A novel recurrent network based pitch detection technique for quasi-periodic/pitch-varying signals

Proceedings of the International Joint Conference on Neural Networks

Volumn 1, Issue , 2002, Pages 816-821

  Chang, Wei Chen ^a   Su, Alvin W Y ^a  

^a NATIONAL CHENG KUNG UNIVERSITY   (Taiwan)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC NOISE; ACOUSTIC SIGNAL PROCESSING; ALGORITHMS; COMPUTER SIMULATION; DIFFERENCE EQUATIONS; FOURIER TRANSFORMS; FUNCTIONS; INTERPOLATION; SPEECH ANALYSIS; SPEECH SYNTHESIS;

AVERAGE MAGNITUDE DIFFERENCE FUNCTIONS; PITCH DETECTION TECHNIQUE; QUASI-PERIODIC PITCH VARYING SIGNALS; SHORT TERM DIFFERENCE FUNCTIONS; SYNTHESIZED TONES; WINDOWED FOURIER TRANSFORMS;

RECURRENT NEURAL NETWORKS;

EID: 0036073710     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. MELP: The new federal standard at 2400 bps
2. Towards high-quality sound synthesis of the guitar and string instruments
3. Representing musical instrument sounds for their automatic classification
4. A new automatic analysis/synthesis technique for plucked-string instruments
5. A novel Portamento embedded model for electronic music analysis/synthesis
6. An efficient gradient-based algorithm for on-line training of recurrent network trajectories
7. Recurrent backpropagation and the dynamical approach to adaptive neural computation
8. Simulated annealing and weight decay in adaptive learning: The SARPROP algorithm