Method and Apparatus for Obtaining Information from the Web

• US 20170249385A1
• Filed: 03/24/2017
• Published: 08/31/2017
• Est. Priority Date: 01/26/2011
• Status: Abandoned Application

• Current Assignee: TrackThings LLC
• Original Assignee: TrackThings LLC
• Inventors: Gabara, Thaddeus John
• Application Number:
  US15/468,233
• Publication Number:
  US 20170249385A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/953 Querying, e.g. by the use of web search engines
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 21/034 Automatic adjustment
• CPC Class Codes: G10L 25/87 Detection of discrete points within a voice signal
• CPC Class Codes: G10L 25/93 Discriminating between voiced and unvoiced parts of speech signals G10L25/90 takes precedence

Abstract

An intelligent conversation system augmenting a conversation between two or more individuals uses a speech to text block configured to convert voices of the conversation into text, a determination circuit configured to determine topics from the text of the conversation, search parameters determined by the determination circuit from the topics are sent to an Internet, search results corresponding to the search parameters are received from the Internet; and a memory configured to store the search results received from the Internet. The speech to test block is configured to convert the search results to speech. An earphone is configured to transmit the speech to one of the two or more individuals. The speech is used by one of the individuals to augment the conversation.

Claims

1. An intelligent portable conversation system augmenting a conversation with information related to the conversation, the information obtained from the Internet comprising:

a microphone configured to pick up the conversation, audio contents of the conversation is applied to a speech to text block, the speech to text block configured to convert the audio contents of the conversation into text;

a finite state machine configured to determine the one or more topics from the text of the conversation, the one or more topics used to form search parameters;

the search parameters are coupled to the Internet and sent to at least one search engine;

text responses of the search results corresponding to the search parameters are coupled to the finite state machine; and

the finite state machine determines a period of silence in the conversation, the finite state machine sends the text responses of the at least one search engine to a text to speech block, the text to speech block converts the text responses into an audio signal, wherein

during at least one silent period in the conversation, a person participating in the conversation, after hearing the audio signal, considers filling in the silent period of the conversation with at least a portion of the audio signal, the audio signal containing information obtained from the Internet.

2. The apparatus of claim 1, wherein

at least one silent period within a discussion, the discussion addressing, at least one or more topics, the one or more topics are used to form search parameters.

3. The apparatus of claim 2, wherein

the silence period is about one second.

4. The apparatus of claim 1, wherein

at least one memory configured to store the text of the conversation and the search parameters.

5. The apparatus of claim 1, wherein

an RF module wirelessly transmits the search parameters to the Internet, the Internet routes the search parameters to at least one search engine.

6. The apparatus of claim 1, further comprising:

at least one memory configured to store the responses of the search results received from the Internet.

7. The apparatus of claim 1, further comprising:

an earphone, the earphone is inserted into the auditory canal of the person, the person hearing the audio signal.

8. An intelligent portable conversation system augmenting a conversation with information related to the conversation, the information obtained from a search engine on the Internet comprising:

a speech to text block configured to convert the audio contents of the conversation into text;

a finite state machine configured to determine the one or more topics from the text of the conversation, the finite state machine uses the one or more topics to form search parameters;

the search parameters are coupled to the Internet and sent to a search engine;

text responses of the search engine responding to the search parameters are coupled to a text to speech block, the text to speech block converts the text responses into an audio signal, wherein a person participating in the conversation, after hearing the audio signal, considers filling any silent period of the conversation with at least a portion of the audio signal, the audio signal containing information obtained from the Internet.

9. The apparatus of claim 8, wherein

at least one or more topics of the conversation are used to form search parameters.

10. The apparatus of claim 8, wherein

the silence period is about one second.

11. The apparatus of claim 8, wherein

at least one memory configured to store the text of the conversation and the search parameters.

12. The apparatus of claim 8, wherein

an RF module wirelessly transmits the search parameters to the Internet, the Internet routes the search parameters to the search engine.

13. The apparatus of claim 8, further comprising:

at least one memory configured to store the responses of the search results received from the Internet.

14. The apparatus of claim 8, further comprising:

an earphone, the earphone is inserted into the auditory canal of the person, the person hearing the audio signal.

15. The apparatus of claim 8, further comprising:

an RF module wirelessly receives the text responses of the search engine from the Internet, the RF module routes the responses to the finite state machine.

16. The apparatus of claim 8, wherein

during at least one silent period in the conversation, the person hearing the audio signal of the search result response, considers filling in the silent period of the conversation with information obtained from the Internet.

17. An intelligent portable conversation system augmenting a conversation with information related to the conversation, the information obtained from a search engine on the Internet comprising:

at least one silent period within a discussion addressing at least one or more topics, the one or more topics are used to form search parameters;

a microphone configured to pick up the conversation, audio contents of the conversation is applied to a speech to text block, the speech to text block configured to convert the audio contents of the conversation into text;

at least one memory configured to store the text of the conversation;

a finite state machine configured to determine the one or more topics from the text of the conversation stored in the memory, the one or more topics used to form the search parameters, the search parameters are stored in the at least one memory;

an RF module wirelessly transmits the search parameters stored in memory to the Internet, the Internet routes the search parameters to at least one search engine;

search parameters determined by the finite state machine from the topics are sent to the at least one search engine;

responses of the search results corresponding to the search parameters are routed through the Internet to the RF module;

the at least one memory configured to store the responses of the search results received from the Internet by the RF module;

the finite state machine determines a period of silence in the conversation, the finite state machine reads text of the responses of the search results from the at least one memory; and

a text to speech block converts the text of the responses of the search result into an audio signal of the search result response.

18. The apparatus of claim 17, further comprising:

a text to speech block converts the text of the responses of the search result into an audio signal of the search result response.

19. The apparatus of claim 18, further comprising:

an earphone inserted into the auditory canal of a person, the person participating in the conversation, wherein during at least one silent period in the conversation.

20. The apparatus of claim 19, wherein

the person, after hearing the audio signal of the search result response, considers filling in the silent period of the conversation with information obtained from the Internet.