Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
Torchaudio
Commits
209145a4
Unverified
Commit
209145a4
authored
Nov 05, 2021
by
moto
Committed by
GitHub
Nov 05, 2021
Browse files
Fix sections of MVDR tutorial (#1989)
parent
b9247022
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
24 additions
and
24 deletions
+24
-24
examples/tutorials/mvdr_tutorial.py
examples/tutorials/mvdr_tutorial.py
+24
-24
No files found.
examples/tutorials/mvdr_tutorial.py
View file @
209145a4
...
...
@@ -8,7 +8,7 @@ MVDR with torchaudio
######################################################################
# Overview
#
========
#
--------
#
# This is a tutorial on how to apply MVDR beamforming by using `torchaudio <https://github.com/pytorch/audio>`__.
#
...
...
@@ -25,7 +25,7 @@ MVDR with torchaudio
######################################################################
# Preparation
#
===========
#
-----------
#
# First, we import the necessary packages and retrieve the data.
#
...
...
@@ -71,12 +71,12 @@ for filename in filenames:
######################################################################
# Generate the Ideal Ratio Mask (IRM)
#
===================================
#
-----------------------------------
#
######################################################################
# Loading audio data
#
------------------
#
~~~~~~~~~~~~~~~~~~
#
mix
,
sr
=
torchaudio
.
load
(
'_assets/mix.wav'
)
...
...
@@ -100,7 +100,7 @@ reverb_clean = reverb_clean.to(torch.double)
######################################################################
# Compute STFT
#
------------
#
~~~~~~~~~~~~
#
stft
=
torchaudio
.
transforms
.
Spectrogram
(
...
...
@@ -117,7 +117,7 @@ spec_noise = stft(noise)
######################################################################
# Generate the Ideal Ratio Mask (IRM)
#
-----------------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
# .. note::
# We found using the mask directly peforms better than using the
...
...
@@ -143,12 +143,12 @@ irm_speech, irm_noise = get_irms(spec_reverb_clean, spec_noise, spec_mix)
######################################################################
# Apply MVDR
#
==========
#
----------
#
######################################################################
# Apply MVDR beamforming by using multi-channel masks
#
---------------------------------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
results_multi
=
{}
...
...
@@ -160,7 +160,7 @@ for solution in ['ref_channel', 'stv_evd', 'stv_power']:
######################################################################
# Apply MVDR beamforming by using single-channel masks
#
----------------------------------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
# We use the 1st channel as an example.
# The channel selection may depend on the design of the microphone array
...
...
@@ -174,7 +174,7 @@ for solution in ['ref_channel', 'stv_evd', 'stv_power']:
######################################################################
# Compute Si-SDR scores
#
---------------------
#
~~~~~~~~~~~~~~~~~~~~~
#
def
si_sdr
(
estimate
,
reference
,
epsilon
=
1e-8
):
...
...
@@ -198,12 +198,12 @@ def si_sdr(estimate, reference, epsilon=1e-8):
######################################################################
# Results
#
=======
#
-------
#
######################################################################
# Single-channel mask results
#
---------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
for
solution
in
results_single
:
...
...
@@ -211,7 +211,7 @@ for solution in results_single:
######################################################################
# Multi-channel mask results
#
--------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~
#
for
solution
in
results_multi
:
...
...
@@ -219,73 +219,73 @@ for solution in results_multi:
######################################################################
# Original audio
#
==============
#
--------------
#
######################################################################
# Mixture speech
#
--------------
#
~~~~~~~~~~~~~~
#
ipd
.
Audio
(
mix
[
0
],
rate
=
16000
)
######################################################################
# Noise
#
-----
#
~~~~~
#
ipd
.
Audio
(
noise
[
0
],
rate
=
16000
)
######################################################################
# Clean speech
#
------------
#
~~~~~~~~~~~~
#
ipd
.
Audio
(
clean
[
0
],
rate
=
16000
)
######################################################################
# Enhanced audio
#
==============
#
--------------
#
######################################################################
# Multi-channel mask, ref_channel solution
#
----------------------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
ipd
.
Audio
(
results_multi
[
'ref_channel'
],
rate
=
16000
)
######################################################################
# Multi-channel mask, stv_evd solution
#
------------------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
ipd
.
Audio
(
results_multi
[
'stv_evd'
],
rate
=
16000
)
######################################################################
# Multi-channel mask, stv_power solution
#
--------------------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
ipd
.
Audio
(
results_multi
[
'stv_power'
],
rate
=
16000
)
######################################################################
# Single-channel mask, ref_channel solution
#
-----------------------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
ipd
.
Audio
(
results_single
[
'ref_channel'
],
rate
=
16000
)
######################################################################
# Single-channel mask, stv_evd solution
#
-------------------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
ipd
.
Audio
(
results_single
[
'stv_evd'
],
rate
=
16000
)
######################################################################
# Single-channel mask, stv_power solution
#
---------------------------------------
#
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
ipd
.
Audio
(
results_single
[
'stv_power'
],
rate
=
16000
)
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment