Providing translations encoded within embedded digital information

• US 7,627,471 B2
• Filed: 06/24/2008
• Issued: 12/01/2009
• Est. Priority Date: 12/15/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Creamer, Thomas E., Moore, Victor S., Jaiswal, Peeyush
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): Neway; Samuel G
• Application Number:
  US12/145,177
• Publication Number:
  US 20080255825A1
• Time in Patent Office: 525 Days
• Field of Search: None
• US Class Current: 704/235
• CPC Class Codes: G10L 19/018 Audio watermarking, i.e. embedding inaudible data in the audio signal
• CPC Class Codes: G10L 19/167 Audio streaming, i.e. formatting and decoding of an encoded audio signal representation into a data stream for transmission or storage purposes

Abstract

A method of providing a translation within a voice stream can include receiving a speech signal in a first language, determining text from the speech signal, translating the text to a second and different language, and encoding the translated text within the speech signal.

Claims

1. A computer-implemented system for providing a translation within a voice stream comprising:

at least one input for receiving a speech signal in a first language;

at least one computer capable of receiving the speech signal from the at least one input, the at least one computer configured to implement;

a speech recognizer for determining text from the speech signal;

a translation component for translating the textual representation to a second language different from the first language;

a time stamp component for adding time stamp information to each of a predetermined number of portions of the received speech signal and to each of a predetermined number of portions of the translated text; and

an encoder for identifying within each portion of the speech signal in the voice stream one or more inaudible portions and for embedding each portion of the translated text in place of the identified inaudible portions, irrespective of whether the added time stamp information for the embedded text and a speech signal portion associated with the identified portion are synchronized.

2. The computer-implemented system of claim 1, further comprising a transmitter for transmitting the resulting speech signal.

3. The computer-implemented system of claim 1, wherein the encoder embeds the translated text within the voice stream as digital information to provide an encoded voice stream.

4. The computer-implemented system of claim 1, further comprising at least one device to receive the encoded voice stream and to decode the translated text.

5. The computer-implemented system of claim 4, wherein the at least one device is capable of presenting a representation of the translated text.

6. The computer-implemented system of claim 5, wherein the at least one device is capable of playing an audible representation of the received speech signal in the first language.

7. The computer-implemented system of claim 6, wherein the at least one device plays the audible representation of the received speech signal substantially concurrently with the presentation of the translated text.

8. A machine-readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

receiving a speech signal for the voice stream in a first language;

determining text from the speech signal;

translating the text to a second and different language;

adding time stamp information to each of a predetermined number of portions of the received speech signal and to each of a predetermined number of portions of the translated text;

identifying within each portion of the speech signal in the voice stream one or more inaudible portions; and

embedding each portion of the translated text in place of the identified inaudible portions, irrespective of whether the added time stamp information for the embedded text and a speech signal portion associated with the identified portion are synchronized.

9. The machine-readable storage of claim 8, further comprising code sections for transmitting the resulting speech signal.

10. The machine-readable storage of claim 8, said embedding step further comprising code sections for including the translated text within the voice stream as digital information.

11. The machine-readable storage of claim 9, further comprising code sections for:

receiving the voice stream including the translated text; and

decoding the translated text.

12. The machine-readable storage of claim 11, further comprising code sections for presenting a representation of the translated text.

13. The machine-readable storage of claim 12, further comprising code sections for playing an audible representation of the received speech signal.

14. The machine-readable storage of claim 13, further comprising code sections for playing the audible representation of the received speech signal substantially concurrently with the presentation of the translated text.