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
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Ben Fields
July 05, 2016
Technology
0
56
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
170
Human-centric evaluation of similarity spaces of news articles
bfields
2
83
Ethics, Data Science, and Public Service Media
bfields
1
91
The Case for Public Service Recommender Algorithms
bfields
0
790
Bikes are Dope
bfields
0
93
Beyond Your Reckons: from feels to facts
bfields
0
99
People who like cheese also like crackers: a learning hour on recommender systems
bfields
0
110
Auto-Summarising Beer Reviews
bfields
0
93
rMIXr: how we learned to stop worrying and love the graph
bfields
0
110
Other Decks in Technology
See All in Technology
予期せぬコストの急増を障害のように扱う――「コスト版ポストモーテム」の導入とその後の改善
muziyoshiz
1
2k
SREのプラクティスを用いた3領域同時 マネジメントへの挑戦 〜SRE・情シス・セキュリティを統合した チーム運営術〜
coconala_engineer
2
710
AWS Network Firewall Proxyを触ってみた
nagisa53
1
240
生成AIを活用した音声文字起こしシステムの2つの構築パターンについて
miu_crescent
PRO
3
210
M&A 後の統合をどう進めるか ─ ナレッジワーク × Poetics が実践した組織とシステムの融合
kworkdev
PRO
1
480
CDK対応したAWS DevOps Agentを試そう_20260201
masakiokuda
1
370
フルカイテン株式会社 エンジニア向け採用資料
fullkaiten
0
10k
データの整合性を保ちたいだけなんだ
shoheimitani
8
3.2k
SREが向き合う大規模リアーキテクチャ 〜信頼性とアジリティの両立〜
zepprix
0
470
Bill One 開発エンジニア 紹介資料
sansan33
PRO
5
17k
Cosmos World Foundation Model Platform for Physical AI
takmin
0
950
顧客との商談議事録をみんなで読んで顧客解像度を上げよう
shibayu36
0
270
Featured
See All Featured
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.6k
Bioeconomy Workshop: Dr. Julius Ecuru, Opportunities for a Bioeconomy in West Africa
akademiya2063
PRO
1
55
Reflections from 52 weeks, 52 projects
jeffersonlam
356
21k
Un-Boring Meetings
codingconduct
0
200
Thoughts on Productivity
jonyablonski
74
5k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
1.7k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
249
1.3M
The innovator’s Mindset - Leading Through an Era of Exponential Change - McGill University 2025
jdejongh
PRO
1
93
Embracing the Ebb and Flow
colly
88
5k
Bootstrapping a Software Product
garrettdimon
PRO
307
120k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
9
1.2k
Practical Orchestrator
shlominoach
191
11k
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?