Pre and Post-Processing for Pitch Tracking

Slides:



Advertisements
Similar presentations
Digital Signal Processing
Advertisements

Pitch Tracking (音高追蹤) Jyh-Shing Roger Jang (張智星) MIR Lab (多媒體資訊檢索實驗室)
Shallow Copy Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
Onset Detection in Audio Music J.-S Roger Jang ( 張智星 ) MIR LabMIR Lab, CSIE Dept. National Taiwan University.
Retrieval Methods for QBSH (Query By Singing/Humming) J.-S. Roger Jang ( 張智星 ) Multimedia Information Retrieval.
Experiments with MATLAB Experiments with MATLAB Google PageRank Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University, Taiwan
Overview of Adaptive Multi-Rate Narrow Band (AMR-NB) Speech Codec
Communications & Multimedia Signal Processing Report of Work on Formant Tracking LP Models and Plans on Integration with Harmonic Plus Noise Model Qin.
Digital Image Processing Chapter 5: Image Restoration.
MSU CSE 803 Stockman Linear Operations Using Masks Masks are patterns used to define the weights used in averaging the neighbors of a pixel to compute.
Classification of Music According to Genres Using Neural Networks, Genetic Algorithms and Fuzzy Systems.
MSU CSE 803 Linear Operations Using Masks Masks are patterns used to define the weights used in averaging the neighbors of a pixel to compute some result.
2016/6/41 Recent Improvement Over QBSH and AFP J.-S. Roger Jang (張智星) Multimedia Information Retrieval (MIR) Lab CSIE Dept, National Taiwan Univ.
Chapter 5: Neighborhood Processing
Generating Sinusoidal Signals Prof. Brian L. Evans Dept. of Electrical and Computer Engineering The University of Texas at Austin EE 445S Real-Time Digital.
Binary Search Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
QBSH Corpus The QBSH corpus provided by Roger Jang [1] consists of recordings of children’s songs from students taking the course “Audio Signal Processing.
Digital Image Processing Lecture 9: Filtering in Frequency Domain Prof. Charlene Tsai.
Simulation of Stock Trading J.-S. Roger Jang ( 張智星 ) MIR Lab, CSIE Dept. National Taiwan University.
Linear Classifiers (LC) J.-S. Roger Jang ( 張智星 ) MIR Lab, CSIE Dept. National Taiwan University.
Pitch Tracking in Time Domain Jyh-Shing Roger Jang ( 張智星 ) MIR Lab, Dept of CSIE National Taiwan University
Final Project: English Preposition Usage Checker J.-S. Roger Jang ( 張智星 ) MIR Lab, CSIE Dept. National Taiwan University.
Onset Detection, Tempo Estimation, and Beat Tracking
CS 591 S1 – Computational Audio -- Spring, 2017
Search in Google's N-grams
Intro. to Audio Signals Jyh-Shing Roger Jang (張智星)
Quadratic Classifiers (QC)
DP for Optimum Strategies in Games
PATTERN COMPARISON TECHNIQUES
Query by Singing/Humming via Dynamic Programming
Discrete Fourier Transform (DFT)
Introduction to Pattern Recognition
Singing Voice Separation via Active Noise Cancellation 使用主動式雜訊消除於歌聲分離
MART: Music Assisted Running Trainer
Pat P. W. Chan,  Michael R. Lyu, Roland T. Chin*
Automatic Speech Processing Project
Vocoders.
Closing Remarks on MSAR-2017
Intro. to Audio Signals Jyh-Shing Roger Jang (張智星)
Chapter 3 Sampling.
Introduction to Music Information Retrieval (MIR)
Feature Selection for Pattern Recognition
Error Concealment In The Pixel Domain And MATLAB commands
EE Audio Signals and Systems
1 Vocoders. 2 The Channel Vocoder (analyzer) : The channel vocoder employs a bank of bandpass filters,  Each having a bandwidth between 100 HZ and 300.
Fundamentals Data.
Search in OOXX Games J.-S. Roger Jang (張智星) MIR Lab, CSIE Dept.
Applications of Stacks and Queues for Constraint Satisfaction Problems
Intro. to Audio Signals Jyh-Shing Roger Jang (張智星)
Lab 5 Part II Instructions
Neuro-Fuzzy and Soft Computing for Speaker Recognition (語者辨識)
Measured Period VOICE SIGNAL
Hierarchical Clustering
Image and Video Processing
Circularly Linked Lists and List Reversal
Linear Operations Using Masks
Endpoint Detection ( 端點偵測)
Applications of Heaps J.-S. Roger Jang (張智星) MIR Lab, CSIE Dept.
Query by Singing/Humming via Dynamic Programming
Insertion Sort Jyh-Shing Roger Jang (張智星)
Examples of Time Complexity
Scientific Computing: Closing 科學計算:結語
EE Audio Signals and Systems
Prediction in Stock Trading
Naive Bayes Classifiers (NBC)
Game Trees and Minimax Algorithm
Duration & Pitch Modification via WSOLA
Sorting Algorithms Jyh-Shing Roger Jang (張智星)
Jyh-Shing Roger Jang (張智星) CSIE Dept, National Taiwan University
Storing Game Entries in an Array
Presentation transcript:

Pre and Post-Processing for Pitch Tracking Jyh-Shing Roger Jang (張智星) MIR Lab, Dept of CSIE National Taiwan University jang@mirlab.org http://mirlab.org/jang

Preprocessing for Pitch Tracking Some commonly used preprocessing for the audio signals before pitch tracking Pre-filtering the signals Clipping the signals SIFT method for the signals

Preprocessing: Pre-filtering Observation Range of humans’ pitch: [40, 1000] Idea Low-pass the signals with a cutoff frequency between 800 and 1000 Characteristics The effect is yet to be verified

Preprocessing: Clipping Observation Small signals near zero is likely to cause pitch tracking error Idea Clip the signals Characteristics Save computation for embedded system Overall effect is yet to be verified

Preprocessing: SIFT Observation Channel effect is likely to cause pitch tracking error Idea of SIFT (simple inverse filter tracking) Identify the excitation via LPC Use the excitation for PDF Characteristics Overall effect is yet to be verified

Example of SIFT siftAcf01.m

Example of PT based on SIFT & ACF ptBySiftAcf01.m

Postprocessing for Pitch Tracking Some commonly used postprocessing for pitch tracking Smoothing to remove abrupt-changing pitch Interpolation to increase pitch precision

Postprocessing: Smoothing Smoothing by a median filter ptWithMedianFilter01.m

Postprocessing: Interpolation Idea Using the pitch point and its neighbors to identify the max position ptWithParabolicFit01.m

Unreliable Pitch Removal (1/2) Pitch removal via volume thresholding Plot by self demo of ptByPf.m

Unreliable Pitch Removal (2/2) Pitch removal via volume/clarity thresholding Plot by self demo of ptByPf.m

Rest Handling Original pitch vectors with rests. Rests are replaced by previous nonzero pitch. Good for LS. Rests are removed. Good for DTW.

Typical Result of Pitch Tracking Pitch tracking via autocorrelation for茉莉花 (jasmine)

Comparison of Pitch Vectors Yellow line : Target pitch vector