Browsing by Author "Wang, Hsin-Min"

Now showing 1 - 20 of 25

A kernel-based discrimination framework for solving hypothesis testing problems with application to speaker verification
(2006)
Chao, Yi-Hsiang
;
Tsai, Wei-Ho
;
Wang, Hsin-Min
;
Chang, Ruei-Chuan
;
資訊工程學系
Real-word applications often involve a binary hypothesis testing problem with one of the two hypotheses ill-defined and hard to be characterized precisely by a single measure. In this paper, we develop a framework that integrates multiple hypothesis testing measures into a unified decision basis, and apply kernel-based classification techniques, namely, Kernel Fisher Discriminant (KFD) and Support Vector Machine (SVM), to optimize the integration. Experiments conducted on speaker verification demonstrate the superiority of our approaches over the predominant approaches.
A novel alternative hypothesis characterization using kernel classifiers for LLR-based speaker verification
(2006)
Chao, Yi-Hsiang
;
Wang, Hsin-Min
;
Chang, Ruei-Chuan
;
資訊工程學系
;
Department of Computer Science
In a log-likelihood ratio (LLR)-based speaker verification system, the alternative hypothesis is usually ill-defined and hard to characterize a priori, since it should cover the space of all possible impostors. In this paper, we propose a new LLR measure in an attempt to characterize the alternative hypothesis in a more effective and robust way than conventional methods. This LLR measure can be further formulated as a non-linear discriminant classifier and solved by kernel-based techniques, such as the Kernel Fisher Discriminant (KFD) and Support Vector Machine (SVM). The results of experiments on two speaker verification tasks show that the proposed methods outperform classical LLR-based approaches.
A NOVEL MECHANICAL-MECHANISM ENHANCED THERMOMAGNETIC TWEEZER DEMONSTRATING GRIPPING OF FERROMAGNETIC AND NON-FERROMAGNETIC OBJECTS
(2016)
Wang, Hsin-Min
;
Chung, Tien-Kan
;
Chen, Chin-Chung
;
Cheng, Chih-Cheng
;
Lin, Chu-Yi
In this article, we demonstrate a mechanical-mechanism enhanced thermomagnetic tweezer. The tweezer which utilizes a thermal-magnetic-mechanical converting consists of two cross jointed Al arms, two Gd sheets, two NdFeB hard magnets, two thermoelectric generators (TEGs), and a ball bearing set. When comparing conventional thermomagnetic grippers, our thermomagnetic tweezer can grip either ferromagnetic or non-ferromagnetic objects and avoid producing temperature-influence to the gripped objects. Experimental results show that we can control TEGs to generate a temperature difference to operate the tweezer to grip small ferromagnetic objects (such as NdFeB hard magnet) and other non-ferromagnetic objects (such as PMMA bulk). The maximum gripping force produced by the tweezer operated by applying the DC current of 1.3 A with the voltage of 0.85 V is 0.59 newton. The corresponding gripping and releasing duration is 7.9 seconds and 8.1 seconds, respectively. According to these results, our tweezer would produce more practical objects-gripping applications.
A NOVEL NANOELECTROMAGNETIC SYSTEM USING MULTIFERROIC/MAGNETOELECTRIC NI-NANO-CHEVRON/PMN-PT HETEROSTRUCTURE TO DEMONSTRATE AN ELECTRIC -FIELD -CONTROLLED PERMANENT MAGNETIC SINGLE -DOMAIN TRANSFORMATION
(2018-01-01)
Cheng, Chih-Cheng
;
Lin, Shin-Hung
;
Chen, Yu-Jen
;
Wang, Hsin-Min
;
Chu, Hou-Jen
In this paper, we report a novel nanoelectromagnetic system using multiferroic/magnetoelectric Ni-nanochevron/PMN-PT heterostructure to demonstrate an electric field -controlled permanent magnetic single-domain transformation. The heterostructure consists of a magnetostrictive Ni-nano-chevron, Pt top and bottom electrodes, and a piezoelectric PMN-PT substrate. In initial state (as demagnetized), the magnetization of the magnetic single domain is stably along the long axis of the nano-chevron. A magnetic field of 3000 Oe (along 45 degree of nano-chevron) is applied to magnetize the Ni-nano-chevron from stable single domain to metastable two-domains. After this, an electric field of 0.8MV/m is applied to the PMN-PT substrate to produce the converse magnetoelectric effect to transform the two-domains. After the electric field is removed, the two-domains are further transformed back to the single-domain. Finally, when comparing the domains before and after applying our approach, approximately 50 % of single-domains are successfully and permanently switched (i.e., magnetization-direction is permanently rotated 180 degrees).
A NOVEL THERMOMAGNETIC ROTATIONAL-ACTUATOR
(2016)
Cheng, Chih-Cheng
;
Chung, Tien-Kan
;
Chen, Chin-Chung
;
Wang, Hsin-Min
;
機械工程學系
In this article, we demonstrate a novel thermomagnetic rotational-actuator. The actuator consists of thermomagnetic material Gadolinium sheets, thermoelectric generators, a rotary aluminum cantilever beam with NdFeB hard magnets fixed on the free-end of the beam, a stainless steel bearing, and a mechanical frame. As conventional magnetic rotational actuators are controlled by using electromagnetic-induction based magnetic-force interaction produced by electromagnets or coils, our actuator is controlled by using a heating-induced magnetic force interaction produced by the thermomagnetic generators. Experimental results show that our actuator is successfully rotated by a controlled sequence of temperature difference generated by the TEGs.
A Probabilistic Interpretation for Artificial Neural Network-based Voice Conversion
(2015)
Hwang, Hsin-Te
;
Tsao, Yu
;
Wang, Hsin-Min
;
Wang, Yih-Ru
;
Chen, Sin-Horng
Voice conversion (VC) using artificial neural networks (ANNs) has shown its capability to produce better sound quality of the converted speech than that using Gaussian mixture model (GMM). Although ANN-based VC works reasonably well, there is still room for further improvement. One of the promising ways is to adopt the successful techniques in statistical model-based parameter generation (SMPG), such as trajectory-based mapping approaches that are originally designed for GMM-based VC and hidden Markov model (HMM)-based speech synthesis. This study presents a probabilistic interpretation for ANN-based VC. In this way, ANN-based VC can easily incorporate the successful techniques in SMPG. Experimental results demonstrate that the performance of ANN-based VC can be effectively improved by two trajectory-based mapping techniques (maximum likelihood parameter generation (MLPG) algorithm and maximum likelihood-based trajectory mapping considering global variance (referred to as MLGV)), compared to the conventional ANN-based VC with frame-based mapping and the GMM-based VC with the MLPG algorithm. Moreover, ANN-based VC with the trajectory-based mapping techniques can achieve comparable performance when compared to the state-of-the-art GMM-based VC with the MLGV algorithm.
A prototypes-embedded genetic K-means algorithm
(2006)
Cheng, Shih-Sian
;
Chao, Yi-Hsiang
;
Wang, Hsin-Min
;
Fu, Hsin-Chia
;
資訊工程學系
This paper presents a genetic algorithm (GA) for K-means clustering. Instead of the widely applied string-of-group-numbers encoding, we encode the prototypes of the clusters into the chromosomes. The crossover operator is designed to exchange prototypes between two chromosomes. The one-step K-means algorithm is used as the mutation operator. Hence, the proposed GA is called the prototypes-embedded genetic K-means algorithm (PGKA). With the inherent evolution process of evolutionary algorithms, PGKA has superior performance than the classical K-means algorithm, while comparing to other GA-based approaches, PGKA is more efficient and suitable for large scale data sets.
A Rotational Actuator Using a Thermomagnetic-Induced Magnetic Force Interaction
(2018-01-01)
Cheng, Chih-Cheng
;
Chung, Tien-Kan
;
Chen, Chin-Chung
;
Wang, Hsin-Min
;
機械工程學系
In this paper, we demonstrate a rotational actuator using a thermomagnetic-induced magnetic force interaction. The actuator consists of a magnetic rotary beam, stainless-steel bearing, mechanical frame, thermomagnetic Gadolinium sheets, and thermoelectric generators (TEGs). Experimental results show that applying a sequence of currents to the TEGs successfully produces sequential magnetic forces. Consequently, these sequential magnetic forces rotate the beam for revolutions. When applying a sequence set of currents of -0.5 and 1.3 A, the maximum rotation speed and maximum stall torque of the actuator is 3.81 rpm and 136.2 mu Nm, respectively. Most importantly, the operating temperatures of other thermomagnetic (and electrothermal) actuators are usually high, but the operating temperature of our actuator is approximately room temperature (13 degrees C-27 degrees C). Therefore, our actuators have more practical applications. According to the above-mentioned features, we believe our actuator is an important alternative approach to developing future rotational actuators and motors.
A Study of Mutual Information for GMM-Based Spectral Conversion
(2012)
Hwang, Hsin-Te
;
Tsao, Yu
;
Wang, Hsin-Min
;
Wang, Yih-Ru
;
Chen, Sin-Horng
The Gaussian mixture model (GMM)-based method has dominated the field of voice conversion (VC) for last decade. However, the converted spectra are excessively smoothed and thus produce muffled converted sound. In this study, we improve the speech quality by enhancing the dependency between the source (natural sound) and converted feature vectors (converted sound). It is believed that enhancing this dependency can make the converted sound closer to the natural sound. To this end, we propose an integrated maximum a posteriori and mutual information (MAPMI) criterion for parameter generation on spectral conversion. Experimental results demonstrate that the quality of converted speech by the proposed MAPMI method outperforms that by the conventional method in terms of formal listening test.
Alleviating the Over-Smoothing Problem in GMM-Based Voice Conversion with Discriminative Training
(2013-01-01)
Hwang, Hsin-Te
;
Tsao, Yu
;
Wang, Hsin-Min
;
Wang, Yih-Ru
;
Chen, Sin-Horng
In this paper, we propose a discriminative training (DT) method to alleviate the muffled sound effect caused by over smoothing in the Gaussian mixture model (GMM)-based voice conversion (VC). For the conventional GMM-based VC, we often observed a large degree of ambiguities among acoustic classes (generative classes), determined by the source feature vectors for generating the converted feature vectors, causing the "muffled sound" effect on the converted voice. The proposed DT method is applied to refine the parameters in the maximum likelihood (ML)-trained joint density GMM (JDGMM) in the training stage to reduce the ambiguities among acoustic classes (generative classes) to alleviate the muffled sound effect. Experimental results demonstrate that the DT method significantly enhances the discriminative power between acoustic classes (generative classes) in the objective evaluation and effectively alleviates the muffled sound effect in the subjective evaluation.
Automatic construction of regression class tree for MLLR via model-based hierarchical clustering
(2006)
Cheng, Shih-Sian
;
Xu, Yeong-Yuh
;
Wang, Hsin-Min
;
Fu, Hsin-Chia
;
資訊工程學系
In this paper, we propose a model-based hierarchical clustering algorithm that automatically builds a regression class tree for the well-known speaker adaptation technique - Maximum Likelihood Linear Regression (MLLR). When building a regression class tree, the mean vectors of the Gaussian components of the model set of a speaker independent CDHMM-based speech recognition system are collected as the input data for clustering. The proposed algorithm comprises two stages. First, the input data (i.e., all the Gaussian mean vectors of the CDHMMs) is iteratively partitioned by a divisive hierarchical clustering strategy, and the Bayesian Information Criterion (BIC) is applied to determine the number of clusters (i.e., the base classes of the regression class tree). Then, the regression class tree is built by iteratively merging these base clusters using an agglomerative hierarchical clustering strategy, which also uses BIC as the merging criterion. We evaluated the proposed regression class tree construction algorithm on a Mandarin Chinese continuous speech recognition task. Compared to the regression class tree implementation in HTK, the proposed algorithm is more effective in building the regression class tree and can determine the number of regression classes automatically.
Automatic Music Video Generation Based on Simultaneous Soundtrack Recommendation and Video Editing
(2017-01-01)
Lin, Jen-Chun
;
Wei, Wen-Li
;
Yang, James
;
Wang, Hsin-Min
;
Liao, Hong-Yuan Mark
An automated process that can suggest a soundtrack to a user-generated video (UGV) and make the UGV a music-compliant professional-like video is challenging but desirable. To this end, this paper presents an automatic music video (MV) generation system that conducts soundtrack recommendation and video editing simultaneously. Given a long UGV, it is first divided into a sequence of fixed-length short (e.g., 2 seconds) segments, and then a multi-task deep neural network (MDNN) is applied to predict the pseudo acoustic (music) features (or called the pseudo song) from the visual (video) features of each video segment. In this way, the distance between any pair of video and music segments of same length can be computed in the music feature space. Second, the sequence of pseudo acoustic (music) features of the UGV and the sequence of the acoustic (music) features of each music track in the music collection are temporarily aligned by the dynamic time warping (DTW) algorithm with a pseudosong-based deep similarity matching (PDSM) metric. Third, for each music track, the video editing module selects and concatenates the segments of the UGV based on the target and concatenation costs given by a pseudo-song-based deep concatenation cost (PDCC) metric according to the DTW-aligned result to generate a music-compliant professional-like video. Finally, all the generated MVs are ranked, and the best MV is recommended to the user. The MDNN for pseudo song prediction and the PDSM and PDCC metrics are trained by an annotated official music video (OMV) corpus. The results of objective and subjective experiments demonstrate that the proposed system performs well and can generate appealing MVs with better viewing and listening experiences.
BIC-based audio segmentation by divide-and-conquer
(2008)
Cheng, Shih-Sian
;
Wang, Hsin-Min
;
Fu, Hsin-Chia
;
資訊工程學系
;
Department of Computer Science
Audio segmentation has received increasing attention in recent years for its potential applications in automatic indexing and transcription of audio data. Among existing audio segmentation approaches, the BIC-based approach proposed by Chen and Gopalakrishnan is most well-known for its high accuracy. However, this window-growingbased segmentation approach suffers from the high computation cost. In this paper, we propose using the efficient divide-and-conquer strategy in audio segmentation. Our approaches detect acoustic changes by recursively partitioning an analysis window into two sub-windows using Delta BIC. The results of experiments conducted on the broadcast news data demonstrate that our approaches not only have a lower computation cost but also achieve a higher segmentation accuracy than window-growing-based segmentation.
BIC-Based Speaker Segmentation Using Divide-and-Conquer Strategies With Application to Speaker Diarization
(2010-01-01)
Cheng, Shih-Sian
;
Wang, Hsin-Min
;
Fu, Hsin-Chia
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose three divide-and-conquer approaches for Bayesian information criterion (BIC)-based speaker segmentation. The approaches detect speaker changes by recursively partitioning a large analysis window into two sub-windows and recursively verifying the merging of two adjacent audio segments using Delta BIC, a widely-adopted distance measure of two audio segments. We compare our approaches to three popular distance-based approaches, namely, Chen and Gopalakrishnan's window-growing-based approach, Siegler et al.'s fixed-size sliding window approach, and Delacourt and Wellekens's DISTBIC approach, by performing computational cost analysis and conducting speaker change detection experiments on two broadcast news data sets. The results show that the proposed approaches are more efficient and achieve higher segmentation accuracy than the compared distance-based approaches. In addition, we apply the segmentation approaches discussed in this paper to the speaker diarization task. The experiment results show that a more effective segmentation approach leads to better diarization accuracy.
DISCRIMINATIVE FEEDBACK ADAPTATION FOR GMM-UBM SPEAKER VERIFICATION
(2008)
Chao, Yi-Hsiang
;
Tsai, Wei-Ho
;
Wang, Hsin-Min
;
資訊工程學系
;
Department of Computer Science
The GMM-UBM system is the current state-of the-art approach for text-independent speaker verification. The advantage of the approach is that both target speaker model and impostor model (UBM) have generalization ability to handle "unseen" acoustic patterns. However, since GMM-UBM uses a common anti-model, namely UBM, for all target speakers, it tends to be weak in rejecting impostors\' voices that are similar to the target speaker\'s voice. To overcome this limitation, we propose a discriminative feedback adaptation (DFA) framework that reinforces the discriminability between the target speaker model and the antimodel, while preserves the generalization ability of the GMM-UBM approach. This is done by adapting the UBM to a target-speaker-dependent anti-model based on a minimum verification squared-error criterion, rather than estimating from scratch by applying the conventional discriminative training schemes. The results of experiments conducted on the NIST2001-SRE database show that DFA substantially improves the performance of the conventional GMM-UBM approach.
EXPLORING MUTUAL INFORMATION FOR GMM-BASED SPECTRAL CONVERSION
(2012)
Hwang, Hsin-Te
;
Tsao, Yu
;
Wang, Hsin-Min
;
Wang, Yih-Ru
;
Chen, Sin-Horng
In this paper, we propose a maximum mutual information (MMI) training criterion to refine the parameters of the joint density GMM (JDGMM) set to tackle the over-smoothing issue in voice conversion (VC). Conventionally, the maximum likelihood (ML) criterion is used to train a JDGMM set, which characterizes the joint property of the source and target feature vectors. The MMI training criterion, on the other hand, updates the parameters of the JDGMM set to increase its capability on modeling the dependency between the source and target feature vectors, and thus to make the converted sounds closer to the natural ones. The subjective listening test demonstrates that the quality and individuality of the converted speech by the proposed ML followed by MMI (ML+MMI) training method is better that by the ML training method.
Improved methods for characterizing the alternative hypothesis using minimum verification error training for LLR-based speaker verification
(2007)
Chao, Yi-Hsiang
;
Tsai, Wei-Ho
;
Wang, Hsin-Min
;
Chang, Ruei-Chuan
;
資訊工程學系
Speaker verification based on the log-likelihood ratio (LLR) is essentially a task of modeling and testing two hypotheses: the null hypothesis and the alternative hypothesis. Since the alternative hypothesis involves unknown imposters, it is usually hard to characterize a priori. In this paper, we propose a framework to better characterize the alternative hypothesis with the goal of optimally separating client speakers from imposters. The proposed framework is built on either a weighted arithmetic combination or a weighted geometric combination of useful information extracted from a set of pre-trained anti-speaker models. The parameters associated with the combinations are then optimized using Minimum Verification Error training such that both the false acceptance probability and the false rejection probability are minimized. Our experiment results show that the proposed framework outperforms conventional LLR-based approaches.
Improving the characterization of the alternative hypothesis via minimum verification error training with applications to speaker verification
(2009-07-01)
Chao, Yi-Hsiang
;
Tsai, Wei-Ho
;
Wang, Hsin-Min
;
Chang, Ruei-Chuan
;
資訊工程學系
Speaker verification is usually formulated as a statistical hypothesis testing problem and solved by a log-likelihood ratio (LLR) test. A speaker verification system's performance is highly dependent on modeling the target speaker's voice (the null hypothesis) and characterizing non-target speakers' voices (the alternative hypothesis). However, since the alternative hypothesis involves unknown impostors, it is usually difficult to characterize a priori. in this paper, we propose a framework to better characterize the alternative hypothesis with the goal of optimally distinguishing the target speaker from impostors. The proposed framework is built on a weighted arithmetic combination (WAC) or a weighted geometric combination (WGC) of useful information extracted from a set of pre-trained background models. The parameters associated with WAC or WGC are then optimized using two discriminative training methods, namely, the minimum verification error (MVE) training method and the proposed evolutionary, MVE (EMVE) training method, such that both the false acceptance probability and the false rejection probability are minimized. Our experiment results show that the proposed framework Outperforms conventional LLR-based approaches. (C) 2008 Elsevier Ltd. All rights reserved.
Incorporating Global Variance in the Training Phase of GMM-based Voice Conversion
(2013)
Hwang, Hsin-Te
;
Tsao, Yu
;
Wang, Hsin-Min
;
Wang, Yih-Ru
;
Chen, Sin-Horng
Maximum likelihood-based trajectory mapping considering global variance (MLGV-based trajectory mapping) has been proposed for improving the quality of the converted speech of Gaussian mixture model-based voice conversion (GMM-based VC). Although the quality of the converted speech is significantly improved, the computational cost of the online conversion process is also increased because there is no closed form solution for parameter generation in MLGV-based trajectory mapping, and an iterative process is generally required. To reduce the online computational cost, we propose to incorporate GV in the training phase of GMM-based VC. Then, the conversion process can simply adopt ML-based trajectory mapping (without considering GV in the conversion phase), which has a closed form solution. In this way, it is expected that the quality of the converted speech can be improved without increasing the online computational cost. Our experimental results demonstrate that the proposed method yields a significant improvement in the quality of the converted speech comparing to the conventional GMM-based VC method. Meanwhile, comparing to MLGV-based trajectory mapping, the proposed method provides comparable converted speech quality with reduced computational cost in the conversion process.
Locally Linear Embedding Based Post-Filtering for Speech Enhancement
(2018-11-01)
Hwang, Hsin-Te
;
Wu, Yi-Chiao
;
Wang, Syu-Siang
;
Hsu, Chin-Cheng
;
Tsao, Yu
We present a novel speech enhancement method based on locally linear embedding (LLE). The proposed method works as a post-filter to further suppress the residual noises in the enhanced speech signals obtained by a speech enhancement system to attain improved speech quality and intelligibility. We design two types of LLE-based post-filters: the direct LLE-based post-filter (called the DL post-filter) and the LLE-based difference compensation post-filter (called the LDC post-filter). The key technique of the proposed post-filters is to apply the LLE-based feature prediction method, which integrates the LLE algorithm, a classical manifold learning method, with the exemplar-based feature prediction method, to predict either the spectral features of the clean speech from those of the enhanced speech (for DL) or the spectral difference of {clean speech; noisy speech} from that of {enhanced speech; noisy speech} (for LDC). As a result, for DL, the predicted clean speech signals can be directly reconstructed from the predicted clean spectral features. On the other hand, for LDC, the predicted clean spectral features are obtained by compensating the spectral features of the noisy speech with the predicted clean-noisy spectral difference, and then the predicted clean speech signals can be reconstructed accordingly. Experimental results demonstrate the effectiveness of the proposed post-filters for two representative speech enhancement methods, namely the deep denoising autoencoder (DDAE) and the minimum mean-square-error (MMSE) spectral estimation methods.