.

17. A method according to claim 14 wherein said steps of:

a. producing an audio output of the text-to-speech synthesis; and

b. producing an audio output of the automatic translation. are performed in an order;

a, b, a.

18. A method according to claim 11, wherein said step of producing an output of the automatic translation includes displaying the automatic translation, continuously, in parallel with the audio output of the text-to-speech synthesis.

19. A method according to claim 11, wherein said step of producing an output of the automatic translation includes providing definitions of selected words and phrases, in context, based on the automatic translation, upon a user'"'"'s request.

20. A method for teaching correct pronunciation, which includes the following steps:

a. scanning a portion of text;

b. performing OCR conversion to the scanned text;

c. performing text-to-speech synthesis of the scanned text;

d. producing an audio output of the text-to-speech synthesis;

e. recording a user'"'"'s pronunciation of the scanned text; and

f. playing back the user'"'"'s pronunciation of the scanned text.

21. A method according to claim 20 and further including the following steps:

evaluating the user'"'"'s pronunciation, vis a vis the text-to-speech synthesis; and

correcting the user'"'"'s pronunciation, by repeating the audio output of the text-to-speech synthesis of a mispronounced portion of text.