Is there a speech to text framework for iOS that supports Spanish out of the box? Commercial or OS is ok.
Android does have offline speech recognition capabilities. You can activate this by going to Settings - Language and Input - Voice Input and touch the cog icon next to Enhanced Google Services.
Under "Text-to-Speech," select Customize Voice Settings. Customize your Select-to-speak voice: Change the language and preferred voice: Under “Speech," choose the language and type of voice you want to hear. Change natural voice: To use a more realistic, lifelike voice, select Use natural voice when device is online.
Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs).
There are a bunch of commercial IOS librariers for speech recognition. The names I keep hearing are Nuance, iSpeech, and Yapme. Each offers cloud speech recognition (off the device) and a client library and SDK to build into your app.
Nuance seems to support Spanish - http://blog.dragonmobileapps.com/2011/01/mobile-app-developer-dragon-mobile-sdk.html
...you can speech-enable your app for including US and UK English, European Spanish, European French, German, Italian and Japanese---with even more languages on tap for 2011!
and now Nuance gives developers free access - http://www.masshightech.com/stories/2011/09/26/daily13-Nuance-tweaks-mobile-dev-program-with-free-access-to-Dragon.html
iSpeech is likely to support Spanish - http://www.ispeech.org/developers/iphone
iSpeech's Mobile SDKs support 27 TTS and ASR (defined grammar) languages and 15 languages for free-form dictation voice recognition.
Yapme, sorry, I'm not sure - http://yapinc.com/speech-cloud.html
Take a look here: http://src.chromium.org/viewvc/chrome/trunk/src/content/browser/speech/
It's the Chrome Browser Speech to search...... you can do it in Objective-C. Try go google.com on chrome browser and if spanish is recognized, you win! :)
You can easily use:
- (void) SpeechFromGooglezzz {
NSURL *url = [NSURL URLWithString:@"https://www.google.com/speech-api/v1/recognize?xjerr=1&client=chromium&lang=en-US"];
ASIFormDataRequest *request = [ASIFormDataRequest requestWithURL:url];
NSString *filePath = [NSString stringWithFormat:@"%@%@", [[NSBundle mainBundle] resourcePath], @"tmpAudio.flac"];
NSData *myData = [NSData dataWithContentsOfFile:filePath];
[request addPostValue:myData forKey:@"Content"];
[request addPostValue:@"audio/x-flac; rate=16000" forKey:@"Content-Type"];
[request startSynchronous];
NSLog(@"req: %@", [request responseString]);
}
Remember that you must recording a 16000 bitrate FLAC file! Or nothing!
Google responds with a json containing the words.
hope this helps.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With