#!/usr/bin/env python
# coding: utf-8

# # Binaural Hearing
# 
# [return to main page](index.ipynb)

# In[ ]:


import numpy as np
import soundfile as sf
import sounddevice as sd
from scipy.signal import fftconvolve
import tools


# ## Interaural Correlation, Degree of Coherence
# 
# This exercise examines the degree of coherence $k$ between right and left ear using noise signals.
# You can find more information in the (non-public) lecture notes on slides 4-29 to 4-31.

# In[ ]:


fs = 44100
dur = 1  # seconds
ks = np.linspace(0, 1, 11)
stddev = 0.2


# In[ ]:


length = int(dur * fs)

np.random.seed(7)

for k in ks:
    R = [[1, k],
         [k, 1]]
    L, V = np.linalg.eig(R)
    L.shape = 1, -1  # turn L into row vector
    W = V * np.sqrt(L)
    # create a new random signal in each iteration:
    stereo_noise = np.random.normal(scale=stddev, size=(length, 2))
    outsig = np.dot(stereo_noise, W.T)  # matrix product
    sf.write('outdata/noise_k{:.1f}.wav'.format(k), outsig, fs)


# This creates several WAV files containing noise.
# The degree of coherence $k$ between both channels is part of the
# respective filename.
# 
# *Exercise:* Listen to the different files and note how you perceive different degrees of
# coherence.
# 
# $k=1.0$<audio src="outdata/noise_k1.0.wav" controls></audio>
# [outdata/noise_k1.0.wav](outdata/noise_k1.0.wav)
# 
# $k=0.9$<audio src="outdata/noise_k0.9.wav" controls></audio>
# [outdata/noise_k0.9.wav](outdata/noise_k0.9.wav)
# 
# $k=0.8$<audio src="outdata/noise_k0.8.wav" controls></audio>
# [outdata/noise_k0.8.wav](outdata/noise_k0.8.wav)
# 
# $k=0.7$<audio src="outdata/noise_k0.7.wav" controls></audio>
# [outdata/noise_k0.7.wav](outdata/noise_k0.7.wav)
# 
# $k=0.6$<audio src="outdata/noise_k0.6.wav" controls></audio>
# [outdata/noise_k0.6.wav](outdata/noise_k0.6.wav)
# 
# $k=0.5$<audio src="outdata/noise_k0.5.wav" controls></audio>
# [outdata/noise_k0.5.wav](outdata/noise_k0.5.wav)
# 
# $k=0.4$<audio src="outdata/noise_k0.4.wav" controls></audio>
# [outdata/noise_k0.4.wav](outdata/noise_k0.4.wav)
# 
# $k=0.3$<audio src="outdata/noise_k0.3.wav" controls></audio>
# [outdata/noise_k0.3.wav](outdata/noise_k0.3.wav)
# 
# $k=0.2$<audio src="outdata/noise_k0.2.wav" controls></audio>
# [outdata/noise_k0.2.wav](outdata/noise_k0.2.wav)
# 
# $k=0.1$<audio src="outdata/noise_k0.1.wav" controls></audio>
# [outdata/noise_k0.1.wav](outdata/noise_k0.1.wav)
# 
# $k=0.0$<audio src="outdata/noise_k0.0.wav" controls></audio>
# [outdata/noise_k0.0.wav](outdata/noise_k0.0.wav)

# ## Binaural Unmasking
# 
# Create audio examples based on slide 4-33.
# 
# To do that, convolve the given HRIRs (stored in the files `data/hrir00.wav`,
# `data/hrir45.wav` and `data/hrir90.wav`) on the one hand with an arbitrary
# speech signal (e.g. from the `data/` directory), on the other hand with a noise signal
# (use the function [numpy.random.normal()](http://docs.scipy.org/doc/numpy/reference/generated/numpy.random.normal.html)).
# 
# Add speech and noise in different combinations of angles of incidence.
# Amplify or attenuate speech and noise in a way that the speech is just barely
# understandable.
# 
# Listen to the different combinations.
# In which combination can you understand the speech better or worse?

# In[ ]:





# ## Interaural Time Difference/Interaural Level Difference
# 
# Two important *cues* for spatial hearing are ITD and ILD.
# 
# *Exercise:* Click and learn:
# 
# * Watch (and listen to!) the videos on this page: http://auditoryneuroscience.com/spatial-hearing/binaural-cues
# 
# * Here is an interactive example: http://auditoryneuroscience.com/spatial-hearing/time-intensity-trading
# 
# *Exercise (only if you happen to have access to Matlab®):* Do the listening test described on this page: http://auditoryneuroscience.com/spatial-hearing/ITD-ILD-practical
# 
# *Exercise:* Try to calculate the ITD as function of the angle of incidence using a
# very much simplified head model. Assume a spherical head with ear holes on
# exactly opposite points on the sphere.
# Make the head radius an adjustable parameter in your calculations; use
# 8.75 cm as default value.
# Assume further, that the sound source is sufficiently far away, so that the
# angle of incidence is constant on the whole sphere.
# 
# What is the maximum distance in the path from the sound source to the two ear
# holes, respectively?
# 
# What time difference does that correspond to, assuming the speed of sound
# $c = 343 \text{ m/s}$?
# 
# Plot the ITD as a function of angle of incidence for a given head radius.

# ## Spatial Hearing of Multiple Sound Sources
# 
# Simulate the ear signals of the listening experiments on slide 4-26 and 4.27.
# 

# *Exercise*: Create a function that takes a mono signal and returns two signals.
# The left signal is same as the input but the right signal is delayed and scaled.

# In[ ]:


def delay_and_attenuate(x, delay, gain, fs=44100):
    """
    Parameters
    ----------
    x : array_like
        Mono signal
    delay : float
        Delay of the second channel (in milliseconds)
    gain : float
        Gain of the second channel (in dB)
    """
    d = int(np.round(delay * fs * 0.001))
    x = np.tile(np.concatenate((x, np.zeros(np.abs(d))), axis=-1), (2, 1)).T
    x[:, 1] = 10**(gain / 20) * np.roll(x[:, 1], d, axis=0)
        
    return tools.normalize(x, maximum=0.6)


# In[ ]:





# *Exercise*: Use two HRIR pairs to create the ear signals

# In[ ]:


def virtual_stereo(x, **kwargs):
    """
    
    """
    # load HRIRs
    hright, _ = sf.read('data/hrir30.wav')
    hleft = np.roll(hright, 1)

    return np.column_stack([fftconvolve(x[:, 0], ir, **kwargs) for ir in hleft.T]) \
            + np.column_stack([fftconvolve(x[:, 1], ir, **kwargs) for ir in hright.T])


# In[ ]:





# Create the ear signals of the 'Virtual Stereo System'.
# Try it with different types of signals in 'data/' ('castanets.wav', 'xmax.wav', 'singing.wav').

# In[ ]:


delay = 0
gain = 0
# mono_signal, _ = sf.read('...')

stereo_signal = delay_and_attenuate(mono_signal, delay, gain)
y = tools.normalize(virtual_stereo(stereo_signal), maximum=0.6)

sd.play(y)
sd.wait()


# ### Summing Localization
# Vary the relative gain between the left and right channels.
# Try to localize the sound source.
# Do you hear only one source?
# Compare your observations with the results on Slide 4-26.

# In[ ]:





# ### Law of the First Wave Front
# 
# Apply a delay to the second (right) signal, in the range of 0 -- 50 ms. Compare your observation with the results shown in Slide 4-27.

# In[ ]:





# ## Applications of Binaural Synthesis
# * Games https://www.youtube.com/watch?v=8e-O2V8QcUE
# * Virtual studio http://www.waves.com/plugins/nx#nx-head-tracker-for-headphones-quick-start
# * Demo with head-tracker https://www.waves.com/nx/player
# * Demo https://www.bbc.co.uk/programmes/p05189jv
# 

# ## Solutions
# 
# If you had problems solving some of the exercises, don't despair!
# Have a look at the [example solutions](binaural-hearing-solutions.ipynb).
# 
# <p xmlns:dct="http://purl.org/dc/terms/">
#   <a rel="license"
#      href="http://creativecommons.org/publicdomain/zero/1.0/">
#     <img src="http://i.creativecommons.org/p/zero/1.0/88x31.png" style="border-style: none;" alt="CC0" />
#   </a>
#   <br />
#   To the extent possible under law,
#   <span rel="dct:publisher" resource="[_:publisher]">the person who associated CC0</span>
#   with this work has waived all copyright and related or neighboring
#   rights to this work.
# </p>