Is it possible to adapt an acoustic model using "sphinx4" only? I have already checked the website but the commands mentioned are for pocketShphinx "Adapting the default acoustic model".
I have also checked some other solutions but all those used pocketsphinx.
It is not possible, you need sphinxtrain and pocketsphinx for adaptation.
Related
Has anyone ever programmed using CNTK for reading hand-filled documents? I tried OCRs and they dont do handwriting recognition at all (next to nothing). Thinking of using CNTK for the same. I searched and found that not many have tried such a thing. Any advice on libraries or any pointers anyone?
Here a basic OCR example using CNTK:
https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_103B_MNIST_FeedForwardNetwork.ipynb
However, in order to use the model in a real application you will need a way to segment the handwritting.
I have a working model built with HTK for online handwriting recognition. Now I want to build another recognition system for Android. After some research I found out that PocketSphinx has a version running on Android OS. Now, what I think of is to convert my HTK model to Sphinx ( or to rebuild it in Sphinx) and then use it with PocketSphinx-on-Android.
First, is there any point that I miss in my plan?
Second, will the converted system (or rebuild with Sphinx) be directly useable in PocketSphinx? In other words, will there be any further conversion/adaptation for a Sphinx model to PocketSphinx?
Thanks in advance
Now, what I think of is to convert my HTK model to Sphinx ( or to rebuild it in Sphinx) and then use it with PocketSphinx-on-Android.
Pocketsphinx has more strict format of HMM which is more speech-oriented. For example, all HMMs must have equal number of states. So it might not be easy to convert. It is easier to retrain.
Second, will the converted system (or rebuild with Sphinx) be directly useable in PocketSphinx? In other words, will there be any further conversion/adaptation for a Sphinx model to PocketSphinx?
Model conversion is not required.
However, there is an issue that pocketsphinx on android allows only voice input, it has no means to input custom features. So you will have to implement that part yourself.
I want to use CMU sphinx4 to transcribe a given audio file. It should take an audio file in .wav format and having conversation in Indian English. I am new to CMUSphinx and can't get easy step wise description of the process.
You might want to look into the transcriber demo provided with the sphinx api.
You can just change the language model and the acoustic model, configure the same in the config.xml file, and use the same code.
The language model- depending on the use-case of your application, you can use the WSJ language model having 5k words, or you can make your own model.To make your own landuage model, you can read more here. One easy way is to use the lmtool. google "lmtool cmu"
The acoustic model- As you want to have an application for Indian accent, you need to have audio files for Indian english, and the corresponding transcription file. Based on your use-case, you can either train your own acoustic model, or you can adapt an existing acoustic model. read more here. you can also search data sets online.
Configure things in the config.xml file so your application uses your language and acoustic model.
For a beginner, these steps might be helpful-
Read about sphinx architecture and try demos
Study about what the language model is.
Read about how to construct the language model. (lmtool, cmuclmtk, etc)
Read about what the acoustic model is.
Read about how to train/adapt the acoustic model.
Configure the config.xml file in your java application to use these models.
I am doing a project on hand sign recognition on a static image. Can I use just Haar training to accomplish this?
As what I've understood, it is somewhat similar to the concept of neural networks.
Using Haar training maybe help to detect the hand, but not for recognize.
The people use many approaches, so I cannot give a unique. You could make some research using Google Scholar and use the keywords "hand sign", "recognition" and "detection".
Some tips: you need to segment the hand and use some template matching or other method to recognize the format. There is also a project for hand gestures here.
I'm trying to find some free XNA friendly FBX Models to use in my test application. I found some 3DS models and converted them to FBX and tried using them, but I just see some 'lines' on the screen .. I know I may have to scale/translate them, but I tried doing this and nothing worked ... Some models won't show anything at all, not even the line artifacts ..
Any ideas where I can get fairly simply FBX models from which can be used in XNA 3.1 ?
Also, there are some models I saw which contain mutiple FBX files .. I dont want these as they require more complexity .. Right now I'm just looking for models contained within one FBX file ..
http://turbosquid.com is a great place to get some free models, but the paid ones are always better.
http://www.mixamo.com/ also has some free character models. No animations though, unless you pay. However, if you're looking for animations, Carnegie mellon university has a whole slew of motion-capture files for free. You'd have to re-rig the character yourself using 3ds max or whatever 3D program you like to use, so that they use "biped" instead of bones, that's the only way to use BVH.
Motion capture BVH files can be found here: https://sites.google.com/a/cgspeed.com/cgspeed/motion-capture/cmu-bvh-conversion