Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Exercises for Patterns in Recordings
Search
Ben Fields
July 05, 2016
Technology
0
46
Exercises for Patterns in Recordings
from DHOxSS 2015-16
Ben Fields
July 05, 2016
Tweet
Share
More Decks by Ben Fields
See All by Ben Fields
People in the loop machine learning: A case Study in news similarity
bfields
0
150
Human-centric evaluation of similarity spaces of news articles
bfields
2
65
Ethics, Data Science, and Public Service Media
bfields
1
65
The Case for Public Service Recommender Algorithms
bfields
0
720
Bikes are Dope
bfields
0
75
Beyond Your Reckons: from feels to facts
bfields
0
84
People who like cheese also like crackers: a learning hour on recommender systems
bfields
0
90
Auto-Summarising Beer Reviews
bfields
0
76
rMIXr: how we learned to stop worrying and love the graph
bfields
0
110
Other Decks in Technology
See All in Technology
我々は雰囲気で仕事をしている / How can we do vibe coding as well
naospon
2
220
Go で言うところのアレは TypeScript で言うとコレ / Kyoto.なんか #7
susisu
5
1.6k
R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization
takmin
0
430
AIエージェントの開発に必須な「コンテキスト・エンジニアリング」とは何か──プロンプト・エンジニアリングとの違いを手がかりに考える
masayamoriofficial
0
370
LLMエージェント時代に適応した開発フロー
hiragram
1
410
自社製CMSからmicroCMSへのリプレースがプロダクトグロースを加速させた話
nextbeatdev
0
130
そのコンポーネント、サーバー?クライアント?App Router開発のモヤモヤを可視化する補助輪
makotot
3
280
サービスロボット最前線:ugoが挑むPhysical AI活用
kmatsuiugo
0
190
Browser
recruitengineers
PRO
3
290
kintone開発チームの紹介
cybozuinsideout
PRO
0
73k
広島発!スタートアップ開発の裏側
tsankyo
0
240
開発と脆弱性と脆弱性診断についての話
su3158
1
1.1k
Featured
See All Featured
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
jQuery: Nuts, Bolts and Bling
dougneiner
64
7.9k
Visualization
eitanlees
147
16k
How to Ace a Technical Interview
jacobian
279
23k
It's Worth the Effort
3n
187
28k
GitHub's CSS Performance
jonrohan
1031
460k
Agile that works and the tools we love
rasmusluckow
329
21k
Build your cross-platform service in a week with App Engine
jlugia
231
18k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
283
13k
Building Adaptive Systems
keathley
43
2.7k
Intergalactic Javascript Robots from Outer Space
tanoku
272
27k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
358
30k
Transcript
Patterns in Recording - Exercises Ben Fields
WEKA basics • Launch the WEKA Application • Select ‘Explorer’
• Load ’50_weka_class_labeled.arff’ • Select various Attributes (features)
WEKA basics • Attribute selection with regular expressions (‘.*’ is
an expanding wild card) • Find all the MFCC attributes • also select ‘CLASS’ • press ‘Invert’, then ‘Remove’
using a classifier • Select ‘Classify’ tab • ‘Choose’ >>
‘classifiers/bayes/ NaiveBayes’ • set test options to ‘Cross-validation’ • press ‘Start’
putting it all together • now repeat the whole process
using LPC features
Explore more files and features • Load ‘training_data_after_parsing.arff’ • Classify
against the CLASS mood labels using Random Forests and J48. Which performs better? Which classes are most confused?