voice-recognition

Voice Biometrics for Android [closed]

由 一曲冷凌霜 提交于 2019-12-07 10:42:37
问题 Closed. This question is off-topic. It is not currently accepting answers. Want to improve this question? Update the question so it's on-topic for Stack Overflow. Closed 4 years ago . i am planning to build a voice authentication system for android devices. Simply meaning instead of the login screen where you have to type your password or draw the pattern, you only only need to say one word such as "Login" and the phone authenticates you and automatically unlocks the phone. I was initially

How to convert log probability into simple probability between 0 and 1 values using python

由 泪湿孤枕 提交于 2019-12-07 06:11:00
问题 I am using Gaussian mixture model for speaker identification. I use this code to predict the speaker for each voice clip. for path in file_paths: path = path.strip() print (path) sr,audio = read(source + path) vector = extract_features(audio,sr) #print(vector) log_likelihood = np.zeros(len(models)) #print(len(log_likelihood)) for i in range(len(models)): gmm1 = models[i] #checking with each model one by one #print(gmm1) scores = np.array(gmm1.score(vector)) #print(scores) #print(len(scores))

Java voice recognition for very small dictionary

由 寵の児 提交于 2019-12-07 02:06:12
问题 I have MP3 audio files that contain voicemails that are left by a computer. The message content is always in same format and left by the same computer voice with only a slight variation in content: "You sold 4 cars today" (where the 4 can be anything from 0 to 9). I have be trying to set up Sphinx, but the out-of-the-box models did not work too good. I then tried to write my own acoustic model and haven't had much better success yet (30% unrecognized is my best). I am wondering if voice

How to detect homophone

由 我们两清 提交于 2019-12-06 16:15:56
I am fairly new to speech processing, but wondering how homophones are detected. I am in search for an API which gives similarity between two words on the basis of how they are pronounced. for example: "to" and "two" are highly similar in terms of how they sound with respect to say "to" and "from". You might want to try calculating the edit distance not on the original strings, but on pronunciations, like they are available in the CMU Pronouncing Dictionary at http://www.speech.cs.cmu.edu/cgi-bin/cmudict The following are used for indexing words by their English pronunciation Soundex or

training UBM with sidekit from custom data

由 老子叫甜甜 提交于 2019-12-06 14:02:32
问题 I am trying to train GMM-UBM model from data that i have already extracted for emotion recognition with SIDEKIT(pretty much the same as speaker recognition. I also don't understand the HDF5 feature file system). My data is an ndarray with shape (1101,78) [78 are the number of acoustic features and 1101 the number of feature vectors(frames). ubm = sidekit.Mixture() llks = ubm.EM_uniform(anger, distribNb, iteration_min=3, iteration_max=10, llk_gain=0.01, do_init=True) The error that is thrown

How can I do voice recognition for Turkish on cmusphinx?

由 只愿长相守 提交于 2019-12-06 11:58:42
问题 I imported this project: https://github.com/cmusphinx/pocketsphinx-android-demo And it works fine on Android studio. But as you can see it on tutorial it has English voice recognition. How can I turn it to Turkish ? I searched a lot but I cant find it. thanks in advance. 回答1: You have to train the model yourself following the tutorial http://cmusphinx.sourceforge.net/wiki/tutorialam You have to collect transcribed speech data for that. Alternatively you can contact people who already did that

Recognize Speech To Text Swift

由 為{幸葍}努か 提交于 2019-12-06 10:49:34
Is it possible to recognize speech and then convert it into text with custom keyboard. Like by default message app in iphone. Screen Shot 1. Default recognize speech in iphone keyboard. 2. Speech to text Any help would be greatly appreciated. Thanks in advance. I have following code which are used in my sample application to convert speech-to-text. import UIKit import Speech import AVKit class ViewController: UIViewController { //------------------------------------------------------------------------------ // MARK:- // MARK:- Outlets //---------------------------------------------------------

Voice recognition [closed]

由 我只是一个虾纸丫 提交于 2019-12-06 08:38:34
问题 Closed . This question needs to be more focused. It is not currently accepting answers. Want to improve this question? Update the question so it focuses on one problem only by editing this post. Closed 6 years ago . I try to search about voice recognition in android. Almost of search result, I have only founded the voice recognition api which provided by Google. Moreover, I want to know which other api that provide for android. Because I would to use my voice recognition to search in my file.

Android - Voice recognition

由 房东的猫 提交于 2019-12-06 08:36:04
I am looking for a voice recognition library for Android. I only need it to understand "Yes/No" answers ( in different languages - like English, German, French ). Any suggestions? Not sure about V-R libraries because the Play Store max App size is 50megs and those voice packages are about 15 to 20 megs each so it will impossible to include multiple languages directly into the App. There may be an online service to use but you need to search the net for that. What most people use is the inbuilt Android voice recognition Intent. For different languages should be ok for the ones you want as they

How can we convert .wav file to text by using pocketsphinx?

由 此生再无相见时 提交于 2019-12-06 07:49:45
问题 I installed pocketsphinx in my Linux machine correctly, and now I want to convert an audio file (.wave) to text by using pocketsphinx,how can i do that? is there any clear command and short command to do that? somthing like this command: ./src/programs/pocketsphinx_continuous -samprate 8000 -nfft 2048 -adcdev hw:1,0 -lm 2530.lm -dict 2530.dic myvoice.wav and also how can I do that with using python? Thanks in advance. 回答1: I find my answer, pocketsphinx with version 0.8 has an option that can
订阅 voice-recognition