I've just finished installing, and it is hearing wrong? I say "scroll up", and it thinks I said "view".
What is wrong and how to fix please?
I've just finished installing, and it is hearing wrong? I say "scroll up", and it thinks I said "view".
What is wrong and how to fix please?
Okeys, i did managed to install it lol. But i have two questions.
1) Why it's installed in my home directory? Oo
2) On start it says this: runtime error: could not find activate registry (and not starting of course)
I have ubuntu 11.10 with unity.
Will give more additional info, if needed, just tell me what that should be. a little bit noobie in linux. lol
Hi Happyyasu09,
1. VEDICS is not installed in the HOME directory. It is installed in /usr/bin and /usr/lib/VEDICS. Only a few configuration files are kept in home directory in .VEDICS folder.
2. Is the accessibility feature turned on? If not please turn it on and let me know if it works or not.
By the way, which version of VEDICS did you install?
Hi!
I just installed it today and have done a bit of bug-searching.
I'm on Ubuntu 11.10 with Gnome-Shell.
Actually if you use the recommended python-pyatspi instead of the installed-by-default python-pyatspi2 you get the annoying
But if you use python-pyatspi2 you'll get the annoyingCode:RuntimeError: Could not find or activate registrywhich will be corrected by addingCode:ImportError: could not import gobject (error was: ImportError('When using gi.repository you must not import static modules like "gobject". Please change all occurrences of "import gobject" to "from gi.repository import GObject".',))toCode:import gi from gi.repository import GObjectOk, we are quite there. At this time I got/usr/local/lib/python2.7/dist-packages/pyVEDICS/vedics.py
which I solved by using this script (from a comment on the project page)Code:UnboundLocalError: local variable 'accessibleList' referenced before assignment
now there are two big problems:Code:import dbus try : _bus = dbus.SessionBus() _proxy = _bus.get_object("org.a11y.Bus", "/org/a11y/bus") _desktopProps = dbus.Interface(_proxy, dbus_interface='org.freedesktop.DBus.Properties') isAtspi2 = True except: import gconf isAtspi2 = False if isAtspi2 : _desktopProps.Set('org.a11y.Status', 'IsEnabled', True) else : cl = gconf.client_get_default() cl.set_bool('/desktop/gnome/interface/accessibility', True)
1) I have to run this script everytime I launch vedics, otherwise I'll get the local variable error.
2) It doesn't work, because it says
but when I try to speak it doesn't say me anything.Code:vedics /usr/lib/python2.7/dist-packages/gobject/constants.py:24: Warning: g_boxed_type_register_static: assertion `g_type_from_name (name) == 0' failed import gobject._gobject start end 10:08.102 CONFIG logMath Log base is 1.0001 10:08.122 CONFIG logMath Using AddTable when adding logs 10:08.122 CONFIG logMath LogAdd table has 99022 entries. 10:08.303 INFO microphone Desired format: PCM_SIGNED 16000.0 Hz, 16 bit, mono, 2 bytes/frame, big-endian supported. event 10:08.327 CONFIG wsjLoader Loading Sphinx3 acoustic model: etc/WSJ_clean_13dCep_16k_40mel_130Hz_6800Hz.4000.mdef 10:08.327 CONFIG wsjLoader modellName: etc/WSJ_clean_13dCep_16k_40mel_130Hz_6800Hz.4000.mdef 10:08.328 CONFIG wsjLoader dataDir : cd_continuous_8gau/ event 10:08.477 INFO unitManager CI Unit: *+AH+ 10:08.481 INFO unitManager CI Unit: *+BREATH+ 10:08.482 INFO unitManager CI Unit: *+CLICK+ 10:08.482 INFO unitManager CI Unit: *+GRUNT+ 10:08.483 INFO unitManager CI Unit: *+NOISE+ 10:08.483 INFO unitManager CI Unit: *+RING+ 10:08.483 INFO unitManager CI Unit: *+SLAM+ 10:08.484 INFO unitManager CI Unit: *+SMACK+ 10:08.484 INFO unitManager CI Unit: *+TONE+ 10:08.485 INFO unitManager CI Unit: AA 10:08.485 INFO unitManager CI Unit: AE 10:08.486 INFO unitManager CI Unit: AH 10:08.486 INFO unitManager CI Unit: AO 10:08.486 INFO unitManager CI Unit: AW 10:08.487 INFO unitManager CI Unit: AY 10:08.487 INFO unitManager CI Unit: B 10:08.488 INFO unitManager CI Unit: CH 10:08.488 INFO unitManager CI Unit: D 10:08.488 INFO unitManager CI Unit: DH 10:08.489 INFO unitManager CI Unit: EH 10:08.489 INFO unitManager CI Unit: ER 10:08.490 INFO unitManager CI Unit: EY 10:08.490 INFO unitManager CI Unit: F 10:08.490 INFO unitManager CI Unit: G 10:08.491 INFO unitManager CI Unit: HH 10:08.491 INFO unitManager CI Unit: IH 10:08.492 INFO unitManager CI Unit: IY 10:08.492 INFO unitManager CI Unit: JH 10:08.493 INFO unitManager CI Unit: K 10:08.493 INFO unitManager CI Unit: L 10:08.493 INFO unitManager CI Unit: M 10:08.494 INFO unitManager CI Unit: N 10:08.494 INFO unitManager CI Unit: NG 10:08.495 INFO unitManager CI Unit: OW 10:08.495 INFO unitManager CI Unit: OY 10:08.496 INFO unitManager CI Unit: P 10:08.496 INFO unitManager CI Unit: R 10:08.496 INFO unitManager CI Unit: S 10:08.497 INFO unitManager CI Unit: SH 10:08.498 INFO unitManager CI Unit: T 10:08.498 INFO unitManager CI Unit: TH 10:08.498 INFO unitManager CI Unit: UH 10:08.499 INFO unitManager CI Unit: UW 10:08.499 INFO unitManager CI Unit: V 10:08.500 INFO unitManager CI Unit: W 10:08.500 INFO unitManager CI Unit: Y 10:08.500 INFO unitManager CI Unit: Z 10:08.501 INFO unitManager CI Unit: ZH 10:08.597 INFO wsjLoader ModelLoader 10:08.598 INFO wsjLoader Pool cd_continuous_8gau/means Entries: 33176 10:08.598 INFO wsjLoader Pool cd_continuous_8gau/variances Entries: 33176 10:08.598 INFO wsjLoader Pool cd_continuous_8gau/transition_matrices Entries: 49 10:08.598 INFO wsjLoader Pool senones Entries: 4147 10:08.598 INFO wsjLoader Pool meanTransformationMatrix Entries: 1 10:08.598 INFO wsjLoader Pool meanTransformationMatrix Entries: 1 10:08.599 INFO wsjLoader Pool varianceTransformationMatrix Entries: 1 10:08.599 INFO wsjLoader Pool varianceTransformationMatrix Entries: 1 10:08.599 INFO wsjLoader Pool cd_continuous_8gau/mixture_weights Entries: 4147 10:08.599 INFO wsjLoader Pool senones Entries: 4147 10:08.599 INFO wsjLoader Context Independent Unit Entries: 49 10:08.599 INFO wsjLoader HMM Manager: 110878 hmms 10:08.600 INFO wsj CompositeSenoneSequences: 0 10:08.600 INFO dictionary Loading dictionary from: file:/tmp/VEDICS/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/cmudict.0.6d 10:08.603 INFO dictionary Loading filler dictionary from: file:/tmp/VEDICS/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/fillerdict WARNING: Grammar missing self identifying header 10:08.699 WARNING dictionary Missing word: terminale 10:08.699 WARNING jsgfGrammar Can't find pronunciation for terminale 10:08.699 WARNING dictionary Missing word: cerca 10:08.699 WARNING jsgfGrammar Can't find pronunciation for cerca 10:08.700 WARNING dictionary Missing word: modifica 10:08.700 WARNING jsgfGrammar Can't find pronunciation for modifica 10:08.700 WARNING dictionary Missing word: visualizza 10:08.700 WARNING jsgfGrammar Can't find pronunciation for visualizza 10:08.700 WARNING dictionary Missing word: aiuto 10:08.700 WARNING jsgfGrammar Can't find pronunciation for aiuto 10:08.703 INFO jsgfGrammar Num nodes : 569 10:08.703 INFO jsgfGrammar Num arcs : 770 10:08.704 INFO jsgfGrammar Avg arcs : 1.3532513 10:08.473 INFO microphone Final format: PCM_SIGNED 16000.0 Hz, 16 bit, mono, 2 bytes/frame, big-endian 10:08.478 INFO microphone open 10:08.489 INFO microphone line listener Open event from line com.sun.media.sound.DirectAudioDevice$DirectTDL@1b7e189 10:08.493 INFO microphone Frame size: 320 bytes 10:08.509 INFO microphone started recording 10:08.511 INFO microphone DataStartSignal added 10:08.515 INFO microphone line listener Start event from line com.sun.media.sound.DirectAudioDevice$DirectTDL@1b7e189 genrating dict done genrating dict WARNING: Grammar missing self identifying header 10:08.768 WARNING dictionary Missing word: terminale 10:08.769 WARNING jsgfGrammar Can't find pronunciation for terminale 10:08.769 WARNING dictionary Missing word: cerca 10:08.770 WARNING jsgfGrammar Can't find pronunciation for cerca 10:08.770 WARNING dictionary Missing word: modifica 10:08.770 WARNING jsgfGrammar Can't find pronunciation for modifica 10:08.771 WARNING dictionary Missing word: visualizza 10:08.771 WARNING jsgfGrammar Can't find pronunciation for visualizza 10:08.771 WARNING dictionary Missing word: aiuto 10:08.771 WARNING jsgfGrammar Can't find pronunciation for aiuto 10:08.773 INFO jsgfGrammar Num nodes : 569 10:08.774 INFO jsgfGrammar Num arcs : 770 10:08.774 INFO jsgfGrammar Avg arcs : 1.3532513 # --------------- Summary statistics --------- Total Time Audio: 0,00s Proc: 0,00s Speed: 0,00 X real time 10:08.776 INFO dictionary Loading dictionary from: file:/tmp/VEDICS/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/cmudict.0.6d 10:08.779 INFO dictionary Loading filler dictionary from: file:/tmp/VEDICS/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/fillerdict 10:08.813 INFO jsgfGrammar Num nodes : 569 10:08.814 INFO jsgfGrammar Num arcs : 770 10:08.814 INFO jsgfGrammar Avg arcs : 1.3532513 1 Sending 1 event event
Any suggestions?
Hi,
Please try adjusting your mic.
As for the other problems, it will be fixed in vedics-0.5
Ok, after a shoutdown the situation now is this:
The mic is working fine with Cheese, Skype and GoogleTalk.Code:$ vedics /usr/lib/python2.7/dist-packages/gobject/constants.py:24: Warning: g_boxed_type_register_static: assertion `g_type_from_name (name) == 0' failed import gobject._gobject start end WARNING: Grammar missing self identifying header WARNING: Grammar missing self identifying header # --------------- Summary statistics --------- Total Time Audio: 0,00s Proc: 0,00s Speed: 0,00 X real time 1 event event
Vedics, simply ignores what I say.
Are there more informations I can provide?
Hi dadexix86,
Its not a matter about whether the mic is working fine or not. There are many things that come into picture when speech is processed by software like background noise, accent etc. What appears as normal speech for us (when we, say, record sound and replay it or hear it on skype) may appear as distorted speech to software. So adjusting the mic so that speech recognition works fine is necessary.
A good way to adjust the mic would be to open the sound settings and check the mic input level. If the mic is detecting sounds even when you are not speaking then it means that there is lot of (white) noise around. Reduce the mic input level such that the mic input level changes only when you speak.
There is also a way to make speech recognition work in noisy environment. I haven't tested it and so I cannot guarantee you success. But if it works do let me know.
Replace the file /usr/lib/VEDICS/vedics.config.xml with the following:
For details visit: http://nsh.nexiwave.com/2010/02/nois...n-sphinx4.htmlCode:<?xml version="1.0" encoding="UTF-8"?> <!-- ******************************************************** --> <!-- an4 configuration file --> <!-- ******************************************************** --> <config> <!-- ******************************************************** --> <!-- frequently tuned properties --> <!-- ******************************************************** --> <property name="logLevel" value="CONFIG"/> <property name="absoluteBeamWidth" value="-1"/> <property name="relativeBeamWidth" value="1E-80"/> <property name="wordInsertionProbability" value="1E-36"/> <property name="languageWeight" value="8"/> <property name="frontend" value="epFrontEnd"/> <property name="recognizer" value="recognizer"/> <property name="showCreations" value="false"/> <!-- ******************************************************** --> <!-- word recognizer configuration --> <!-- ******************************************************** --> <component name="recognizer" type="edu.cmu.sphinx.recognizer.Recognizer"> <property name="decoder" value="decoder"/> <propertylist name="monitors"> <item>accuracyTracker </item> <item>speedTracker </item> <item>memoryTracker </item> </propertylist> </component> <!-- ******************************************************** --> <!-- The Decoder configuration --> <!-- ******************************************************** --> <component name="decoder" type="edu.cmu.sphinx.decoder.Decoder"> <property name="searchManager" value="searchManager"/> </component> <component name="searchManager" type="edu.cmu.sphinx.decoder.search.SimpleBreadthFirstSearchManager"> <property name="logMath" value="logMath"/> <property name="linguist" value="flatLinguist"/> <property name="pruner" value="trivialPruner"/> <property name="scorer" value="threadedScorer"/> <property name="activeListFactory" value="activeList"/> </component> <component name="activeList" type="edu.cmu.sphinx.decoder.search.PartitionActiveListFactory"> <property name="logMath" value="logMath"/> <property name="absoluteBeamWidth" value="${absoluteBeamWidth}"/> <property name="relativeBeamWidth" value="${relativeBeamWidth}"/> </component> <component name="trivialPruner" type="edu.cmu.sphinx.decoder.pruner.SimplePruner"/> <component name="threadedScorer" type="edu.cmu.sphinx.decoder.scorer.ThreadedAcousticScorer"> <property name="frontend" value="${frontend}"/> <property name="isCpuRelative" value="true"/> <property name="numThreads" value="2"/> <property name="minScoreablesPerThread" value="50"/> <property name="scoreablesKeepFeature" value="true"/> </component> <!-- ******************************************************** --> <!-- The linguist configuration --> <!-- ******************************************************** --> <component name="flatLinguist" type="edu.cmu.sphinx.linguist.flat.FlatLinguist"> <property name="logMath" value="logMath"/> <property name="grammar" value="jsgfGrammar"/> <property name="acousticModel" value="wsj"/> <property name="wordInsertionProbability" value="${wordInsertionProbability}"/> <property name="languageWeight" value="${languageWeight}"/> <property name="unitManager" value="unitManager"/> </component> <!-- ******************************************************** --> <!-- The Grammar configuration --> <!-- ******************************************************** --> <component name="jsgfGrammar" type="edu.cmu.sphinx.jsapi.JSGFGrammar"> <property name="dictionary" value="dictionary"/> <property name="grammarLocation" value="resource:/vedics!/vedics/"/> <property name="grammarName" value="vedics"/> <property name="logMath" value="logMath"/> </component> <!-- ******************************************************** --> <!-- The Dictionary configuration --> <!-- ******************************************************** --> <component name="dictionary" type="edu.cmu.sphinx.linguist.dictionary.FastDictionary"> <property name="dictionaryPath" value="resource:/edu.cmu.sphinx.model.acoustic.WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.Model!/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/cmudict.0.6d"/> <property name="fillerPath" value="resource:/edu.cmu.sphinx.model.acoustic.WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.Model!/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/fillerdict"/> <property name="addSilEndingPronunciation" value="false"/> <property name="allowMissingWords" value="true"/> <property name="unitManager" value="unitManager"/> </component> <!-- ******************************************************** --> <!-- The acoustic model configuration --> <!-- ******************************************************** --> <component name="wsj" type="edu.cmu.sphinx.model.acoustic.WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.Model"> <property name="loader" value="wsjLoader"/> <property name="unitManager" value="unitManager"/> </component> <component name="wsjLoader" type="edu.cmu.sphinx.model.acoustic.WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.ModelLoader"> <property name="logMath" value="logMath"/> <property name="unitManager" value="unitManager"/> </component> <!-- ******************************************************** --> <!-- The unit manager configuration --> <!-- ******************************************************** --> <component name="unitManager" type="edu.cmu.sphinx.linguist.acoustic.UnitManager"/> <!-- ******************************************************** --> <!-- The frontend configuration --> <!-- ******************************************************** --> <component name="frontEnd" type="edu.cmu.sphinx.frontend.FrontEnd"> <propertylist name="pipeline"> <item>microphone </item> <item>preemphasizer </item> <item>windower </item> <item>fft </item> <item>melFilterBank </item> <item>dct </item> <item>liveCMN </item> <item>featureExtraction </item> </propertylist> </component> <!-- ******************************************************** --> <!-- The live frontend configuration --> <!-- ******************************************************** --> <component name="epFrontEnd" type="edu.cmu.sphinx.frontend.FrontEnd"> <propertylist name="pipeline"> <item>microphone </item> <item>dataBlocker </item> <item>speechClassifier </item> <item>speechMarker </item> <item>nonSpeechDataFilter </item> <item>preemphasizer </item> <item>windower </item> <item>fft </item> <item>wiener</item> <item>melFilterBank </item> <item>dct </item> <item>liveCMN </item> <item>featureExtraction </item> </propertylist> </component> <!-- ******************************************************** --> <!-- The frontend pipelines --> <!-- ******************************************************** --> <component name="dataBlocker" type="edu.cmu.sphinx.frontend.DataBlocker"> <!--<property name="blockSizeMs" value="10"/>--> </component> <component name="speechClassifier" type="edu.cmu.sphinx.frontend.endpoint.SpeechClassifier"> <property name="threshold" value="13"/> </component> <component name="nonSpeechDataFilter" type="edu.cmu.sphinx.frontend.endpoint.NonSpeechDataFilter"/> <component name="speechMarker" type="edu.cmu.sphinx.frontend.endpoint.SpeechMarker" > <property name="speechTrailer" value="50"/> </component> <component name="preemphasizer" type="edu.cmu.sphinx.frontend.filter.Preemphasizer"/> <component name="windower" type="edu.cmu.sphinx.frontend.window.RaisedCosineWindower"> </component> <component name="fft" type="edu.cmu.sphinx.frontend.transform.DiscreteFourierTransform"> </component> <component name="melFilterBank" type="edu.cmu.sphinx.frontend.frequencywarp.MelFrequencyFilterBank"> </component> <component name="dct" type="edu.cmu.sphinx.frontend.transform.DiscreteCosineTransform"/> <component name="liveCMN" type="edu.cmu.sphinx.frontend.feature.LiveCMN"/> <component name="featureExtraction" type="edu.cmu.sphinx.frontend.feature.DeltasFeatureExtractor"/> <component name="microphone" type="edu.cmu.sphinx.frontend.util.Microphone"> <property name="closeBetweenUtterances" value="false"/> </component> <!-- ******************************************************* --> <!-- monitors --> <!-- ******************************************************* --> <component name="accuracyTracker" type="edu.cmu.sphinx.instrumentation.BestPathAccuracyTracker"> <property name="recognizer" value="${recognizer}"/> <property name="showAlignedResults" value="false"/> <property name="showRawResults" value="false"/> </component> <component name="wiener" type="edu.cmu.sphinx.frontend.endpoint.WienerFilter"> <property name="classifier" value="speechClassifier"/> </component> <component name="memoryTracker" type="edu.cmu.sphinx.instrumentation.MemoryTracker"> <property name="recognizer" value="${recognizer}"/> <property name="showSummary" value="false"/> <property name="showDetails" value="false"/> </component> <component name="speedTracker" type="edu.cmu.sphinx.instrumentation.SpeedTracker"> <property name="recognizer" value="${recognizer}"/> <property name="frontend" value="${frontend}"/> <property name="showSummary" value="true"/> <property name="showDetails" value="false"/> </component> <!-- ******************************************************* --> <!-- Miscellaneous components --> <!-- ******************************************************* --> <component name="logMath" type="edu.cmu.sphinx.util.LogMath"> <property name="logBase" value="1.0001"/> <property name="useAddTable" value="true"/> </component> </config>
Ok, I think that the problem does not depend on Vedics.
In fact, if I let the mic volume on "Not amplified" no sound at all is recorded by any application.
But, when I let it up a bit, until I can hear it, a lot of noise shows up. This noise is automatically reduced by GTalk but is not reduced, as an example, by Skype or Cheese.
I have not thought that the problem should be this. I'll investigate it, because this noise is really annoying and, moreover, it shows up both with the integrated mic and with an external one, so I think that's not hardware-related.
Many, many thanks.
Bookmarks