Integrated speech recognition, closed captioning, and translation system and method

• US 7,747,434 B2
• Filed: 10/30/2006
• Issued: 06/29/2010
• Est. Priority Date: 10/24/2000
• Status: Active Grant

• Current Assignee: Global Translations, Inc.
• Original Assignee: Speech Conversion Technologies, Inc.
• Inventors: Garr, Michael, Flanagan, Mary
• Primary Examiner(s): Chawan; Vijay B
• Application Number:
  US11/554,411
• Publication Number:
  US 20080052069A1
• Time in Patent Office: 1,338 Days
• Field of Search: 348/468, 348/461, 348/552, 348/564, 348/588, 348/563, 704/235, 704/211, 715/723, 709/219, 725/37, 725/139
• US Class Current: 704/235
• 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: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04N 7/0885 for the transmission of subtitles

Abstract

A system and method that integrates automated voice recognition technology and speech-to-text technology with automated translation and closed captioning technology to provide translations of “live” or “real-time” television content is disclosed. It converts speech to text, translates the converted text to other languages, and provides captions through a single device that may be installed at the broadcast facility. The device accepts broadcast quality audio, recognizes the speaker'"'"'s voice, converts the audio to text, translates the text, processes the text for multiple caption outputs, and then sends multiple text streams out to caption encoders and/or other devices in the proper format. Because it automates the process, it dramatically reduces the cost and time traditionally required to package television programs for broadcast into foreign or multi-language U.S. markets.

Claims

1. A method for processing a speech portion of audio signals from multiple speakers in a broadcast program signal comprising the steps of:

(a) receiving said audio signal from said broadcast program signal comprising at least a speech portion, wherein said speech portion of said audio signal is not previously processed by a human operator for syntax or context;

(b) processing said speech portion of said audio signal for a speaker without any input from a human operator;

(c) converting said speech portion of said audio signal for said speaker to text without any input from a human operator;

(d) transmitting said text to a first closed caption channel;

(e) translating said text in real time to produce translated text for said speaker;

(f) transmitting said translated text to a second closed caption channel; and

(g) converting said translated text to an audio signal comprising speech generated for said speaker according to said translated text.

2. The method of claim 1 wherein translating said text to produce translated text comprises pre-processing said text to:

(a) extract closed captioning control codes;

(b) corrects spelling errors; and

(c) map usage errors and colloquialisms to correct forms.

3. The method of claim 1 wherein translating said text to produce translated text comprises post-processing said translated text to perform monolingual automatic editing of said translated text based on previous examples.

4. The method of claim 1 wherein receiving said audio signal from said broadcast program signal comprises receiving said audio signal from a live broadcast program signal.

5. The method of claim 1 wherein receiving said audio signal from said broadcast program signal comprises receiving said audio signal from a recorded broadcast program signal.