[wuwen128]

If I generate this:
@{
ThisWillBeSaidOnce = (
“SO HOW LONG HAVE YOU BEEN FEELING LIKE THIS”);
}

And speak “SO LONG YOU FEELING THIS”, OpenEars will never output hypothesis like “SO LONG YOU FEELING THIS”, no matter how good the pronunciation is. I guess because it doesn’t have DTW as preprocess module?

BTW, I am always using
pocketsphinxController.pathToTestFile = wavFilePath
and
[self.pocketsphinxController startListeningWithLanguageModelAtPath:self.pathToGrammarToStartAppWith
dictionaryAtPath:self.pathToDictionaryToStartAppWith
acousticModelAtPath:[OEAcousticModel pathToModel:@”AcousticModelEnglish”]
languageModelIsJSGF:YES];

[wuwen128]

Purpose is to recognise word by word, not just sequentially, in a sentence, just like using .DMP + .arpa files?

The point is using JSGF .gram file as language model will only result in sequential/sub-sequential words from the sentence.

[wuwen128]

Thanks very much, Halle.

[wuwen128]

Crash happens in OpenEars.framework 2.03 + Rejecto.framework 2.04

BTW: Is Rejecto supporting JSGF?

[wuwen128]

Thanks, Halle, but crash sill happens, in different method:

OpenEarsSampleApp[15135:1457561] -[OELanguageModelGenerator compactWhitespaceAndFixCharactersOfArrayEntries:]: unrecognized selector sent to instance 0x7fc4ead80580
OpenEarsSampleApp[15135:1457561] *** Terminating app due to uncaught exception ‘NSInvalidArgumentException’, reason: ‘-[OELanguageModelGenerator compactWhitespaceAndFixCharactersOfArrayEntries:]: unrecognized selector sent to instance 0x7fc4ead80580’
*** First throw call stack:
(
0 CoreFoundation 0x000000010751ec65 __exceptionPreprocess + 165
1 libobjc.A.dylib 0x00000001071b5bb7 objc_exception_throw + 45
2 CoreFoundation 0x00000001075260ad -[NSObject(NSObject) doesNotRecognizeSelector:] + 205
3 CoreFoundation 0x000000010747c13c ___forwarding___ + 988
4 CoreFoundation 0x000000010747bcd8 _CF_forwarding_prep_0 + 120
5 OpenEarsSampleApp 0x0000000104a6f014 OpenEarsSampleApp + 667668

[wuwen128]

NSArray *firstLanguageArray = @[@”BACKWARD”,
@”CHANGE”,
@”FORWARD”,
@”GO”,
@”LEFT”,
@”MODEL”,
@”RIGHT”,
@”TURN”];

OELanguageModelGenerator *languageModelGenerator = [[OELanguageModelGenerator alloc] init];

NSError *error = [languageModelGenerator generateRejectingLanguageModelFromArray:firstLanguageArray withFilesNamed:@”FirstOpenEarsDynamicLanguageModel” withOptionalExclusions:nil usingVowelsOnly:FALSE withWeight:nil forAcousticModelAtPath:[OEAcousticModel pathToModel:@”AcousticModelEnglish”]];

[Author]

Posts