Television/radio speech-to-text translating processor

• US 6,542,200 B1
• Filed: 08/14/2001
• Issued: 04/01/2003
• Est. Priority Date: 08/14/2001
• Status: Expired due to Term

• Current Assignee: Cheldan Technologies, Inc.
• Original Assignee: Cheldan Technologies, Inc.
• Inventors: Barcy, Daniel J., Statkus, Charles W.
• Primary Examiner(s): LEE, MICHAEL
• Application Number:
  US09/930,704
• Time in Patent Office: 595 Days
• Field of Search: H04/N.700, H04/N 1.100, 348/468, 348/473, 348/467, 348/476, 348/477, 348/478, 348/553, 348/563, 348/564, 348/552, 348/725, 348/724, 348/61, 704/271, 704/277, 704/270, 704/235, 704/251, 704/257, 704/260
• US Class Current: 348/468
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/4221 Dedicated function buttons, e.g. for the control of an EPG, subtitles, aspect ratio, picture-in-picture or teletext
• CPC Class Codes: H04N 21/439 Processing of audio elementary streams
• CPC Class Codes: H04N 21/440236 by media transcoding, e.g. video is transformed into a slideshow of still pictures, audio is converted into text
• CPC Class Codes: H04N 21/4622 Retrieving content or additional data from different sources, e.g. from a broadcast channel and the Internet web site content organization and management for information retrieval from the Internet G06F16/958; transmission by internet of broadcast information H04H60/82; stock exchange data over packet-switching network H04L12/1804; push services including data channel over packet-switching network H04L12/1859
• CPC Class Codes: H04N 21/47 End-user applications
• CPC Class Codes: H04N 21/4856 for language selection, e.g. for the menu or subtitles
• CPC Class Codes: H04N 21/4884 for displaying subtitles
• CPC Class Codes: H04N 21/8106 involving special audio data, e.g. different tracks for different languages
• CPC Class Codes: H04N 5/60 for the sound signals
• CPC Class Codes: H04N 7/0885 for the transmission of subtitles

Abstract

A device used with a conventional television set that permits both hearing impaired and non hearing impaired individuals to view television audio voice signals in a text format on the television screen without the requirement of a closed/open caption broadcast signal or a closed/open caption enabled television. The device also can utilize an FM audio input, an audio line input, and a microphone or impedance input for conversion into a text format. The system may use on-board or remote displays, wireless or wired, for also providing the text format representative of human speech. The system includes audio filters for filtering a television audio signal and filtering out human speech audio signals for processing and conversion by a speech-to-text converter.

Claims

1. A device for use with a conventional television set, that can receive a television signal from an antenna, from a cable input, or from a satellite input, that permit'"'"'s both hearing impaired and non hearing impaired individuals to view television audio voice signals in a text format on the television screen in real time without the requirement of a closed/open caption broadcast signal or a closed/open caption enabled television comprising:

input means for receiving a conventional television signal that may include a closed/open caption video signal;

a television channel tuner connected to said television signal input;

means for decoding the audio and video signals in said television signal connected to the output of said channel under;

said means for decoding audio and video signals having first, second, and third output means;

means for encoding audio/video/closed-caption/text connected to said first output of said decoding means for receiving audio complete signal from said decoding means;

means for decoding closed-captioned video signal input connected to said second output of said decoding means for receiving the video closed-captioned signal for decoding;

audio input selector connected to said third output of said means for decoding audio and video;

automatic gain control connected to the output of said audio input selector;

means for providing audio filters connected to the output of said automatic gain control for filtering out audio signals other than human speech;

speech-to-text converters connected to the output of said audio filter means for converting the audio speech signals received from said audio filters to text signals;

means connected to said speech-to-text converter for electing the input language to said speech-to-text converter;

language translation means connected to the output of said speech-to-text converter and connected to an input from said means for selecting the input language;

output language selector connected to said language translator for selecting the desired language that is outputted from the language translator;

a closed-caption/local text display encode selector connected to the output of said means for decoding said closed-caption and the output of said language translator, said closed-caption/local text display encode selector including a manual selection switch having two modes of operation, one designating automatic encode selection for selecting either closed-caption or local text display, depending on the output of the closed-caption decoding means if available from the broadcast station, and a second mode of operation in which the selector switch selects continuous local text display, bypassing the closed-captioned data;

said audio/video closed-captioned text encoding means connected to the output of said closed-caption/local text display encode selector for receiving either closed-caption video signals or local text display signals, depending on the selector mode;

a TV/RF modulator connected to the output of said audio/video/close-caption/text encoder for combining the conventional television signal and the local text display, if selected, in the television signal and modulating the signal for either channel 3 or channel 4 output; and

output means connected to the output of said TV/RF modulator for receiving the conventional TV signal, including audio and the close-captioned video signal or the local text display video signal in a selected language, having the frequency modulated to channel 3 or channel 4 for connecting to the conventional television set, whereby a hearing impaired or non hearing impaired individual may view both the conventional television signal and television audio voice signals in a text format on the television screen if closed-captioned broadcast signal is not available or if the television set is not enabled for closed/open caption.

2. A device in claim 1, including:

an RF (FM) audio input means; and

FM tuner and audio detector connected to the output of said FM input means, the output of said FM tuner and audio detector means being connected to the audio input selector.

3. A device as in claim 1, including:

line input means for receiving a signal from a speaker output, said line input means having an output connected to the audio input selector means.

4. A device as in claim 1, including:

high impedance input means for receiving an audio signal from a microphone or an inductance; and

pre-amplifier means having an input connected to the output of high inductance input means, said pre-amplifier means for amplifying the audio signal received from said high impedance input and having an output connected to the audio input selector means.

5. A device as in claim 1, including:

a hand-held, portable, remote control means for controlling and selecting the desired input signal, including the television tuner input signal, the line input signal, the RF/FM input signal, and the high impedance input signal, said remote control including a manual switch for selecting the input language remotely connected to said input language selector means, and an output language selector switch connected remotely to said output language selector means.

6. A device as in claim 1, including:

an LCD display that is connected to the output of said language translator that provides a visual on-board text display of the audio voice input signals mounted on the device.

7. A device as in claim 1, including:

an infrared modulator connected to the output of said language translator; and

an infrared output connected to the output of said infrared modulator for providing a wireless output that transmits a signal representing the audio text to a remote display device.