Add readme.md

README.MD

@@ -0,0 +1,26 @@
+# INTRA-LINGUAL AND CROSS-LINGUAL VOICE CONVERSION USING HARMONIC PLUS STOCHASTIC MODELS
+This is a *C++ 11* implementation of the above algorithm proposed by **Dr. Daniel Erro Eslava** based on his PhD thesis, available at [PhD thesis] (http://www.lsi.upc.edu/~nlp/papers/phd_daniel_erro.pdf). This algorithm can be used to convert a speaker's voice to another speaker's after training with audio materials from both speakers. For fun, you could convert your voice to President Trump's by downloading his audios from YouTube, for example.
+# Features
++ Written with modern C++ (C++11/14)
++ Depend on the [Eigen](http://eigen.tuxfamily.org/index.php?title=Main_Page) linear algebra library for high numeric performance
++ Utilize OpenMP on Windows or GCD on Mac/iOS to take full advantage of parallel computation on multiple cores of a modern CPU for high speed
++ Expose **C interfaces** to adapt this implementation to multiple platforms, such as Windows, Mac OS and iOS
+# Usage
+## Training
+The C API for the training phase are presented in *train_C.h*， which requires the user to specify the source audios, target audios such that it can generate a model file from the source speaker to the target speaker. All the parameters are documented in detail in the corresponding header file.
+To use an API, just 
+```c++
+#include "train_C.h"
+```
+## Conversion
+After training, this algorithm produces a model file (whose path is specified by the user in the training phase). Then we can convert any voice audios from the source speaker to make it hear like the target speaker's voice with this model file. All the C APIs for conversion are contained in *convert_C.h,* which are well documented.
+```c++
+#include "convert_C.h"
+```
+## Note
+For both training and conversion APIs, a user needs to provide multiple arguments such as the list of source audios, target audios and the path of the model file. To make this process more friendly, the API also supports a single configuration file including of all the required parameters. 
+## Example
+In the *audios* subdirectory, we have provided the audio samples from *Dr. Daniel Erro Eslava*, which includes a training set taking 20 audio samples from two speakers and a test set containing 10 audio samples from the source speaker.
+## Additional notes for application on Mac/iOS
+Since the Mac/iOS platforms prefer GCD to OpenMP for multiple-core parallel programming, the equivalent implementation using GCD is provided in *train_C.mm*.  Just use *train_C.mm*  to replace *train_C.cpp* (which depends on OpenMP) if you plan to deploy it on Mac/iOS.
+