政府計畫(GRB),建議「依年度遞減排序」,以查看最新的研究方向。
畢業學年度 | 論文標題 | 連結 | 學位 | 畢業時長(years) |
---|---|---|---|---|
關鍵字 | ||||
113 | 日語與中文... 日語與中文的跨語言歌唱口音適應:訓練策略的比較分析 (Cross-lingual Singing Accent Adaptation in Japanese and Mandarin: Comparative Analysis of Training Strategies) | NTHU | 碩 | 暫無口試日期 |
跨語言轉換(Cross-lingual conversion)、歌聲轉換(SInging voice syhthesis)、歌聲合成(SInging voice conversion)、口音轉換(Accent conversion) 跨語言轉換... | ||||
113 | 以古典音樂... 以古典音樂術語為指引生成的鋼琴演奏詮釋 (Piano Performance Rendering Guided by Classical Expressive Markings) | NTHU NDLTD | 碩 | 2.32 |
富有表情的演奏詮釋(Expressive performance rendering)、鋼琴資料集(Piano dataset)、古典音樂(Classical music)、音樂術語(Expressive markings)、音樂資訊檢索(Music Information Retrieval) 富有表情的... | ||||
113 | 將日本流行... 將日本流行歌曲轉換為晶片音樂風格 - 結合音高偵測與矩陣分解之轉換系統設計與實作 (From J-Pop to Chiptune: Design and Implementation of a Conversion System Based on Pitch Detection and Matrix Decomposition) | NTHU NDLTD | 碩 | 2.32 |
曲風轉換(Music style transfer)、非負矩陣分解(Nonnegative Matrix Factorization)、音高偵測(Pitch detection)、峰值偵測(Peak detection) 曲風轉換(... | ||||
113 | 同步壓縮變... 同步壓縮變換與正弦模型對掃頻正弦波所誘發的變頻耳聲傳射之應用 (Application of synchronsqueezing transform and sinusoidal modeling on extracting distortion-product otoacoustic emissions evoked by swept sinusoids) | NTHU NDLTD | 碩 | 3.08 |
變頻耳聲傳射(distortion-product otoacoustic emissions)、同步壓縮變換(synchronsqueezing transform)、正弦模型(sinusoidal modeling)、掃頻正弦波(swept sinusoids) 變頻耳聲傳... | ||||
113 | 代理驅動之... 代理驅動之大語言模型在中文歌詞創作中的實踐 (Agent-Driven Large Language Models for Mandarin Lyric Generation) | NTHU NDLTD | 碩 | 3.08 |
大語言模型(Large Language Model)、人工智慧代理(AI agent)、中文歌詞(Mandarin lyric)、歌詞生成(Lyric generation)、旋律轉歌詞(Melody-to-Lyric)、詞曲咬合(Lyric-melody alignment)、多代理合作(Multi-agent collaboration) 大語言模型... | ||||
113 | 泰雅語電腦... 泰雅語電腦輔助發音訓練系統 (A Computer-assisted Pronunciation Training System for Atayal) | NTHU NDLTD | 碩 | 2.08 |
泰雅語(Atayal)、電腦輔助發音訓練(Computer-assisted pronunciation training)、少數語言建模(Low-resourced language modelling) 泰雅語(A... | ||||
113 | 基於台灣本... 基於台灣本地年長者之語音特徵偵測早期認知功能障礙 (Early Detection for Cognitive Impairment in Taiwanese Elderly People based on Features of Speech) | NTHU NDLTD | 碩 | 2.08 |
輕微認知障礙(mild cognitive impairment)、聲學特徵(acoustic features)、語速(speech rate)、元音空間特徵(vowel space characteristics)、特徵選取(feature selection) 輕微認知障... | ||||
112 | 實現於邊緣... 實現於邊緣裝置之基於深度學習模型之麥克風陣列語音增強系統 (Microphone Array Speech Enhancement on Edge Devices based on Deep Learning) | NTHU NDLTD | 碩 | 2.44 |
語音增強(Speech enhancement)、邊緣運算(Edge computing)、麥克風陣列(Microphone array)、深度學習(Deep learning)、語音處理(Speech processing) 語音增強(... | ||||
112 | 使用漢克爾... 使用漢克爾矩陣奇異值分解對於同步自發性耳聲傳射進行降噪 (Denoising Synchronized Spontaneous Otoacoustic Emission using Hankel Matrix Singular Value Decomposition) | NTHU NDLTD | 碩 | 2.07 |
Hankel 矩陣(Hankel matrix)、奇異值分解(SVD)、最佳化收縮法(optimal shrinkage)、耳聲傳射訊號(otoacoustic emission) Hanke... | ||||
112 | 結合半監督... 結合半監督式學習和領域適應以在多樣化環境中進行聲音事件檢測 (Combining Semi-Supervised Learning and Domain Adaptation for Sound Event Detection in Diverse Environments) | NTHU NDLTD | 碩 | 2.07 |
聲音事件檢測(Sound event detection)、半監督式學習(Semi-supervised learning)、領域自適應(Domain adaptation) 聲音事件檢... | ||||
112 | 以複合音訊... 以複合音訊特徵及叢集分群實現非監督式異音檢測系統 (Unsupervised Anomaly Sound Detection through Composite Audio Features and their Clustering) | NTHU NDLTD | 碩 | 2.07 |
異音檢測(anomaly sound detection)、非監督式學習(unsupervised learning)、叢集分群(clustering) 異音檢測(... | ||||
111 | 應用於中文... 應用於中文語音情緒辨識的聲學特徵萃取 (Acoustic Feature Extraction for Mandarin Speech Emotion Recognition) | NTHU NDLTD | 碩 | 2.74 |
語音情緒辨識(Speech Emotion Recognition)、聲學特徵萃取(Feature Extraction) 語音情緒辨... | ||||
111 | 基於多任務... 基於多任務卷積遞迴神經網路之即時吉他和弦辨識 (Real-time Guitar Chord Recognition Based on Multi-task Convolutional Recurrent Neural Networks) | NTHU NDLTD | 碩 | 2.72 |
和弦辨識(Chord Recognition)、多任務學習(Multi-task Learning)、卷積遞迴神經網路(Convolutional Recurrent Neural Network) 和弦辨識(... | ||||
111 | 基於聲訊之... 基於聲訊之聲帶疾病偵測與分類 (Voice-based detection and classification of vocal cord disorders) | NTHU NDLTD | 碩 | 2.47 |
聲帶疾病(vocal cord disorders)、支援向量機(support vector machine)、卷積神經網路(convolutional neural network)、梅爾頻率倒譜係數(Mel-frequency cepstral coefficients) 聲帶疾病(... | ||||
111 | 以雙耳錄音... 以雙耳錄音偵測電動機車 (Detecting Electric Motorcycles by Binaural Recordings) | NTHU NDLTD | 碩 | 2.47 |
雙耳線索(binaural cue)、電動機車(electric motorcycle)、隨機森林(random forest)、聲音定位(sound localization)、雙耳時間差(interaural time difference)、雙耳聲強差(interaural level difference) 雙耳線索(... | ||||
111 | 基於馬可夫... 基於馬可夫鏈與音樂理論之互動式藍調吉他呼喊與回應即興系統 (An Interactive Call and Response Blues Guitar Jamming System based on Markov Chain and Music Theory) | NTHU NDLTD | 碩 | 3.16 |
馬可夫鍊(Markov chain)、藍調(Blues)、吉他(guitar)、呼喊與回應(call and response)、即興(improvisation)、互動系統(jamming) 馬可夫鍊(... | ||||
111 | 利用神經正... 利用神經正切泛化攻擊以防禦聲音驗證碼 (Defending an Audio CAPTCHA system by Neural Tangent Generalization Attack) | NTHU NDLTD | 碩 | 3.42 |
聲音驗證碼(Audio CAPTCHA)、對抗式機器學習(Adversarial machine learning)、神經正切核(Neural tangent kernel)、泛化攻擊(Generalization attack) 聲音驗證碼... | ||||
111 | 口語講座文... 口語講座文本之自動生成:“紅樓夢” 系列 (Toward Automatic Generation of Transcript from Spoken Lectures: the “Dream of the Red Chamber” Series) | NTHU NDLTD | 碩 | 2.33 |
語音辨識(Speech recognition)、自動轉錄(Automatic transcription)、遷移學習(Transfer learning)、講座語料(Lecture corpus)、紅樓夢文學(Dream of the Red Chamber) 語音辨識(... | ||||
111 | 一個單詞級... 一個單詞級別的中文聽視覺語音辨識系統 (A Word-level Mandarin Audio-visual Speech Recognition System) | NTHU NDLTD | 碩 | 2.33 |
深度神經網路(Deep-neural-network)、聽視覺(Audio-visual)、語音辨識(Speech-recognition) 深度神經網... | ||||
111 | 個人完全存... 個人完全存在觀點: 現實與夢境虛實比較之藝術創作 (Personal Complete-existence Assumption:Real-Virtual Comparison Art of Reality and Dream) | NTHU NDLTD | 碩(提早入學) | 2.81 |
科技藝術(Existentialism)、擴增實境(Tech Art)、存在主義(Augmented Reality)、存在(Dream)、夢境(Existence) 科技藝術(... | ||||
111 | 基於降噪擴... 基於降噪擴散 Wasserstein 對抗式神經網路之中文歌聲合成 (Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GAN) | NTHU NDLTD | 碩 | 2.05 |
深度神經網路(deep neural network)、對抗式神經網路(Wasserstein generative adversarial network)、降噪擴散機率模型(denoising diffusion probabilistic model)、歌聲合成(singing voice synthesis) 深度神經網... | ||||
109 | 通過逐點偽... 通過逐點偽影去除法進行瞬態誘發耳聲傳射及其群延遲在高訊噪比頻段之估算 (A point-wise artifact rejection method for estimating transient-evoked otoacoustic emissions and their group delay from frequency bands with high SNR) | NTHU NDLTD | 碩 | 2.24 |
瞬態誘發耳聲傳射(transient-evoked otoacoustic emissions)、偽影去除法(artifact rejection)、群延遲(group delay)、梅尼爾氏症(Meniere’s disease)、雜訊分布(noise distribution) 瞬態誘發耳... | ||||
109 | 基於自適應... 基於自適應一維沃爾泰拉濾波以單一揚聲器測量人耳之變頻耳聲傳射 (Measuring Distortion Product Otoacoustic Emissions with a Single Speaker in the Ear Based on Adaptive One-Dimensional Volterra Filtering) | NTHU NDLTD | 碩 | 2.23 |
耳聲傳射(otoacoustic emissions)、交互調變失真(intermodulation distortion)、非線性訊號處理(nonlinear signal processing)、沃爾泰拉濾波(Volterra filtering) 耳聲傳射(... | ||||
109 | 基於音韻學... 基於音韻學的時長模型之中文歌聲合成 (Mandarin Singing Voice Synthesis with a Phonology-based Duration Model) | NTHU NDLTD | 碩 | 2.22 |
歌聲合成(singing voice synthesis)、時長模型(duration model)、中文音韻學(Mandarin phonology) 歌聲合成(... | ||||
109 | 基於實例查... 基於實例查詢演算法之聲音檢索輔助標注工具 (An Assistant Annotation Tool for Audio Retrieval based on Query by Example) | NTHU NDLTD | 碩 | 2.96 |
聲音檢索(Audio Fingerprinting)、實例查詢(Audio Retrieval)、聲音指紋(Query-by-example)、資料標註(Data Annotation) 聲音檢索(... | ||||
109 | 弱監督聲音... 弱監督聲音事件偵測模型訓練策略 (Weakly Supervised Sound Event Detection Model Training Strategies) | NTHU NDLTD | 碩 | 1.96 |
聲音事件辨識(Sound event detection)、弱監督式學習(Weakly supervised learning)、半監督式學習(Semi-supervised learning)、領域自適應(Domain adaptation) 聲音事件辨... | ||||
109 | 使用最佳化... 使用最佳化收縮估計法與時頻濾波器進行暫態音誘發性耳聲傳射訊號之降噪 (Denoising Click-Evoked Otoacoustic Emissions by Optimal Shrinkage and Time-Frequency Filtering) | NTHU NDLTD | 碩逕博 | 7.94 |
耳聲傳射(otoacoustic emissions)、矩陣降噪(matrix denoising)、最佳化收縮估計法(optimal shrinkage)、時頻濾波器(time-frequency filtering) 耳聲傳射(... | ||||
109 | 不同發音方... 不同發音方式所測得之電聲門圖與音訊綜合比較與分析 (Joint comparison and analysis of EGG and audio signals measured during different types of phonation) | NTHU NDLTD | 碩 | 2.50 |
電聲門圖(Electroglottography)、聲門逆濾波(Glottal inverse filtering)、聲門氣流(Glottal flow)、發聲方式(Phonation type) 電聲門圖(... | ||||
109 | 非同步學習... 非同步學習「過渡」及「延音」以改善中文歌聲合成之基頻軌跡 (Improving the Fundamental Frequency (F0) Trajectories in Mandarin Singing Voice Synthesis by Asynchronously Learning the Transition and Sustain) | NTHU NDLTD | 碩 | 2.34 |
歌聲合成(singing voice synthesis)、神經網路(neural network)、深度學習(deep learning) 歌聲合成(... | ||||
109 | 以消除耳機... 以消除耳機交互調變失真的方法測量人耳之變頻耳聲傳射 (Measuring Distortion Product Otoacoustic Emissions in Human Ears Based on an Earphone Intermodulation Distortion Cancellation Method) | NTHU NDLTD | 碩 | 2.19 |
耳聲傳射(Otoacoustic emission)、交互調變失真(intermodulation distortion) 耳聲傳射(... | ||||
109 | 基於心理聲... 基於心理聲學之聲音驗證碼及其背後之攻防 (Attacking and Defending behind a Psychoacoustics-based Audio CAPTCHA) | NTHU NDLTD | 碩 | 2.08 |
聽覺驗證碼(audio CAPTCHA)、心理聲學(Psychoacoustics)、聲音浮水印(watermarks)、使用者介面(user interface)、聲音事件偵測(sound event detection)、後門(backdoor) 聽覺驗證碼... | ||||
108 | 透過Wor... 透過World vocoder進行中文語音至歌聲之自動轉換 (Automatic Mandarin Speech-to-singing conversion via the World vocoder) | NTHU NDLTD | 碩 | 2.23 |
語音至歌聲轉換(speech-to-singing conversion)、中文(Mandarin)、World vocoder(World vocoder) 語音至歌聲... | ||||
108 | 針對女性頭... 針對女性頭聲、混偏頭聲、混偏胸聲、胸聲區音聲的分析與分類 (Analysis and Classification of Female Voices in Head, Headmix, Chestmix, and Chest Register) | NTHU NDLTD | 碩 | 2.23 |
女性音聲(Female Voices)、聲區(Vocal Registers)、頻譜分析(Spectral Analysis)、頭聲區(Head Register)、混偏頭聲區(Headmix Register)、混偏胸聲區(Chestmix Register)、胸聲區(Chest Register)、支援向量機(Support Vector Machines)、多層感知器(Multi-layer Perceptron)、分類(Classification) 女性音聲(... | ||||
108 | 基於雙向時... 基於雙向時間遞歸神經網路之中文歌聲合成 (Mandarin Singing Voice Synthesis Based on Bidirectional LSTM Recurrent Neural Networks) | NTHU NDLTD | 碩 | 2.19 |
歌聲合成(Singing voice synthesis)、歌聲資料庫(Singing voice database)、聲調語言(Tone language) 歌聲合成(... | ||||
108 | 綜合考量音... 綜合考量音色及音樂表情控制之歌聲轉換 (Singing voice conversion by joint consideration of timbre and expressive control) | NTHU NDLTD | 碩 | 2.16 |
歌聲轉換(Singing voice conversion)、韻律(Prosody)、情感(Expression) 歌聲轉換(... | ||||
108 | 基於共振峰... 基於共振峰迭代濾波的歌聲轉換 (Singing Voice Conversion based on Iterative Formant Filtering) | NTHU NDLTD | 碩 | 2.05 |
共振峰濾波(Formant Filtering)、歌聲合成(Singing Synthesis) 共振峰濾波... | ||||
108 | 結合物理模... 結合物理模型與卷積神經網路之小號聲音合成 (Trumpet Sound Synthesis by Collaboration between a Physical model and a Convolutional Neural Network) | NTHU NDLTD | 碩 | 2.05 |
聲音合成(Sound Synthesis)、聲學物理(Acoustical Physics)、物理模型模擬(Physical Modeling Simulation)、類神經網路(Neural Network)、補償系統(Compensating System)、深度學習(Deep Learning) 聲音合成(... | ||||
107 | 利用遮蔽效... 利用遮蔽效應結合抖動技術以提升音訊在頻域量化後之聽感動態 (Combining the Masking Effect and Dithering Techniques to Enhance Auditory Dynamics of Quantized Audio Signals in the Frequency Domain) | NTHU NDLTD | 碩 | 2.20 |
抖動(dithering)、量化(quantize)、遮蔽效應(masking) 抖動(di... | ||||
107 | 台灣小學生... 台灣小學生英語單字發音自動評量系統方法之開發 (Development of Automatic Evaluation Systems on Taiwanese Elementary School Students’ English Pronunciation) | NTHU NDLTD | 碩 | 2.20 |
語音評分(speech assessment)、共振峰曲線(pronunciation scoring)、支持向量機(Mel-Frequency Cepstral Coefficients)、發音評分(Speech Evaluation)、梅爾倒頻譜參數(computer assisted language learning) 語音評分(... | ||||
107 | 基於語音特... 基於語音特徵判斷語句內容真實性 (Determining the authenticity of speech content via analyzing the voice characteristics) | NTHU NDLTD | 碩 | 2.20 |
測謊(deception)、決策樹(speech)、語音特徵(decision tree) 測謊(de... | ||||
107 | 基於分離自... 基於分離自動編碼器及卷積遞歸神經網路之聲音事件偵測 (Sound Event Detection Based on Partitioned Autoencoder and Convolutional Recurrent Neural Network) | NTHU NDLTD | 碩 | 3.18 |
聲音事件偵測(Sound Event Detection)、分離自動編碼器(Partitioned Autoencoder)、卷積遞歸神經網路(Convolutional Recurrent Neural Network) 聲音事件偵... | ||||
107 | 頻域上之聲... 頻域上之聲源分離: 利用滑動k-平均演算法解決排列問題 (Source Separation in the Frequency Domain: Solving the Permutation Problem by a Sliding K-means Method) | NTHU NDLTD | 碩 | 2.18 |
獨立成分分析(independent)、膨脹問題(component)、排列問題(analysis) 獨立成分分... | ||||
107 | 基於瞬態誘... 基於瞬態誘發耳聲傳射與同步自發性耳聲傳射特徵之身份辨識 (Person Identification Based on features of Transient Evoked Otoacoustic Emission and Synchronized Spontaneous Otoacoustic Emission) | NTHU NDLTD | 碩 | 2.10 |
瞬態誘發耳聲傳射(Person)、同步自發性耳聲傳射(Identification)、身份辨識(Transient) 瞬態誘發耳... | ||||
106 | 利用功能性... 利用功能性近紅外線光譜及獨立成分分析演算法來評估更新作業的活化腦區 (Using Independent Component Analysis Algorithm to Evaluate Activated Brain Regions in Updating Task by Functional Near-Infrared Spectroscopy) | NTHU NDLTD | 碩 | 1.98 |
功能性近紅外線光譜(functional near-infrared spectroscopy)、前額葉(prefrontal cortex)、工作記憶(working memory)、快速獨立成分分析(fast independent components analysis) 功能性近紅... | ||||
106 | 多對麥克風... 多對麥克風於殘響房間之聲源定位 (Source Localization in a Reverberant Room via Multiple Pairs of Microphones) | NTHU NDLTD | 碩 | 2.98 |
聲源定位(sound source localization)、抵達時間差(time difference of arrival)、殘響(reverberation)、多通道音頻訊號處理(multichannel audio processing)、最大似然估計(maximum likelihood) 聲源定位(... | ||||
106 | 梅尼爾氏症... 梅尼爾氏症患者瞬態誘發耳聲傳射之訊號分析 (Signal analysis of transient evoked otoacoustic emissions from Meniere's disease patients) | NTHU NDLTD | 碩 | 2.49 |
瞬態誘發耳聲傳射(Transient Evoked Otoacoustic Emission)、梅尼爾氏症(TEOAE) 瞬態誘發耳... | ||||
106 | 基於局部線... 基於局部線性嵌入語音轉換的快速演算法與改良 (Fast Algorithm and Quality Improvement for Locally Linear Embedding based Voice Conversion) | NTHU NDLTD | 碩 | 2.49 |
語音轉換(Voice Conversion)、局部線性嵌入演算法(Locally Linear Embedding Algorithm)、快速演算法(Fast Algorithm)、音質改良(Quality Improvement) 語音轉換(... | ||||
105 | 自動樂器家... 自動樂器家族分類 (Music Instrument Family Classification) | NTHU NDLTD | 碩 | 暫無口試日期 |
音樂訊號處理(music signal processing)、機器學習(machine learning)、音色分類(timbre classification) 音樂訊號處... | ||||
105 | 基於RBM... 基於RBM模型以非監督式學習歸納環境中的聲響 (Unsupervised sound summarization from an environment based on the Restricted Boltzmann Machine) | NTHU NDLTD | 碩 | 暫無口試日期 |
聲響歸納(RBM)、非監督式(Unsupervised learning) 聲響歸納(... | ||||
105 | 基於調制頻... 基於調制頻譜向量之環境聲響事件分類 (Environmental Sound Event Classification Based on Modulation Spectral Vectors) | NTHU NDLTD | 碩 | 3.99 |
調制頻譜向量(modulation spectral vectors)、噪音訓練(noisy training)、環境聲響事件(environment sound event)、高斯混合模型(gmm) 調制頻譜向... | ||||
105 | 聲音事件偵... 聲音事件偵測之特徵萃取與分類方法之測試 (Sound Event Detection Using Different Feature Extraction and Multi-label Classification Methods) | NTHU NDLTD | 碩 | 2.46 |
聲音事件偵測(Sound Event Detection) 聲音事件偵... | ||||
105 | 頻域上雙聲... 頻域上雙聲道聲源分離方法:運算簡化以及音質改進之做法 (Source Separation in Frequency Domain: Computation Cost Reduction and Sound Quality Enhancement) | NTHU NDLTD | 碩 | 2.46 |
聲源分離(source separation)、獨立成分分析(ICA)、排列問題(scaling problem)、膨脹問題(permutation problem) 聲源分離(... | ||||
105 | 瞬態誘發耳... 瞬態誘發耳聲傳射測量系統實作與測試 (Implementation and Testing of a Transient Evoked Otoacoustic Emission Measurement System) | NTHU NDLTD | 碩 | 2.38 |
瞬態誘發耳聲傳射(Transient Evoked Otoacoustic Emission) 瞬態誘發耳... | ||||
104 | 基於聲音辨... 基於聲音辨識特徵之聲音重建 (Sound reconstruction based on features for sound recognition) | NTHU NDLTD | 碩 | 暫無口試日期 |
聲音重建(sound reconstruction)、聲音辨認(sound recognition)、梅爾(mel) 聲音重建(... | ||||
104 | 基於稀疏表... 基於稀疏表示之電子鼻混合氣味辨識之研究 (Sparse Representation Based Mixed Odor Recognition by an Electric Nose) | NTHU NDLTD | 碩 | 暫無口試日期 |
電子鼻(Electronic Nose)、混合氣味(Mixed Odor)、稀疏表示法(Sparse Representation)、最近鄰居分類器(K-nearest neighbor classifier)、多類別辨識方法(Multi-Class Classification)、多標籤辨識方法(Multi-Label Classification) 電子鼻(E... | ||||
104 | 運用多個聯... 運用多個聯網麥克風進行室內環境語音與音樂之增強:波束成形方法開發與評估 (Acoustic Enhancement of Music and Speech in an Indoor Space using Multiple Networked Microphones: Development and Evaluation of Beamforming Methods) | NTHU NDLTD | 碩 | 暫無口試日期 |
聲學(Acoustic)、增強(Enhancement) 聲學(Ac... | ||||
104 | 自動樂譜辨... 自動樂譜辨識 (Automatic Music Score Recognition) | NTHU NDLTD | 碩 | 暫無口試日期 |
模型識別(Pattern Recognition)、圖像處理(Image Processing)、音樂科技(Music Technology)、光學音樂辨識(Optical Music Recognition) 模型識別(... | ||||
103 | 基於頻域訊... 基於頻域訊噪比機率模型之聲源來向估計 (A Probabilistic Model for Sound Direction of Arrival Estimation Based on Signal-to-noise Ratios in the Frequency Domain) | NTHU NDLTD | 碩 | 暫無口試日期 |
聲源定位(Sound Source Localization)、相位差(Phase Difference)、抵達時間差(Time Difference of Arrival) 聲源定位(... | ||||
103 | 從語音訊號... 從語音訊號估計發聲狀態下之口鼻腔截面積 (Estimation of oral cavity and nasal cavity cross-section areas from speech signals during articulation) | NTHU NDLTD | 碩 | 暫無口試日期 |
線性預估(linear prediction)、逆散射(inverse scattering)、分析格狀架構(analysis lattice structure) 線性預估(... | ||||
103 | 模擬內側橄... 模擬內側橄欖耳蝸之遮蔽與去遮蔽效應 (Simulating Masking and Anti-masking Effects of the Medial Olivocochlear Efferent Reflex) | NTHU NDLTD | 碩 | 暫無口試日期 |
聽覺系統(auditory system)、遮蔽效應(masking)、去遮蔽效應(anti-masking)、內側橄欖耳蝸核(medial olivocochlea)、垂直細胞(tuberculoventral cell) 聽覺系統(... | ||||
103 | 以語音估測... 以語音估測從喉閃頻影像所得之聲門參數 (Prediction of Glottal Parameters Obtained from Stroboscopic Images Using Voice Recordings) | NTHU NDLTD | 碩 | 暫無口試日期 |
喉閃頻、聲門參數 喉閃頻、聲... | ||||
103 | 利用多標籤... 利用多標籤分類器實現電子鼻混合氣體識別方法之研究 (Multi-label Classification for Mixed Odor Recognition using an Electronic Nose System) | NTHU NDLTD | 碩 | 暫無口試日期 |
電子鼻(Electronic Nose)、多標籤分類(Multi-label Classification)、混合氣體(Mixed Odor)、特徵萃取(Feature Extraction)、多變量分析(Multivariate Analysis) 電子鼻(E... | ||||
103 | 利用機器學... 利用機器學習方法分析電子氣體感測資料以鑑別慢性肺阻塞與氣喘患者 (Discrimination of Patients with Chronic Obstructive Pulmonary Disease and Bronchial Asthma by Applying Machine Learning Methods to analyze Electronic Gas-Sensing Data) | NTHU NDLTD | 碩 | 暫無口試日期 |
機器學習方法(Machine Learning Methods)、氣體感測(Electronic Gas-Sensing)、慢性肺阻塞(Chronic Obstructive Pulmonary Disease)、氣喘(Bronchial Asthma) 機器學習方... | ||||
103 | 基於頻率間... 基於頻率間包絡之相關性解決頻域上聲源分離之排列問題 (Solving the Permutation Problem in Frequency Domain Source Separation Based on the Correlation of Envelopes between Frequencies) | NTHU NDLTD | 碩 | 暫無口試日期 |
聲源分離(Sound source separation)、獨立成份分析(Independent component analysis)、排列問題(Permutation problem) 聲源分離(... | ||||
102 | 基於支持向... 基於支持向量機之混合聲響辨認 (Methods for Recognizing Concurrent Sounds Based on Support Vector Machines) | NTHU NDLTD | 碩 | 暫無口試日期 |
聲響辨認、支持向量機 聲響辨認、... | ||||
101 | 利用視訊與... 利用視訊與聲訊雙重處理進行說話者位置偵測 (Detection of the location of talkers via video and audio bimodal processing) | NTHU NDLTD | 碩 | 暫無口試日期 |
到達時間差(TDOA)、聲源追蹤(source detection)、人臉偵測(face detection)、人臉辨識(face recognition)、聲訊(audio)、視訊(video) 到達時間差... | ||||
101 | 以線性預估... 以線性預估法回推聲源進行帶脂肪注射手術之成效評估 (Acoustic inverse scattering by linear prediction methods of patients treated by lipoinjection thyroplasty: effectiveness of the operation) | NTHU NDLTD | 碩 | 暫無口試日期 |
線性預估分析、聲帶脂肪注射 線性預估分... | ||||
101 | 基於多重訊... 基於多重訊號分類演算法之即時平面聲源定位系統 (Real-time Two-Dimensional Sound Source Localization Based on the Multiple Signal Classification Algorithm) | NTHU NDLTD | 碩 | 暫無口試日期 |
聲源定位(sound source localization)、聲源追蹤(source tracking)、粒子定位法(particle localization method)、卡爾曼濾波器(Kalman filter)、粒子濾波器(particle filter) 聲源定位(... | ||||
101 | 以quas... 以quasi-linear法建立頻域內耳聽覺生理模型 (Establishing an auditory model of the inner ear in the frequency domain by quasi-linear methods) | NTHU NDLTD | 碩 | 暫無口試日期 |
耳蝸(cochlea)、時域模型(quasi-linear)、頻域模型(FDM)、電流敏感度常數(TDM)、外毛細胞(sensitivity ratio) 耳蝸(co... | ||||
101 | 利用樣式識... 利用樣式識別實現電子鼻肺炎偵測 (Pattern Recognition Approaches for Pneumonia Detection by an Electronic Nose) | NTHU NDLTD | 碩 | 暫無口試日期 |
電子鼻(Electronic Nose)、特徵選擇(Feature Selection)、肺炎(Pneumonia)、樣式識別(Pattern Recognition) 電子鼻(E... |