Browsing by Author "Bai, Mingsain R."

Now showing 1 - 2 of 2

Intelligent preprocessing and classification of audio signals
(2007-05-01)
Bai, Mingsain R.
;
Chen, Meng-Chun
;
機械工程學系
;
Department of Mechanical Engineering
An audio processor that integrates intelligent classification and preprocessing algorithms is presented. Audio features in the time and frequency domains are extracted and processed prior to classification. Classification algorithms, including the nearest neighbor rule (NNR), artificial neural networks (ANN), fuzzy neural networks (FNN), and hidden Markov models (HMM), are used to classify and identify singers and musical instruments. A training phase is required to establish a feature space template, followed by a test phase in which the audio features of the test data are calculated and matched to the feature space template. In addition to audio classification, the proposed system provides several independent component analysis (ICA)-based preprocessing functions for blind source separation, voice removal, and noise reduction. The proposed techniques were applied to process various kinds of audio program materials. The test results reveal that the performance of the methods is satisfactory, but varies slightly with the algorithm and program materials used in the tests.
Optimization of Microspeaker Diaphragm Pattern Using Combined Finite Element-Lumped Parameter Models
(2008-08-01)
Bai, Mingsain R.
;
Liu, Ching-Yu
;
Chen, Rong-Liang
;
機械工程學系
;
Department of Mechanical Engineering
Microspeakers in portable devices are expected to meet a number of conflicting requirements such as miniaturization, high output level, and good sound quality. In contrast to large loudspeakers, the structures of microspeakers are generally simplified by removal of the suspension. The diaphragm serves as not only a sound radiator but also the suspension. Thus, the pattern design of the diaphragm is crucial to the overall response and performance of a microspeaker. The traditional approach for modeling microspeakers using lumped parameter models is generally incapable of modeling flexural modes in high frequencies. In this paper, we present a hybrid approach that combines finite-element analysis (FEA) and electro-mechano-acoustical (EMA) analogous circuit to provide a more accurate model than the conventional approaches. In particular, the minute details of diaphragms are taken into account in calculating the mechanical impedance of the diaphragm-voice coil assembly using FEA. The mechanical impedance is then incorporated into the lumped parameter model. The responses can be simulated by solving the loop equations. On the basis of this simulation model, we optimize the pattern design of the diaphragm using the Taguchi method. In addition, we determine the optimal number of diaphragm corrugations by using sensitivity analysis.