Message transcription, voice query and query delivery system

A method of transcribing a voice transmission comprising:

• receiving a voice transmission from a user at a computer server;
• splitting up said voice transmission into a plurality of voice fragments;
• transcribing each of said voice fragments into a corresponding text fragment using a speech recognition engine;
• sending said voice fragments and said text fragments to a plurality of computer workstations each operated by an agent, each of said workstations receiving one of said voice fragments and a corresponding one of said text fragments;
• at each of said workstations, producing a corrected text fragment;
• from said computer workstations, sending said corrected text fragments back to said computer server;
• assembling said corrected text fragments into a whole text file, said whole text file representing said voice transmission in textual form;
• and
• storing said whole text file in a memory of said computer server.

A method of broadcasting a wanted advertisement of a user, said method comprising:

• accepting, at a search portal computer, a set of keywords from each of a plurality of individuals, each of said set of keywords indicating a type of wanted advertisement desired to be received by each of said individuals;
• receiving, at said search portal computer, a voice file from said user describing said wanted advertisement, said voice file including wanted keywords;
• transcribing said voice file to produce a text file;
• generating a list of said wanted keywords from said text file;
• determining that said wanted keywords match with at least one of said sets of keywords, said at least one of said set of keywords associated with a contact address;
• and
• delivering said voice file describing said wanted advertisement to said contact address identifying one of said individuals, whereby said one of said individuals may contact said user regarding said wanted advertisement.

A method of broadcasting a wanted advertisement of a user, said method comprising:

• receiving, at said search portal computer, a voice file from said user describing said wanted advertisement, said voice file including wanted keywords;
• transcribing said voice file to produce a text file;
• generating said wanted keywords from said text file;
• determining that said wanted keywords match with at least one set of keywords stored in a memory of said search portal computer, said at least one of said set of keywords associated with a contact address;
• delivering said voice file describing said wanted advertisement to said contact address identifying one of said individuals;
• receiving from said one of said individuals a response to said wanted advertisement;
• and
• delivering said response to a telephone of said user, whereby said user may contact said one of said individuals regarding said wanted advertisement.

A method of responding to a wanted advertisement of a user, said method comprising:

• receiving, at said search portal computer, a voice file from said user describing said wanted advertisement, said voice file including wanted keywords;
• transcribing said voice file to produce a text file;
• generating said wanted keywords from said text file;
• searching a database of said search portal computer using said wanted keywords to locate an existing wanted advertisement equivalent to said wanted advertisement, said existing wanted advertisement being associated with an existing answer from an individual;
• determining that said wanted advertisement is equivalent to said existing wanted advertisement, said existing answer being associated with a contact address of said individual;
• and
• delivering said existing answer to a telephone of said user, whereby said user may contact said individual regarding said wanted advertisement.

A method of delivering a voice message comprising:

• receiving an indication of a contact name from a user over a telephone connection, said indication of contact name being received at a computer server;
• searching an address book of an account of said user stored at said computer server for a contact name using said indication of contact name;
• determining a recipient address associated with a found said contact name;
• receiving a voice message from a user at a computer server along with said indication of contact name;
• recording said voice message as a voice file at said computer server;
• executing a speech recognition engine to transcribe said voice file into a text file;
• and
• delivering said text file to a recipient using said recipient address.

A method of delivering a voice message, said method comprising:

• receiving a spoken e-mail address of a recipient from a user over a telephone connection, said spoken e-mail address being received at a computer server;
• recording said spoken e-mail address into an e-mail address voice file;
• transcribing said e-mail address voice file into a textual e-mail address;
• receiving said voice message from said user at said computer server along with said spoken e-mail address;
• recording said voice message as a voice file at said computer server;
• executing a speech recognition engine to transcribe said voice file into a text file;
• delivering said text file to said recipient using said textual e-mail address.

A method of transcribing a voice message comprising:

• receiving a voice message from a user at a computer server along with a recipient address;
• recording said voice message as a voice file at said computer server;
• executing a first speech recognition engine to transcribe said voice file into a first text file;
• executing a second speech recognition engine to transcribe said voice file into a second text file;
• comparing, by said computer server, said first text file and said second text file to determine accuracy of transcribed words in said first and second text files;
• producing, by said computer server, a hybrid text file based upon said first text file and said second text file, said hybrid text file being more accurate than said first text file or said second text file;
• and
• delivering said hybrid text file to a recipient using said recipient address.

A method of transcribing a voice message comprising:

• receiving said voice message from a user at a computer server;
• recording said voice message as a voice file at said computer server;
• executing a speech recognition engine to transcribe said voice file into a text file;
• sending said voice file and said text file to a computer workstation operated by an agent;
• receiving a corrected text file from said computer workstation at said computer server, said corrected text file being a more accurate transcription of said voice file than said text file;
• feeding said text file and said corrected text file into said speech recognition engine, said corrected text file being flagged as the correct version of said text file;
• building a user speech profile based upon said feeding by said speech recognition engine;
• and
• storing said user speech profile for said user in association with said speech recognition engine.