Method and Apparatus for Obtaining Statistical Data from a Conversation

Abstract

A system is described to monitor various parameters of a conversation, for example distinguishing voices in a conversation and reporting who in the group is violating the proper etiquette rules of conversation. These results would indicate any disruptive individuals in a conversation. So they are identified, monitored, trained to prevent further disturbances, and their etiquette is improved to prevent further disturbances. Some of the functions the system can perform include: report the identity of the voices, report how long one has spoken, report how often one interrupts, report how often one raises their voice, count the occurrences of obscenities and determine length of silences. The system, in addition, can provide meaning of words, send email, identify fast talkers, train to reduce the volume of a voice, provide a period of time to a voice, beep after someone uses a profanity, request a voice to speak up, provide grammatical corrections, provide text copies of conversation, and eliminate background noises.

1 . An apparatus comprising:
 a voice recognition block to distinguish voices in a conversation;   a memory to store the voices of the conversation;   a statistical data unit that determines parameters of the voices in the conversation; and   an interface coupled to a transducer that presents the determined parameters.   
     
     
         2 . The apparatus of  claim 1 , whereby
 a training period is used to recognize each voice.   
     
     
         3 . The apparatus of  claim 1 , whereby
 the parameters are selected from the group consisting of reporting the identity of the voices in a conversation, reporting how long the voices in a conversation have spoken, reporting how often the voices in a conversation interrupt, reporting how often the voices in a conversation exceed the minimum level, reporting how often the voices in a conversation uses obscenities and reporting how often the voices in a conversation are silent.   
     
     
         4 . The apparatus of  claim 1 , whereby
 each of the voices in the conversation stored in the memory has a tag according to the determined parameters.   
     
     
         5 . The apparatus of  claim 4 , further comprising:
 a time stamp associated with each tag.   
     
     
         6 . The apparatus of  claim 1 , whereby
 the transducer is selected from the group consisting of speaker, display and earphone; and   the determined parameters of the voices in the conversation are presented to a user of the apparatus.   
     
     
         7 . The apparatus of  claim 1 , further comprising:
 an audio signal analyzer used to cancel background noise.   
     
     
         8 . An apparatus comprising:
 a voice recognition system to distinguish each voice in a conversation;   a speech to text converter to convert at least one voice of the conversation into text; and   a request circuit to interpret the text for a command, whereby   the command is performed.   
     
     
         9 . The apparatus of  claim 8 , whereby
 a training period is used to identify each voice.   
     
     
         10 . The apparatus of  claim 8 , whereby
 the commands are selected from the group consisting of providing meaning of words, sending email, identifying fast talkers, training to reduce the volume of a voice, providing a period of time to a voice, beeping after someone uses a profanity, requesting a voice to speak up, providing grammatical corrections, providing text copies of conversation, and eliminating background noises.   
     
     
         11 . The apparatus of  claim 8 , whereby
 each of the voices in the conversation stored in a memory and has a tag according to the determined command.   
     
     
         12 . The apparatus of  claim 11 , further comprising:
 a time stamp associated with each command.   
     
     
         13 . The apparatus of  claim 8 , further comprising:
 a transducer to present to a user of the apparatus the determined command; and   the transducer is selected from the group consisting of speaker, display and earphone.   
     
     
         14 . The apparatus of  claim 8 , further comprising:
 an audio signal analyzer used to cancel background noise.   
     
     
         15 . A method of storing parameters of a conversation comprising the steps of:
 determining if there is silence in the conversation;   distinguishing each voice of the conversation by using a Voice Recognition system;   identifying if someone interrupts the conversation; and   storing parameters relating to the conversation.   
     
     
         16 . The method of  claim 15 , whereby
 the storing step is performed in a memory.   
     
     
         17 . The method of  claim 15 , further comprising the steps of:
 training the voice vecognition system to identify each voice of the conversation.   
     
     
         18 . The method of  claim 15 , further comprising the steps of:
 determining a length of time each voice is used in the conversation.   
     
     
         19 . The method of  claim 15 , further comprising the steps of:
 determining if any voice of the conversation raises their voice.   
     
     
         20 . The method of  claim 15 , further comprising the steps of:
 requesting an unknown voice to identify themselves.   
     
     
         21 . The method of  claim 15 , further comprising the steps of:
 requesting an unknown interrupter to identify themselves.   
     
     
         22 . The method of  claim 15 , whereby
 the parameters are selected from the group consisting of reporting the identity of the voices in a conversation, reporting how long the voices in a conversation have spoken, reporting how often the voices in a conversation interrupt, reporting how often the voices in a conversation exceed the minimum level, reporting how often the voices in a conversation uses obscenities and reporting how often the voices in a conversation are silent.