Basic Features of Audio Signals音讯的基本特徵课件.ppt

* * * * * * * * * * * * * * * 三民主義 三國演義 三皇五帝 中流砥柱 中華史地 光明永繼 詩人李杜 聰明穎悟 低吟緩步 遵從禮義 * * * Basic Features of Audio Signals(音訊的基本特徵) Jyh-Shing Roger Jang (張智星) /jang MIR Lab, CSIE Dept National Taiwan Univ., Taiwan Audio Features Commonly used audio features Volume, pitch, spectrum, zero crossing rate, etc. Our goal These features can be perceived (more or less) subjectively. Our goal is to compute them quantitatively (and objectively) for further processing and recognition. General Steps for Audio Analysis Frame blocking Frame duration of 20~40 ms or so Frame-based feature extraction Volume, zero-crossing rate, pitch, MFCC, etc. Frame-based Analysis Pitch vector for QBSH comparison MFCC for speech recognition via HMM training evaluation … Mel-frequency cepstral coefficients Query by singing/humming Hidden Markov models Frame Blocking Sample rate = 16 kHz Frame size = 512 samples Frame duration = 512/16000 = 0.032 s = 32 ms Overlap = 192 samples Hop size = frame size – overlap = 512-192 = 320 samples Frame rate = 16000/320 = 50 frames/sec Overlap Frame Quiz! hop size frame size = hop size + overlap overlap Basic Features of Audio Signals Volume (音量): the amplitude of audio signals Also known as intensity, or energy. Pitch (音高): Fundamental frequency (the number of fundamental periods in a second) Usually males have a lower pitch while females have a higher one Timbre (音色): Waveform inside a fundamental period. Different vowels have different timbres Different singers also have different timbres. Check out waveform Of your recording! Quiz! Audio Features in Time Domain 3 of the most prominent time-domain audio features in a frame (aka analysis window) Intensity Fundamental period Timbre: Waveform within an FP Quiz! Audio Features in Frequency Domain Frequency-domain audio features in a frame Energy: Sum of power spectrum Pitch: Distance between harmonics Timbre: Smoothed spectrum Second formant F2 First formant F1 Pitch freq Energy Frame-based Manipulation