speech in, speech out - PowerPoint PPT Presentation

About This Presentation
Title:

speech in, speech out

Description:

'good morning', 'good afternoon', 'good evening', 'morning' ... nuance-compile %PKGHOME% English.America.1.3.0. recognition grammar. master recognition package ... – PowerPoint PPT presentation

Number of Views:28
Avg rating:3.0/5.0
Slides: 17
Provided by: Computerl
Category:
Tags: out | speech

less

Transcript and Presenter's Notes

Title: speech in, speech out


1
speech in, speech out
2
speech-in components
  • Nuance server
  • compiled recognition grammar, master language
    package, licence manager
  • Nuance client

3
recognition grammar
  • anticipate users responses
  • what pieces of information are needed to
    complete the dialog?
  • in what order will they be requested?
  • one piece of information at a time in
    particular order (directed dialog), several
    pieces at once, in any order, and prompt for
    missing items (mixed initiative)?

4
recognition grammar
  • syntax
  • Nuance Grammar Specification Language (GSL)
  • Diamant Speech Recognition Grammar Format
    (SRGF)

5
recognition grammar
  • GSL grammar doc in a file with .grammar
    extension e.g. mygram.grammar (mygram will
    be the resulting package name)
  • contents GrammarRuleName   GrammarDescription
  • GrammarRuleName at least one uppercase
    character
  • GrammarDescription sequence of words, grammar
    names, and operators that define a set of
    recognizable word sequences
  • words (terminals) in lower-case
  • operators

() concat (A B C ... Y) A and B and ...
disjunction A B C ... Y either A or B or...
? optional ?Y Y is optional
positive closure Y at least one Y
Kleene star Y zero or more Y
6
recognition grammar
  • GSL grammar example expressions
  • morning afternoon evening
  • morning, afternoon, evening
  • (good morning afternoon evening)
  • good morning, good afternoon, good
    evening
  • (?good morning afternoon evening)
  • good morning, good afternoon, good
    evening, morning, afternoon, evening
  • (thanks very much)
  • thanks very much, thanks very very much,
    ...
  • (thanks very much)
  • thanks much, thanks very much, thanks
    very very much, ...

7
recognition grammar
.GO_FLOOR FLOORf (?the FLOORf floor)
(?the FLOORf please) (?Filler ?the FLOORf
floor ?please) ltfloor fgt Filler (i
would like to go to) (i want to go to)
(uh) FLOOR first return("1")
second return("2") third return("3")
fourth return("4")
  • example GSL grammar
  • .grammar file
  • .slot_definitions file

floor
8
recognition grammar
  • another option SRGF and export as Nuance GSL
  • GrammarTest.bat

9
recognition grammar
  • compiling the package (compile-package.bat)
  • set PKGHOME path to your gsl file (w/o
    extension)
  • nuance-compile PKGHOME English.America.1.3.0

10
recognition grammar
  • testing the grammar (text)
  • parse-tool -package path_to_your_model
  • nl-tool package path_to_your_model grammar
    grammar_in_your_model

11
speech recognition
  • running Nuance
  • licence manager lm.bat
  • recognition server rs.bat
  • set PKGHOME path to your compiled model
  • recserver -package PKGHOME
    lm.Addresseslocalhost config. ...
  • testing the grammar (speech)
  • xapp -package path to your compiled model
    lm.Addresseslocalhost

12
Diamant with speech-in
  • running nuance client
  • edit Diamant config file Clients.ini
  • NuanceClient.bat
  • (btw, have the licence manager and the server
    running too... duh!...)

13
Diamant with speech-in
  • adding speech-in
  • add device as usual
  • activate recognition output ltstringgt start
    (start command) to nuance client
  • read (speech) input from nuance
  • client into variable as usual
  • access recognition confidence
  • (of type Real) like this varconfidence

14
speech-out components
  • Mary server
  • online at DFKI...
  • Mary client
  • MaryClient.bat

15
Diamant with speech-out
  • adding speech-out
  • add device as usual
  • optionally, set format format ltstringgt
    (default plain text) and voice
  • voice ltstringgt
  • in output node, output ltstringgt to Mary client
    as usual

16
speech-enabled dialogs
  • recognition tends to be imperfect...
  • if recognition confidence low, then, for example
    (btw, think grounding)
  • repeat question
  • ask for confirmation (did you say blah?)
  • inform user what they can say (you can say
    blah, bloo, and blee, please try again)
  • but... dont let user get stuck in endless
    clarification dialog either!
Write a Comment
User Comments (0)
About PowerShow.com