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
71
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Exercises for Patterns in Recordings
from DHOxSS 2015-16
Ben Fields
July 05, 2016
More Decks by Ben Fields
See All by Ben Fields
People in the loop machine learning: A case Study in news similarity
bfields
0
190
Human-centric evaluation of similarity spaces of news articles
bfields
2
100
Ethics, Data Science, and Public Service Media
bfields
1
120
The Case for Public Service Recommender Algorithms
bfields
0
840
Bikes are Dope
bfields
0
130
Beyond Your Reckons: from feels to facts
bfields
0
120
People who like cheese also like crackers: a learning hour on recommender systems
bfields
0
130
Auto-Summarising Beer Reviews
bfields
0
110
rMIXr: how we learned to stop worrying and love the graph
bfields
0
140
Other Decks in Technology
See All in Technology
現場で使える AWS DevOps Agent 活用ノウハウ - Release Management 機能の検証結果を添えて / AWS DevOps Agent Release Management and Know-How
kinunori
5
790
データ活用研修 問いの発見と仮説構築【MIXI 26新卒技術研修】
mixi_engineers
PRO
1
680
ソフトウェアアーキテクチャ研修【MIXI 26新卒技術研修】
mixi_engineers
PRO
2
1k
AWS環境のセキュリティ不安を解消した企業事例 ~よくある課題と対策を一挙公開~
asanoharuki
0
250
AI驚き屋発見器
yama3133
1
380
StepFunctionsとGraphRAGを活用した暗黙知活用のためのRAG基盤
yakumo
0
190
【5分でわかる】セーフィー エンジニア向け会社紹介
safie_recruit
0
53k
事業成長とAI活用を止めないデータ基盤アーキテクチャの設計思想
hiracky16
0
780
AI駆動開発は個人技からチーム戦へ:組織でAIを使いこなすための実践設計
moongift
PRO
0
320
なぜ、あなたのAPIは使われないのか? AX時代の設計原則、ガードレール、運用体制
yokawasa
1
260
システム監視を 「システムを監視するだけ」で 終わらせないために
seiud
0
150
テックカンファレンス三大ステークホルダーの文化人類学 ─ 違いを認め合う関係性作り
bash0c7
5
1.2k
Featured
See All Featured
brightonSEO & MeasureFest 2025 - Christian Goodrich - Winning strategies for Black Friday CRO & PPC
cargoodrich
3
760
Data-driven link building: lessons from a $708K investment (BrightonSEO talk)
szymonslowik
1
1.2k
Art, The Web, and Tiny UX
lynnandtonic
304
22k
Typedesign – Prime Four
hannesfritz
42
3.1k
Marketing Yourself as an Engineer | Alaka | Gurzu
gurzu
0
270
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
390
Done Done
chrislema
186
16k
Building an army of robots
kneath
306
46k
技術選定の審美眼(2025年版) / Understanding the Spiral of Technologies 2025 edition
twada
PRO
118
120k
For a Future-Friendly Web
brad_frost
183
10k
We Are The Robots
honzajavorek
0
290
Impact Scores and Hybrid Strategies: The future of link building
tamaranovitovic
0
350
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?