Text interface device and method in voice communication

• US 9,237,224 B2
• Filed: 05/03/2011
• Issued: 01/12/2016
• Est. Priority Date: 05/03/2011
• Status: Active Grant

• Current Assignee: Padmanabhan Mahalingam
• Original Assignee: Padmanabhan Mahalingam
• Inventors: Mahalingam, Padmanabhan
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US13/099,701
• Publication Number:
  US 20120284024A1
• Time in Patent Office: 1,715 Days
• Field of Search: 704/258, 704/260, 704270-275
• US Class Current: 1/1
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 2021/0575 Aids for the handicapped in speaking
• CPC Class Codes: H04M 1/642 storing speech in digital form
• CPC Class Codes: H04M 1/72478 for hearing-impaired users

Abstract

A computerized communication device has a display screen, a mechanism for a user to select words or phrases displayed on the display screen, and software executing from a non-transitory physical medium, the software providing a function for providing audio signal output in a connected voice-telephone call from the text words or phrases selected by a user.

Claims

1. A computerized communication device comprising:

a touch display screen, a data repository, voice telephony circuitry and voice telephony functions, and an earphone output coupled to an earphone;

a data repository; and

software executing from a non-transitory physical medium, the software providing an interactive interface on the display screen including a command selection, initiated via interaction by a user with the display screen, activating a quiet-mode application;

wherein the device operating in quiet mode, upon a user connecting to an incoming voice call from a caller;

(i) receives audio signals in the voice call from the caller, converts only those audio signals to text and presents the text in a first region of the display;

(ii) mines the converted text in the first region of the display for keywords or phrases, and the software selects specific second words or phrases from the database, related to the converted text, and displays the second words or phrases in a second region of the display screen, individual ones of the second words or phrases selectable by the user;

and wherein one second word or phrase, displayed in the second region of the display, is selected by the user to make a response in the voice call, while viewing the converted text displayed in the first region, and the quiet-mode application checks whether there is in the data repository a recorded sound file associated with the selected second word or phrase, and if so, plays the associated recorded sound file in the connected telephone call, and if there are no pre-recorded sound files associated with the selected second word or phrase, the software converts the text of the selected second word or phrase into synthetic speech, which is played to the connected telephone call.

2. The computerized communication device of claim 1 wherein the selectable second words or phrases displayed in the second region of the display comprise a hierarchical system wherein the user sorts among a further variety of words or phrases displayed from the data repository, and selects one of the further words or phrases to be rendered as a sound file from the database or synthetic speech in the connected voice call.

3. A method comprising:

(a) connecting to a voice call implemented on a computerized communication device, the device including a data repository and voice telephony circuitry and voice telephony functions,

(b) converting only voice input from the caller, by software stored and executed from a non-transitory physical medium on the communication device, to first text and the first text is displayed in a first region in a touchscreen display;

(c) mining the converted text in the first region of the display for keywords or phrases, and selecting specific second words or phrases from a database, related to the converted text, and displaying in a second region of the touch screen display a variety of second text incorporating individually selectable words or phrases to make a response in the voice telephone call;

(d) selecting one of the words or phrases in the second text by a user;

(e) checking, by the software, whether there is in the data repository a recorded sound file associated with the selected word or phrase, and if so, playing the associated recorded sound file to the connected voice telephone call; and

(f) if there are no pre-recorded associated sound files associated with the selected word or text, converting, by the software, the text of the selected word or phrase into synthetic speech, and playing the resulting synthetic speech in the voice telephone call.

4. The method of claim 3 wherein the second text incorporating individually selectable variety of words or phrases displayed in the first region comprise a hierarchical system wherein the user sorts among a further variety of words or phrases displayed from the data repository, and selects one of the further words or phrases to be rendered as a sound file from the database or synthetic speech in the connected voice call.