speech

I am making a language app that records any new vocabulary a user is trying to learn. It would be great if users can add their words via a speech to text program, instead of having to enter it manually. I am having trouble achieving this task. I am aware that there is an API for apple but not android. Is there anyway possible of doing this, using an API? Like for instance, google speech to text API? But I guess I would first have to be able to access the device's microphone. I am a beginner and this would be very easy using the web. Is React Native still too young for this task? You might

I'm trying to use the Google Speech API v2 (at address https://www.google.com/speech-api/v2/recognize?... ) I need to use my Api Key, but when I use it I get error 403 Forbidden When I use an API key that was on the example project I downloaded it is working fine. I saw that at the Google Developers Console I can enable a lot of api options, but didn't find any Speech-API option. Is there anything else I need to enable to get access to this API using my key? Thank you! Instructions are here : http://www.chromium.org/developers/how-tos/api-keys !! Do not forget to activate the API "Speech API"

I'm searching for a tool that converts text to phonemes, (like text to speech software) I can program one but it will not be without errors and takes a lot of time! so my question is: is there a simple tool for converting e.g. "hello" to "HH AH0 L OW1" maybe some command-line tool so i can capture the stdout? i'm searching for the phonemes in 'Arpabet' style (see the 'hello' example). espeak does something like that but the output is not in Arpabet style and the phonemes are not split by some determiner. If you had searched for Arpabet on wiki you would have found your answer. The CMU guys

I'm trying to use google speech recognition API. Here's the code i've written: http://pastebin.com/zJEhnJ74 It works. I get an answer from the server: {"status":5,"id":"8803471b14a2310dfcf917754e8bd4a7-1","hypotheses":[]} Now the problem is "status:5". Infact, here's status code: status: 0 – correct
, status: 4 – missing audio file, 
status: 5 – incorrect audio file. My problem is "incorrect audio file". I don't understand if it is a .flac file error (you can download my test .flac file here: http://www21.zippyshare.com/v/61888405/file.html ) or how i read the file (in a byte array then

Is there prior open-source work done in the field of 'Audio analysis' to detect human-voice (say in spite of some background noise), determine speaker's gender, possibly determine no. of speakers, age of speaker(s), and the emotion of speakers? My hunch is that the speech recognition software like CMU Sphinx could be a good place to start, but if there's something better, it'd be great. I'm a graduate student doing speech recognition research. These are open research problems, and, unfortunately, I'm not aware of open-source packages that can do these things out of the box. If you have some

I'm using this example from newboston and it prompt me for recording but after it recognized what I said, it won't update the list view. Here is the code. public class MainActivity extends Activity { private static final int RECOGNIZER_RESULT = 1234; ListView list; @Override public void onCreate(Bundle savedInstanceState) { super.onCreate(savedInstanceState); setContentView(R.layout.activity_main); list = (ListView) findViewById(R.id.list); Button btn_speach = (Button)findViewById(R.id.btn_speak); btn_speach.setOnClickListener(new OnClickListener() { public void onClick(View v) { Intent intent

I need a specialized solution optimized to detect numbers between 1 and 1000 to be used on a smartphone. Best solution would be to have this SDK working offline. Any idea ? I do not find any configuration with Google Speech or Amazon Transcribe to allow "number only" It is not quite right to strictly expect numbers from people, they usually say many things like "i don't know" or "wait a bit" even if you ask them for numbers. You will harm the experience significantly. You have to analyze the recognition result intelligently and even if non-number is recognized you have to act accordingly. To