User Tools

Site Tools


public:speech_renderer

Link to this comparison view

public:speech_renderer [2007/04/24 17:24] (current)
gudny created
Line 1: Line 1:
 +==== Description =====
  
 +This module gets a text with markup (now only emph), synthesises it and creates a wave file for each chunk it receives.  This module also aanalyses the synthesised speech and sends out timings for phonemes.
 +
 +==== Functions ====
 +
 +==== Psyspec ====
 +
 +      <module name="SpeechPlanner">      
 +            <description>Generates audio and phoneme data with timing from words.</description>
 +            <trigger from="WBSystem" type="RU.S1.Internal.Module.Status.Ping"/>
 +            <trigger from="WBAction" type=" RU.S1.Output.Plan.Task.Speech.Do"/>
 +            <trigger from="WBPlan" type="RU.S1.Output.Plan.Task"/>
 +            <post to="WBPlan" type="RU.S1.Output.Plan.Task.Speech.Ready"/>
 +            <post to="WBPlan" type="RU.S1.Output.Plan.Task.Answear.Ready"/>
 +            <post to="WBAction" type="RU.S1.Output.Plan.Act.Speech.Timing"/>
 +            <triggers from="WBPlanAns">
 +               <trigger type="RU.S1.Output.Action.Speech.ReplyTo"/>
 +            </triggers>
 +      </module>
 +
 +==== Messages ====
 +Triggers:\\
 +RU.S1.Output.Plan.Task;\\
 +Description:   Processes text and creates phoneme analysis and wave file for playback at a later time
 +     <ThoughtUnit id="9">
 +          <SentenceFragment falsetto="false" fragment_id="9" answer="false">
 +               <Text type="plain">Hello folks, how are you</Text>
 +          </SentenceFragment>
 +     </ThoughtUnit>
 +
 +RU.S1.Output.Plan.Task.Cancel
 +Desription:     Cancel all output
 +Xml:              (empty)
 +
 +
 +RU.S1.Output.Action.Speech.ReplyTo\\
 +RU.S1.Output.Action.Speech.ReplyTo.Do\\
 +
 +Posters:\\
 +RU.S1.Output.Plan.Task.Speech.Ready\\
 +Description: notifies that processing is done
 +     <ProcessingDone fragment_id="9"/>
 +
 +RU.S1.Output.Plan.Task.Speech.Done;\\
 +RU.S1.Output.Action.Speech.ReplyTo.Done;\\
 +RU.S1.Output.Plan.Task.Answear.Ready;\\
 +
 +RU.S1.Output.Plan.Act.Speech.Timing\\
 +Desription:     Phoneme timings sent to other modules when preprocessing for lip syncronization\\
 +Xml:\\              
 +    <phonemecollection id="9">
 +         <phoneme starttime="" endtime="0.21000">#</phoneme>
 +         <phoneme starttime="" endtime="0.26268">w</phoneme>
 +         <phoneme starttime="" endtime="0.36208">ai</phoneme>
 +         <phoneme starttime="" endtime="0.41757">l</phoneme>
 +         <phoneme starttime="" endtime="0.45014">dh</phoneme>
 +         <phoneme starttime="" endtime="0.55284">ei</phoneme>
 +         <phoneme starttime="" endtime="0.63179">d</phoneme>
 +         <phoneme starttime="" endtime="0.66442">r</phoneme>
 +         <phoneme starttime="" endtime="0.79367">e</phoneme>
 +         <phoneme starttime="" endtime="0.88565">s</phoneme>
 +         <phoneme starttime="" endtime="0.92611">t</phoneme>
 +         <phoneme starttime="" endtime="1.00522">uh</phoneme>
 +         <phoneme starttime="" endtime="1.08368">p</phoneme>
 +         <phoneme starttime="" endtime="1.13934">i</phoneme>
 +         <phoneme starttime="" endtime="1.19813">n</phoneme>
 +         <phoneme starttime="" endtime="1.28759">f</phoneme>
 +         <phoneme starttime="" endtime="1.41052">ai</phoneme>
 +         <phoneme starttime="" endtime="1.47001">n</phoneme>
 +         <phoneme starttime="" endtime="1.58399">k</phoneme>
 +         <phoneme starttime="" endtime="1.63730">l</phoneme>
 +         <phoneme starttime="" endtime="1.82570">ou</phoneme>
 +         <phoneme starttime="" endtime="1.85876">dh</phoneme>
 +         <phoneme starttime="" endtime="1.94083">z</phoneme>
 +         <phoneme starttime="" endtime="2.15083">#</phoneme>
 +    </phonemecollection>
 +
 +
 +
 +==== Implementation Remarks ====
 +
 +The executables are located in the "roboradio/is/ru/cadia/roboradio/src/modules/executors/speech/SpeechPlanner" folder
 +
 +The same module is used for Speech_renderer and Speech_player but with different parameters
 +
 +To run the speech_renderer in Linux:
 +./speechplanner psyclone=localhost
 +
 +To run the Speech_player:
 +./speechplanner psyclone=localhost module=Speaker
/var/www/ailab/WWW/wiki/data/pages/public/speech_renderer.txt ยท Last modified: 2007/04/24 17:24 by gudny