$30 off During Our Annual Pro Sale. View Details »

Exercises for Patterns in Recordings

Avatar for Ben Fields Ben Fields
July 05, 2016
Technology
0
53

Exercises for Patterns in Recordings

from DHOxSS 2015-16

Avatar for Ben Fields

Ben Fields

July 05, 2016
Tweet

More Decks by Ben Fields

See All by Ben Fields
People in the loop machine learning: A case Study in news similarity
Avatar for Ben Fields bfields
0
160
Human-centric evaluation of similarity spaces of news articles
Avatar for Ben Fields bfields
2
80
Ethics, Data Science, and Public Service Media
Avatar for Ben Fields bfields
1
81
The Case for Public Service Recommender Algorithms
Avatar for Ben Fields bfields
0
780
Bikes are Dope
Avatar for Ben Fields bfields
0
86
Beyond Your Reckons: from feels to facts
Avatar for Ben Fields bfields
0
92
People who like cheese also like crackers: a learning hour on recommender systems
Avatar for Ben Fields bfields
0
99
Auto-Summarising Beer Reviews
Avatar for Ben Fields bfields
0
81
rMIXr: how we learned to stop worrying and love the graph
Avatar for Ben Fields bfields
0
110

Other Decks in Technology

See All in Technology
GitHub Copilotを使いこなす 実例に学ぶAIコーディング活用術
Avatar for 74th(Atsushi Morimoto) 74th
3
3.1k
打 造 A I 驅 動 的 G i t H u b ⾃ 動 化 ⼯ 作 流 程
Avatar for Bo-Yi Wu appleboy
0
340
MLflowで始めるプロンプト管理、評価、最適化
Avatar for Databricks Japan databricksjapan
1
230
re:Invent2025 3つの Frontier Agents を紹介 / introducing-3-frontier-agents
Avatar for tomoki10 tomoki10
0
110
寫​了​幾年​ Code，​然後​呢？​軟體​工程師​必須重新​認識​的​ DevOps
Avatar for Cheng-Wei Chen cheng_wei_chen
1
1.4k
ChatGPTで論⽂は読めるのか
Avatar for Spatial AI Network spatial_ai_network
9
28k
新 Security HubがついにGA！仕組みや料金を深堀り #AWSreInvent #regrowth / AWS Security Hub Advanced GA
Avatar for MasahiroKawahara masahirokawahara
1
2k
MLflowダイエット大作戦
Avatar for LINEヤフーTech (LY Corporation Tech) lycorptech_jp
PRO
1
120
re:Invent 2025 ~何をする者であり、どこへいくのか~
Avatar for tetutetu214 tetutetu214
0
210
年間40件以上の登壇を続けて見えた「本当の発信力」/ 20251213 Masaki Okuda
Avatar for SHIFT EVOLVE shift_evolve
PRO
1
130
SREには開発組織全体で向き合う
Avatar for k-nagase koh_naga
0
290
エンジニアリングマネージャー はじめての目標設定と評価
Avatar for d-haru halkt
0
280

Featured

See All Featured
Writing Fast Ruby
Avatar for Erik Berlin sferik
630
62k
Imperfection Machines: The Place of Print at Facebook
Avatar for Scott Boms scottboms
269
13k
Keith and Marios Guide to Fast Websites
Avatar for Keith Pitt keithpitt
413
23k
The Illustrated Children's Guide to Kubernetes
Avatar for Chris Short chrisshort
51
51k
Fireside Chat
Avatar for paigeccino paigeccino
41
3.7k
Docker and Python
Avatar for Tania Allard trallard
47
3.7k
Side Projects
Avatar for Sacha Greif sachag
455
43k
Done Done
Avatar for chrislema chrislema
186
16k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
Avatar for Kevin Liebholz kevinliebholz
36
6.2k
A better future with KSS
Avatar for Kyle Neath kneath
240
18k
Bootstrapping a Software Product
Avatar for Garrett Dimon garrettdimon
PRO
307
120k
Why Our Code Smells
Avatar for Brandon Keepers bkeepers
PRO
340
57k

Transcript

  1. Patterns in Recording - Exercises Ben Fields

  2. WEKA basics • Launch the WEKA Application • Select ‘Explorer’

    • Load ’50_weka_class_labeled.arff’ • Select various Attributes (features)

  3. WEKA basics • Attribute selection with regular expressions (‘.*’ is

    an expanding wild card) • Find all the MFCC attributes • also select ‘CLASS’ • press ‘Invert’, then ‘Remove’

  4. using a classifier • Select ‘Classify’ tab • ‘Choose’ >>

    ‘classifiers/bayes/ NaiveBayes’ • set test options to ‘Cross-validation’ • press ‘Start’

  5. putting it all together • now repeat the whole process

    using LPC features

  6. 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?