100 likes | 194 Views
Report about polyphonic music transcription. Enabling Access to Sound Archives through Integration, Enrichment and Retrieval. What is Automatic Music Transcription. Transcription. Play/Synthesis. Key technologies of polyphonic music transcription. Music onset detection
E N D
Report about polyphonic music transcription Enabling Access to Sound Archives through Integration, Enrichment and Retrieval
What is Automatic MusicTranscription Transcription Play/Synthesis
Key technologies of polyphonic music transcription • Music onset detection • Polyphonic music transcription
A particular time-frequency analysis tool: Resonator Time-frequency Image (RTFI) • Computation-efficient • implemented by the first-order complex resonator filter bank • development of multi-resolution fast implementation • A uniform Framework of TF analysis for music signal • unlike Cohen’s class and Affine class, RTFI is not limited to either constant-band or constant-Q • by simply setting several parameters, the RTFI can implement different TF analysis such as constant-band, constant-Q and ear-like TF analysis • a frequency-dependent time-frequency analysis
Music Onset Detection • What is music onset detection • detection of the instant when a new event begins in acoustical signal • hard Onset (fast transition with big energy change) • soft Onset (slow transition with small energy change) • How human detect onset • energy change • pitch change • timbre change
Onset detection method inEASAIER • Time-Frequency Processing: • incorporating psychoacoustics knowledge about loudness perception • making energy-change and pitch-change as clear as possible • Detection Algorithms: detecting onsets by both energy and pitch change clues
Problems in Polyphonic Pitch Estimation • Harmonic components of different music notes may overlap • In-harmonic: some music instrument have inharmonic timbre
Polyphonic Pitch Estimation Method in EASAIER 5 Steps: • Performing RTFI analysis • Extracting harmonic components • Making preliminary estimation of possible pitches • Cancelling the extra pitches by checking harmonic components ( simple timbre model) • Checking pitch candidates by spectral smoothing principle
Compared with other state-of-art methodsMIREX 2007 Evaluation • Music onset detection • According to the overall performance, our method wins this contest • Polyphonic pitch estimation (Multiple-F0 estimation task) • our method performed third best in the submitted 16 methods. The performance differences between our method and the first and second best method are minor. • but most computationally efficient, about 10 time faster than the first best method, and 100 time faster than the second best method
Future plan • To develop the method for note offset detection • To estimate the note duration time • To improve and evaluate the automation music transcription system • To apply the transcription system assisting the other functionalities such as content-based music retrieval