Tina I also need to implement voice recognition in my application and I did a little research on it but have since moved to another part of my app to work on. Although it's a critical part of my app and it’s been looming in the back of my head like I black cloud because I don’t know how hard it will be. That said I will share what I did find. You might have found the same thing.
What I really need to do is localize the incoming callers voice and outgoing callers voice and key off when they actually talk (animations). I know I will have to use VOICE_DOWNLINK and VOICE_UPLINK in some manner but how to actually key when someone talks is still eluding me. RecognizerIntent seems the most promising. http://www.4feets.com/android1.5_ref/docs/reference/android/speech/RecognizerIntent.html although when I tested with it and spoke real time into my phone it didn’t seem to respond to my voice but I didn’t play with it to much. If that doesn't pan out then the only other way I found is to read the voice data in real time by doing something like: int audioSource = MediaRecorder.AudioSource.VOICE_DOWNLINK; int sampleRateInHz = 8000; int channelConfig = AudioFormat.CHANNEL_CONFIGURATION_MONO; int audioFormat = AudioFormat.ENCODING_PCM_16BIT; bufferSize = AudioRecord.getMinBufferSize(sampleRateInHz, channelConfig, audioFormat); AudioRecord recordInstance = new AudioRecord(audioSource, sampleRateInHz, channelConfig, audioFormat, bufferSize); recordInstance.startRecording(); And then read the buffer in real time to analyze and play with the data. Something like: byte buf[] = new byte[bufferSize]; int bytesRead = 0; bytesRead = recordInstance.read(buf, 0, bufferSize) This might be the route you have to go because it sounds like you want to actually change the voice data in real time. There might be a better way to go though. I REALLY don't want to go this route because I have to figure out sound amplitude and all that from the byte stream which I don't have much experience in. Other Apps like this one has to be using voice recognition, so I know it can be done. http://www.droidapps.org/mouthoff-fun-animated-mouths/ I would love to share what each of us finds. Two heads are better than one and all that. If anyone else reads this and has any ideas, please feel free. Your ideas/comments are always welcome. -Chris If that is not the way to do then On Mon, Jan 11, 2010 at 12:02 PM, Joe McCann <[email protected]> wrote: > Speech-to-text is processed in the cloud and the resulting data is > returned. > > On Jan 11, 5:36 am, tina lincon <[email protected]> wrote: > > How is it possible to implement voice recognition on android phones? > > Also to decode the voice and convert the male voice to female voice > > and vice versa?The voice data input from the user will be sent to the > > Google site > > for recognition through Internet, or will be processed and recognized > > locally on my android phone? > > if anyone has any idea regarding it,plzz help.. > > Thanks in advance, > > -- > You received this message because you are subscribed to the Google > Groups "Android Developers" group. > To post to this group, send email to [email protected] > To unsubscribe from this group, send email to > [email protected]<android-developers%[email protected]> > For more options, visit this group at > http://groups.google.com/group/android-developers?hl=en >
-- You received this message because you are subscribed to the Google Groups "Android Developers" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/android-developers?hl=en
