![Page 1: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/1.jpg)
1© 2015 The MathWorks, Inc.
Reusing and Prototyping Code to
Accelerate Innovation
The Case of Smart Voice Interfaces
Gabriele Bunkheila
![Page 2: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/2.jpg)
2
What Device Is This?
![Page 3: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/3.jpg)
3
▪ Innovate
▪ Reuse
▪ Prototype
![Page 4: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/4.jpg)
4
System Prototype Demo
Live voice detection, beamforming and speech recognition
[Video placeholder]
![Page 5: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/5.jpg)
5
What Are Microphone Arrays?
![Page 6: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/6.jpg)
6
Why Microphone Arrays?
![Page 7: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/7.jpg)
7
How Can I…
1. Design and simulate a microphone array system?
2. Validate my voice interface can work
in real-life scenarios?
3. Understand what else can
help me improve my performance?
![Page 8: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/8.jpg)
8
How Can I…
1. Design and simulate a microphone array system?
![Page 9: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/9.jpg)
9
Section Overview
From analysing a microphone topology to simulating a
beamforming scenario
[Video placeholder]
![Page 10: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/10.jpg)
10
How To Get Started?
![Page 11: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/11.jpg)
11
Demo
App-aided exploration of array topologies
[Video placeholder]
![Page 12: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/12.jpg)
12
Demo
Selecting a set of directionally-selective array configurations
[Video placeholder]
![Page 13: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/13.jpg)
13
Demo
Simulating time-domain sound acquisition through a
microphone array
[Video placeholder]
![Page 14: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/14.jpg)
14
Demo
Interactive beamforming simulation with voice source
[Video placeholder]
![Page 15: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/15.jpg)
15
How Can I…
1.
2. Validate my voice interface can work
in real-life scenarios?
![Page 16: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/16.jpg)
16
Constrained Simulations vs. Real Life
![Page 17: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/17.jpg)
17
Constrained Simulations vs. Real Life
![Page 18: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/18.jpg)
18
Demo
Streaming live multichannel audio in and out of MATLAB
[Video placeholder]
![Page 19: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/19.jpg)
19
Demo
Real-time prototyping with live tuning of beamforming
algorithms in MATLAB
[Video placeholder]
![Page 20: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/20.jpg)
20
Demo
Common uses of Digital Audio Workstations (DAW) and audio
plugins for sound acquisition and audio enhancement
[Video placeholder]
![Page 21: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/21.jpg)
21
Demo
Generating VST plugins from MATLAB and prototyping array
processing algorithms on Digital Audio Workstations
[Video placeholder]
![Page 22: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/22.jpg)
22
How Can I…
1. Design and simulate a microphone array system?
2.
3. Understand what else can
help me improve my performance?
![Page 23: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/23.jpg)
23
Recap Demo
Using prototypes to brainstorm on incremental improvements
early on
[Video placeholder]
![Page 24: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/24.jpg)
24
How To Measure Performance?
▪ "91.5% of spoken
sentences correctly
converted"
▪ Output audio
"sounds good"
![Page 25: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/25.jpg)
25
?
?
?
![Page 26: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/26.jpg)
26
Getting Started With a Cloud Service for Speech Recognition
[Video placeholder]
![Page 27: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/27.jpg)
27
Hide Complexity to Accelerate Reuse
>> [samples, fs] = audioread('hellomatlabexpo.wav');
>> soundsc(samples, fs)
>> [speechString, confidenceInterval] = speech2text(samples, fs , 'en-US')
speechString =
'hello Matlab Expo'
confidenceInterval =
0.9526
![Page 28: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/28.jpg)
28
?
?
✓
![Page 29: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/29.jpg)
29
Plugin Hosting
>> noiseRemover = loadAudioPlugin('ERA-N.vst')
noiseRemover =
VST plugin 'ERA-N' 2 in, 2 out
Processing: 40 %Gain: 0 dBTilt: 'NoTilt'
Bypass: 0
>> noiseRemover.Processing = 60;>> noiseRemover.Gain = 3;>> y = process(noiseRemover, x)
https://accusonus.com/products/era-n
![Page 30: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/30.jpg)
30
Demo
Testing an external audio plugin within a MATLAB live system
model
[Video placeholder]
![Page 31: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/31.jpg)
31
?
✓ ✓
![Page 32: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/32.jpg)
32
Building a Small Speech Dataset Quickly
Apps enable interactivity and automation
![Page 33: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/33.jpg)
33
Building a Small Speech Dataset Quickly
Can you improve speech content labelling?
http://www.cs.cmu.edu/afs/cs.cmu.edu/project/fgdata/OldFiles/Recorder.app/utterances/Type1/harvsents.txt
![Page 34: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/34.jpg)
34
Building a Small Speech Dataset Quickly
Example: an App with automated content labelling
![Page 35: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/35.jpg)
35
Demo
Testing speech recognition performance of different design
variants (including with new enhancements)
[Video placeholder]
![Page 36: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/36.jpg)
36
✓ ✓
✓
![Page 37: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/37.jpg)
37
How Can I…
1. Design and simulate a microphone array system?
2. Validate my voice interface can work
in real-life scenarios?
3. Understand what else can
help me improve my performance?
![Page 38: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/38.jpg)
38
System Prototype Demo – Summary and Recap
Live voice detection, beamforming and speech recognition
[Video placeholder]
![Page 39: Reusing and Prototyping Code to Accelerate Innovation€¦ · Demo Testing speech recognition performance of different design variants (including with new enhancements) [Video placeholder]](https://reader033.vdocuments.us/reader033/viewer/2022051915/6006ef60ddd79e329504c05e/html5/thumbnails/39.jpg)
39
Summary
▪ Innovate
▪ Reuse
▪ Prototype