Burak Gündüz
Creative Coder
Enjoying life by building at the intersection of code, audio and creative artistry.
- Vision
- 4
- Tekil Abone
- 1
Burak Gündüz tarafından hazırlanan Vision'lar
How Computers Speak: Written Text, Spoken Words, and Speech Engines
This series walks through how written text becomes spoken audio. You will learn how a speech system is a chain of stages rather than a single box, how dates, money, phone numbers, and abbreviations are rewritten into spoken words, how an offline engine and two neural engines differ in sound and control, how speech is stored and compared, and what a side-by-side listening comparison actually showed.
How Computers Hear Melody: Pitch, Timing, and Note Feedback
This series walks through how a practice engine scores a sung or played melody against a target exercise. You will learn how sound is prepared and converted into MIDI, how probabilistic pitch tracking finds a note over time, how notes are grouped and aligned so extra or missed notes are not graded as pitch mistakes, how pitch and timing scores use perceptual thresholds instead of statistical outliers, and how per-note feedback can stay specific without demotivating false alarms.
How Computers Hear Rhythm: Tempo, Beats, and Musical Style
Diving into how tempo, beat tracking, and genre classification actually work. You will learn how standardized audio becomes a map of musical attacks, how repeating those attacks reveals beats per minute (and why half-time and double-time are not always mistakes), how a tracker can land on strong onsets while staying evenly spaced, how a short list of timbre and rhythm measurements describes style, and how a leakage-free split keeps a classifier honest.
How Computers Hear Harmony: Chords, Keys, and Music Theory
Understand how chord and key recognition actually works. You will learn how sound waves become digital numbers, how the Constant-Q chromagram isolates musical notes, how simple geometry identifies major and minor triads without complex AI models, how majority-vote smoothing cleans up audio jitter, and how cognitive psychology can estimate a home key when the music stays near one major or minor center.