Jeih-weih Hung

128 papers A 17C 3Misc 8Journal 35Unranked 65

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Design and Implementation of an Autonomous Mobile Robot for Object Delivery via Homography-Based Visual Servoing. Future Internet Jung-Shan Lin, Yen-Che Hsiao, Jeih-weih Hung
2025	A	`conf`	Flexible VAD-PVAD Transition: A Detachable PVAD Module for Dynamic Encoder RNN VAD. INTERSPEECH En-Lun Yu, Chien-Chun Wang, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen
2025	—	`conf`	Lightweight Zero-Shot Keyword Spotting via Multi-Granular Knowledge Distillation. APSIPA Yun-Ting Sun, Lo-Ya Li, Tien-Hong Lo, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen
2025	C	`conf`	SincQDR-VAD: A Noise-Robust Voice Activity Detection Framework Leveraging Learnable Filters and Ranking-Aware Optimization. ASRU Chien-Chun Wang, En-Lun Yu, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen
2025	J	`jnl`	SincQDR-VAD: A Noise-Robust Voice Activity Detection Framework Leveraging Learnable Filters and Ranking-Aware Optimization. CoRR Chien-Chun Wang, En-Lun Yu, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen
2024	—	`conf`	COIN-AT-PVAD: A Conditional Intermediate Attention PVAD. APSIPA En-Lun Yu, Ruei-Xian Chang, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen
2024	J	`jnl`	ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning. CoRR Kuan-Hsun Ho, Jeih-weih Hung, Berlin Chen
2024	J	`jnl`	Effective Monoaural Speech Separation through Convolutional Top-Down Multi-View Network. Future Internet Aye Nyein Aung, Che-Wei Liao, Jeih-weih Hung
2024	J	`jnl`	Employing Huber and TAP Losses to Improve Inter-SubNet in Speech Enhancement. Future Internet Jeih-weih Hung, Pin-Chen Huang, Li-Yin Li
2024	—	`conf`	Few-Shot Open-Set Keyword Spotting with Multi-Stage Training. APSIPA Lo-Ya Li, Tien-Hong Lo, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen
2024	—	`conf`	GLASS: Investigating Global and Local context Awareness in Speech Separation. APSIPA Kuan-Hsun Ho, En-Lun Yu, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen
2024	—	`conf`	Leveraging the NOMAD and Intelligibility Loss to Improve MP-SENet for Speech Enhancement. ICCE-Taiwan Yi-Zhen Li, Chung-Wei Chang, Mu-Chin Li, Eric S. Li, Jeih-weih Hung
2024	A	`conf`	Speaker Conditional Sinc-Extractor for Personal VAD. INTERSPEECH En-Lun Yu, Kuan-Hsun Ho, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen
2024	Misc	`conf`	What Do Neural Networks Listen to? Exploring the Crucial Bands in Speech Enhancement Using SINC-Convolution. ICASSP Kuan-Hsun Ho, Jeih-weih Hung, Berlin Chen
2024	J	`jnl`	What do neural networks listen to? Exploring the crucial bands in Speech Enhancement using Sinc-convolution. CoRR Kuan-Hsun Ho, Jeih-weih Hung, Berlin Chen
2023	—	`conf`	ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning. DSP Kuan-Hsun Ho, Jeih-weih Hung, Berlin Chen
2023	—	`conf`	Exploiting Discrete Wavelet Transform Features in Speech Enhancement Technique Adaptive FullSubNet+. ICCE-Taiwan Zong-Tai Wu, Pei-Fang Li, Ping-Chen Wu, Eric S. Li, Jeih-weih Hung
2023	J	`jnl`	Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information. IEEE ACM Trans. Audio Speech Lang. Process. Yen-Ju Lu, Chia-Yu Chang, Cheng Yu, Ching-Feng Liu, Jeih-weih Hung, Shinji Watanabe, Yu Tsao
2023	—	`conf`	Improving the performance of CMGAN in speech enhancement with the phone fortified perceptual loss. ICCE-Taiwan Chi-En Dai, Jia-Xuan Zeng, Wan-Ling Zeng, Eric S. Li, Jeih-weih Hung
2023	—	`conf`	NAaLOSS: Rethinking the Objective of Speech Enhancement. MLSP Kuan-Hsun Ho, En-Lun Yu, Jeih-weih Hung, Berlin Chen
2023	J	`jnl`	Naaloss: Rethinking the objective of speech enhancement. CoRR Kuan-Hsun Ho, En-Lun Yu, Jeih-weih Hung, Berlin Chen
2022	—	`conf`	A Preliminary Study of Employing Lowpass-Filtered and Time-Reversed Feature Sequences as Data Augmentation for Speech Enhancement Deep Networks. ISPACS Che-Wei Liao, Ping-Chen Wu, Jeih-weih Hung
2022	—	`conf`	A Preliminary Study of the Application of Discrete Wavelet Transform Features in Conv-TasNet Speech Enhancement Model. ROCLING Yan-Tong Chen, Zong-Tai Wu, Jeih-weih Hung
2022	—	`conf`	Adaptive-FSN: Integrating Full-Band Extraction and Adaptive Sub-Band Encoding for Monaural Speech Enhancement. SLT Yu-Sheng Tsao, Kuan-Hsun Ho, Jeih-weih Hung, Berlin Chen
2022	—	`conf`	Bi-Sep: A Multi-Resolution Cross-Domain Monaural Speech Separation Framework. TAAI Kuan-Hsun Ho, Jeih-weih Hung, Berlin Chen
2022	—	`conf`	Exploiting the compressed spectral loss for the learning of the DEMUCS speech enhancement network. ROCLING Chi-En Dai, Qi-Wei Hong, Jeih-weih Hung
2022	—	`conf`	Improving the performance of DEMUCS in speech enhancement with the perceptual metric loss. ICCE-TW Zong-Tai Wu, Yan-Tong Chen, Jeih-weih Hung
2022	J	`jnl`	Time-Reversal Enhancement Network With Cross-Domain Information for Noise-Robust Speech Recognition. IEEE Multim. Fu-An Chao, Jeih-weih Hung, Tommy Sheu, Berlin Chen
2021	A	`conf`	Cross-Domain Single-Channel Speech Enhancement Model with BI-Projection Fusion Module for Noise-Robust ASR. ICME Fu-An Chao, Jeih-weih Hung, Berlin Chen
2021	J	`jnl`	Cross-domain Single-channel Speech Enhancement Model with Bi-projection Fusion Module for Noise-robust ASR. CoRR Fu-An Chao, Jeih-weih Hung, Berlin Chen
2021	—	`conf`	Employing low-pass filtered temporal speech features for the training of ideal ratio mask in speech enhancement. ROCLING Yan-Tong Chen, Zi-Qiang Lin, Jeih-weih Hung
2021	C	`conf`	TENET: A Time-Reversal Enhancement Network for Noise-Robust ASR. ASRU Fu-An Chao, Shao-Wei Fan-Jiang, Bi-Cheng Yan, Jeih-weih Hung, Berlin Chen
2021	J	`jnl`	TENET: A Time-reversal Enhancement Network for Noise-robust ASR. CoRR Fu-An Chao, Shao-Wei Fan-Jiang, Bi-Cheng Yan, Jeih-weih Hung, Berlin Chen
2021	—	`conf`	The effect of reducing the acoustic-frequency resolution for spectrograms used in deep denoising auto-encoder. ICCE-TW Yan-Tong Chen, Shu-Ting Tsai, Jeih-weih Hung
2020	—	`conf`	Exponentiated magnitude spectrogram-based relative-to-maximum masking for speech enhancement in adverse environments. ICCE-TW Chen-Li Lin, Zi-Qiang Lin, Syu-Siang Wang, Yu Tsao, Jeih-weih Hung
2020	A	`conf`	Incorporating Broad Phonetic Information for Speech Enhancement. INTERSPEECH Yen-Ju Lu, Chien-Feng Liao, Xugang Lu, Jeih-weih Hung, Yu Tsao
2020	J	`jnl`	Incorporating Broad Phonetic Information for Speech Enhancement. CoRR Yen-Ju Lu, Chien-Feng Liao, Xugang Lu, Jeih-weih Hung, Yu Tsao
2020	—	`conf`	Lowpass-filtered relative-to-maximum masking for speech enhancement in noise-corrupted environments. ICCE-TW Zi-Qiang Lin, Chen-Li Lin, Jeih-weih Hung
2020	—	`conf`	Multi-view Attention-based Speech Enhancement Model for Noise-robust Automatic Speech Recognition. ROCLING Fu-An Chao, Jeih-weih Hung, Berlin Chen
2020	J	`jnl`	Speech enhancement guided by contextual articulatory information. CoRR Yen-Ju Lu, Chia-Yu Chang, Yu Tsao, Jeih-weih Hung
2020	—	`conf`	The preliminary study of robust speech feature extraction based on maximizing the accuracy of states in deep acoustic models. ROCLING Li-chia Chang, Jeih-weih Hung
2020	J	`jnl`	Time-Domain Multi-Modal Bone/Air Conducted Speech Enhancement. IEEE Signal Process. Lett. Cheng Yu, Kuo-Hsuan Hung, Syu-Siang Wang, Yu Tsao, Jeih-weih Hung
2019	—	`conf`	An evaluation study of modulation-domain wavelet denoising method by alleviating different sub-band portions for speech enhancement. ICCE-TW Jian-Yu Lin, Yan-Tong Chen, Kuan-Yi Liu, Jeih-weih Hung
2019	J	`jnl`	Distributed Microphone Speech Enhancement based on Deep Learning. CoRR Syu-Siang Wang, Yu-You Liang, Jeih-weih Hung, Yu Tsao, Hsin-Min Wang, Shih-Hau Fang
2019	—	`conf`	Smoothing the acoustic spectral time series of speech signals for noise reduction. ICCE-TW Yan-Tong Chen, Jian-Yu Lin, Kuan-Yi Liu, Jeih-weih Hung
2019	A	`conf`	Speaker-Aware Deep Denoising Autoencoder with Embedded Speaker Identity for Speech Enhancement. INTERSPEECH Fu-Kai Chuang, Syu-Siang Wang, Jeih-weih Hung, Yu Tsao, Shih-Hau Fang
2019	—	`conf`	Speech enhancement based on the integration of fully convolutional network, temporal lowpass filtering and spectrogram masking. ROCLING Kuan-Yi Liu, Syu-Siang Wang, Yu Tsao, Jeih-weih Hung
2019	J	`jnl`	Time-Domain Multi-modal Bone/air Conducted Speech Enhancement. CoRR Cheng Yu, Yan-Ting Lin, Kuo-Hsuan Hung, Syu-Siang Wang, Szu-Wei Fu, Yu Tsao, Jeih-weih Hung
2018	J	`jnl`	Speech Enhancement Based on Reducing the Detail Portion of Speech Spectrograms in Modulation Domain via Discrete Wavelet Transform. CoRR Shih-Kuang Lee, Syu-Siang Wang, Yu Tsao, Jeih-weih Hung
2018	—	`conf`	Speech Enhancement Based on Reducing the Detail Portion of Speech Spectrograms in Modulation Domain via DiscreteWavelet Transform. ISCSLP Shih-Kuang Lee, Syu-Siang Wang, Yu Tsao, Jeih-weih Hung
2018	J	`jnl`	Suppression by Selecting Wavelets for Feature Compression in Distributed Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. Syu-Siang Wang, Payton Lin, Yu Tsao, Jeih-weih Hung, Borching Su
2017	A	`conf`	Wavelet Speech Enhancement Based on Robust Principal Component Analysis. INTERSPEECH Chia-Lung Wu, Hsiang-Ping Hsu, Syu-Siang Wang, Jeih-weih Hung, Ying-Hui Lai, Hsin-Min Wang, Yu Tsao
2017	—	`conf`	多樣訊雜比之訓練語料於降噪自動編碼器其語音強化功能之初步研究 (A Preliminary Study of Various SNR-level Training Data in the Denoising Auto-encoder (DAE) Technique for Speech Enhancement) [In Chinese]. ROCLING Shih-Kuang Lee, Syu-Siang Wang, Yu Tsao, Jeih-weih Hung
2016	—	`conf`	Employing median filtering to enhance the complex-valued acoustic spectrograms in modulation domain for noise-robust speech recognition. ISCSLP Hsin-Ju Hsieh, Berlin Chen, Jeih-weih Hung
2016	—	`conf`	Leveraging nonnegative matrix factorization in processing the temporal modulation spectrum for speech enhancement. ICCE-TW Syu-Siang Wang, Jeremy Chiaming Yang, Yu Tsao, Jeih-weih Hung
2016	—	`conf`	Linear prediction filtering on cepstral time series for noise-robust speech recognition. ICCE-TW Hsin-Ju Hsieh, Jhih-Hao Jheng, Jung-Shan Lin, Jeih-weih Hung
2016	J	`jnl`	Robust Speech Recognition via Enhancing the Complex-Valued Acoustic Spectrum in Modulation Domain. IEEE ACM Trans. Audio Speech Lang. Process. Jeih-weih Hung, Hsin-Ju Hsieh, Berlin Chen
2016	—	`conf`	Speech enhancement via ensemble modeling NMF adaptation. ICCE-TW Jeremy Chiaming Yang, Syu-Siang Wang, Yu Tsao, Jeih-weih Hung
2016	J	`jnl`	Wavelet Speech Enhancement Based on Nonnegative Matrix Factorization. IEEE Signal Process. Lett. Syu-Siang Wang, Alan Chern, Yu Tsao, Jeih-weih Hung, Xugang Lu, Ying-Hui Lai, Borching Su
2016	J	`jnl`	Wavelet speech enhancement based on nonnegative matrix factorization. CoRR Syu-Siang Wang, Alan Chern, Yu Tsao, Jeih-weih Hung, Xugang Lu, Ying-Hui Lai, Borching Su
2015	—	`conf`	Enhancing the complex-valued acoustic spectrograms in modulation domain for creating noise-robust features in speech recognition. APSIPA Hsin-Ju Hsieh, Berlin Chen, Jeih-weih Hung
2015	J	`jnl`	Histogram equalization of contextual statistics of speech features for robust speech recognition. Multim. Tools Appl. Hsin-Ju Hsieh, Berlin Chen, Jeih-weih Hung
2015	—	`conf`	Magnitude replacement of real and imaginary modulation spectrum of acoustic spectrograms for noise-robust speech recognition. ICCE-TW Hsin-Ju Hsieh, Jeih-weih Hung
2014	—	`conf`	Leveraging threshold denoising on DCT-based modulation spectrum for noise robust speech recognition. ICCA Yen-chih Cheng, Jun-Shan Lin, Jeih-weih Hung
2014	—	`conf`	Sliding backstepping control design for robotic manipulator systems with motor dynamics. ICCA Ya-Yun Hsiao, Po-Hsien Tu, Jeih-weih Hung, Jung-Shan Lin
2014	—	`conf`	Spatial histogram equalization of complex-valued acoustic spectra in modulation domain for noise-robust speech recognition. APSIPA Hsin-Ju Hsieh, Berlin Chen, Jeih-weih Hung
2014	Misc	`conf`	Speech enhancement using segmental nonnegative matrix factorization. ICASSP Hao-Teng Fan, Jeih-weih Hung, Xugang Lu, Syu-Siang Wang, Yu Tsao
2013	J	`jnl`	Employing Linear Prediction Coding in Feature Time Sequences for Robust Speech Recognition in Noisy Environments. Int. J. Comput. Linguistics Chin. Lang. Process. Hao-Teng Fan, Wen-Yu Tseng, Jeih-weih Hung
2013	Misc	`conf`	Filtering on the temporal probability sequence in histogram equalization for robust speech recognition. ICASSP Syu-Siang Wang, Yu Tsao, Jeih-weih Hung
2013	A	`conf`	Histogram equalization of real and imaginary modulation spectra for noise-robust speech recognition. INTERSPEECH Hsin-Ju Hsieh, Berlin Chen, Jeih-weih Hung
2013	J	`jnl`	Improved DFT-Based Channel Estimation for TDS-OFDM Wireless Communication Systems. IEICE Trans. Commun. Jung-Shan Lin, I-Cheng Liu, Shih-Chun Yang, Jeih-weih Hung
2013	J	`jnl`	Intra-frame cepstral sub-band weighting and histogram equalization for noise-robust speech recognition. EURASIP J. Audio Speech Music. Process. Jeih-weih Hung, Hao-Teng Fan
2013	—	`conf`	Modulation spectrum power-law expansion for robust speech recognition. APSIPA Hao-Teng Fan, Zi-Hao Ye, Jeih-weih Hung
2013	—	`conf`	Overlapped sub-band modulation spectrum normalization techniques for robust speech recognition. FSKD Hao-Teng Fan, Wei-Jeih Yeh, Jeih-weih Hung
2013	—	`conf`	Robustifying cepstral features by mitigating the outlier effect for noisy speech recognition. FSKD Hao-Teng Fan, Kuan-wei Hsieh, Chien-Hao Huang, Jeih-weih Hung
2013	—	`conf`	分頻式調變頻譜分解於強健性語音辨識 (Sub-band modulation spectrum factorization in robust speech recognition) [In Chinese]. ROCLING Hao-Teng Fan, Yi-zhang Cai, Jeih-weih Hung
2013	—	`conf`	雜訊環境下應用線性估測編碼於特徵時序列之強健性語音辨識 (Employing linear prediction coding in feature time sequences for robust speech recognition in noisy environments) [In Chinese]. ROCLING Hao-Teng Fan, Wen-Yu Tseng, Jeih-weih Hung
2012	—	`conf`	A study on cepstral sub-band normalization for robust ASR. ISCSLP Syu-Siang Wang, Jeih-weih Hung, Yu Tsao
2012	J	`jnl`	Enhancing the Magnitude Spectrum of Speech Features for Robust Speech Recognition. EURASIP J. Adv. Signal Process. Jeih-weih Hung, Hao-Teng Fan, Wen-Hsiang Tu
2012	A	`conf`	Exploring Joint Equalization of Spatial-Temporal Contextual Statistics of Speech Features for Robust Speech Recognition. INTERSPEECH Hsin-Ju Hsieh, Jeih-weih Hung, Berlin Chen
2012	J	`jnl`	Improved modulation spectrum enhancement methods for robust speech recognition. Signal Process. Jeih-weih Hung, Wen-Hsiang Tu, Chien-chou Lai
2012	—	`conf`	Leveraging gain normalization for sub-band temporal features in noise-robust speech recognition. FSKD Hao-Teng Fan, Jeih-weih Hung
2012	—	`conf`	Modulation spectrum exponential weighting for robust speech recognition. ITST Hao-Teng Fan, Yi-cheng Lian, Jeih-weih Hung
2012	J	`jnl`	Speech Recognition Leveraging Histogram Equalization Methods. Int. J. Comput. Linguistics Chin. Lang. Process. Hsin-Ju Hsieh, Jeih-weih Hung, Berlin Chen
2012	—	`conf`	改良式統計圖等化法強鍵性語音辨識之研究 (Improved Histogram Equalization Methods for Robust Speech Recognition) [In Chinese]. ROCLING Hsin-Ju Hsieh, Jeih-weih Hung, Berlin Chen
2011	—	`conf`	Compensating the Speech Features via Discrete Cosine Transform for Robust Speech Recognition (基於離散餘弦轉換之語音特徵的強健性補償法). ROCLING Hsin-Ju Hsieh, Wen-Hsiang Tu, Jeih-weih Hung
2011	—	`conf`	Exploiting principal component analysis in modulation spectrum enhancement for robust speech recognition. FSKD Jan-Yee Lee, Jeih-weih Hung
2011	—	`conf`	機率式調變頻譜分解於強健性語音辨識 (Probabilistic Modulation Spectrum Factorization for Robust Speech Recognition) [In Chinese]. ROCLING (Posters) Wen-Yi Chu, Yu-Chen Kao, Berlin Chen, Jeih-weih Hung
2010	—	`conf`	DCT-based processing of dynamic features for robust speech recognition. ISCSLP Wen-Chi Lin, Hao-Teng Fan, Jeih-weih Hung
2010	Misc	`conf`	Magnitude spectrum enhancement for robust speech recognition. ICASSP Wen-Hsiang Tu, Jeih-weih Hung
2010	—	`conf`	最小變異數調變頻譜濾波器於強健性語音辨識之研究 (A Study of Minimum Variance Modulation Filter for Robust Speech Recognition) [In Chinese]. ROCLING Ren-hau Hsieh, Hao-Teng Fan, Jeih-weih Hung
2010	—	`conf`	進階式調變頻譜補償法於強健性語音辨識之研究 (Advanced Modulation Spectrum Compensation Techniques for Robust Speech Recognition) [In Chinese]. ROCLING Wei-Jeih Yeh, Wen-Hsiang Tu, Jeih-weih Hung
2009	J	`jnl`	Incorporating Codebook and Utterance Information in Cepstral Statistics Normalization Techniques for Robust Speech Recognition in Additive Noise Environments. IEEE Signal Process. Lett. Jeih-weih Hung, Wen-Hsiang Tu
2009	A	`conf`	Integrating codebook and utterance information in cepstral statistics normalization techniques for robust speech recognition. INTERSPEECH Guan-min He, Jeih-weih Hung
2009	J	`jnl`	Study of Associative Cepstral Statistics Normalization Techniques for Robust Speech Recognition in Additive Noise Environments. Int. J. Comput. Linguistics Chin. Lang. Process. Wen-Hsiang Tu, Jeih-weih Hung
2009	A	`conf`	Sub-band feature statistics compensation techniques based on discrete wavelet transform for robust speech recognition. ICME Hao-Teng Fan, Jeih-weih Hung
2009	C	`conf`	Sub-band modulation spectrum compensation for robust speech recognition. ASRU Wen-Hsiang Tu, Sheng-Yuan Huang, Jeih-weih Hung
2009	J	`jnl`	Subband Feature Statistics Normalization Techniques Based on a Discrete Wavelet Transform for Robust Speech Recognition. IEEE Signal Process. Lett. Jeih-weih Hung, Hao-Teng Fan
2009	—	`conf`	併合式倒頻譜統計正規化技術於強健性語音辨識之研究 (A Study of Hybrid-based Cepstral Statistics Normalization Techniques for Robust Speech Recognition) [In Chinese]. ROCLING Guan-min He, Wen-Hsiang Tu, Jeih-weih Hung
2009	—	`conf`	強健性語音辨識中分頻段調變頻譜補償之研究 (A Study of Sub-band Modulation Spectrum Compensation for Robust Speech Recognition) [In Chinese]. ROCLING Sheng-Yuan Huang, Wen-Hsiang Tu, Jeih-weih Hung
2009	—	`conf`	強健性語音辨識中基於小波轉換之分頻統計補償技術的研究 (A Study of Sub-band Feature Statistics Compensation Techniques Based on a Discrete Wavelet Transform for Robust Speech Recognition) [In Chinese]. ROCLING Hao-Teng Fan, Wen-Hsiang Tu, Jeih-weih Hung
2008	J	`jnl`	Cepstral Statistics Compensation and Normalization Using Online Pseudo Stereo Codebooks for Robust Speech Recognition in Additive Noise Environments. IEICE Trans. Inf. Syst. Jeih-weih Hung
2008	J	`jnl`	Constructing Modulation Frequency Domain-Based Features for Robust Speech Recognition. IEEE Trans. Speech Audio Process. Jeih-weih Hung, Wei-Yi Tsai
2008	Misc	`conf`	Improved modulation spectrum normalization techniques for robust speech recognition. ICASSP Chi-An Pan, Chih-Cheng Wang, Jeih-weih Hung
2008	A	`conf`	Silence feature normalization for robust speech recognition in additive noise environments. INTERSPEECH Chih-Cheng Wang, Chi-An Pan, Jeih-weih Hung
2008	—	`conf`	強健性語音辨識中能量相關特徵之改良式正規化技術的研究 (Study of the Improved Normalization Techniques of Energy-Related Features for Robust Speech Recognition) [In Chinese]. ROCLING Chi-An Pan, Wen-Hsiang Tu, Jeih-weih Hung
2008	—	`conf`	組合式倒頻譜統計正規化法於強健性語音辨識之研究 (Associative Cepstral Statistics Normalization Techniques for Robust Speech Recognition) [In Chinese]. ROCLING Wen-Hsiang Tu, Kuang-chieh Wu, Jeih-weih Hung
2008	—	`conf`	調變頻譜正規化法使用於強健語音辨識之研究 (Study of Modulation Spectrum Normalization Techniques for Robust Speech Recognition) [In Chinese]. ROCLING Chih-Cheng Wang, Wen-Hsiang Tu, Jeih-weih Hung
2007	—	`conf`	Optimization of Temporal Filters in the Modulation Frequency Domain via Constrained Linear Discriminant Analysis (C-LDA) for Constructing Robust Features in Speech Recognition. ICASSP (4) Jeih-weih Hung
2007	A	`conf`	Optimization of temporal filters in the modulation frequency domain for constructing robust features in speech recognition. INTERSPEECH Jeih-weih Hung
2007	A	`conf`	Speech feature compensation based on pseudo stereo codebooks for robust speech recognition in additive noise environments. INTERSPEECH Tsung-hsueh Hsieh, Jeih-weih Hung
2007	—	`conf`	加成性雜訊環境下運用特徵參數統計補償法於強健性語音辨識 (Feature Statistics Compensation for Robust Speech Recognition in Additive Noise Environments) [In Chinese]. ROCLING Tsung-hsueh Hsieh, Jeih-weih Hung
2007	—	`conf`	端點偵測技術在強健語音參數擷取之研究 (Study of the Voice Activity Detection Techniques for Robust Speech Feature Extraction) [In Chinese]. ROCLING Wen-Hsiang Tu, Jeih-weih Hung
2006	—	`conf`	Cepstral Statistics Compensation Using Online Pseudo Stereo Codebooks for Robust Speech Recognition in Additive Noise Environments. ICASSP (1) Jeih-weih Hung
2006	J	`jnl`	Optimization of temporal filters for constructing robust features in speech recognition. IEEE Trans. Speech Audio Process. Jeih-weih Hung, Lin-Shan Lee
2006	A	`conf`	Silence energy normalization for robust speech recognition in additive noise environment. INTERSPEECH Chung-fu Tai, Jeih-weih Hung
2004	—	`conf`	Data-driven temporal filters based on maximum mutual information for robust features in speech recognition. ISCSLP Yung-Sheng Huang, Jeih-weih Hung
2003	—	`conf`	Data-driven temporal filters based on multi-eigenvectors for robust features in speech recognition. ICASSP (1) Ni-Chun Wang, Jeih-weih Hung, Lin-Shan Lee
2002	Misc	`conf`	Data-driven temporal filters for robust features in speech recognition obtained via Minimum Classification Error (MCE). ICASSP Jeih-weih Hung, Lin-Shan Lee
2002	A	`conf`	Data-driven temporal filters obtained via different optimization criteria evaluated on Aurora2 database. INTERSPEECH Jeih-weih Hung, Lin-Shan Lee
2001	A	`conf`	Comparative analysis for data-driven temporal filters obtained via principal component analysis (PCA) and linear discriminant analysis (LDA) in speech recognition. INTERSPEECH Jeih-weih Hung, Hsin-Min Wang, Lin-Shan Lee
2001	J	`jnl`	New approaches for domain transformation and parameter combination for improved accuracy in parallel model combination (PMC) techniques. IEEE Trans. Speech Audio Process. Jeih-weih Hung, Jia-Lin Shen, Lin-Shan Lee
2000	A	`conf`	Automatic metric-based speech segmentation for broadcast news via principal component analysis. INTERSPEECH Jeih-weih Hung, Hsin-Min Wang, Lin-Shan Lee
1999	Misc	`conf`	Improved parallel model combination techniques with split Gaussian mixtures for speech recognition under noisy conditions. ICASSP Jeih-weih Hung, Jia-Lin Shen, Lin-Shan Lee
1998	—	`conf`	Improved parallel model combination based on better domain transformation for speech recognition under noisy environments. ICSLP Jeih-weih Hung, Jia-Lin Shen, Lin-Shan Lee
1998	—	`conf`	Improved robust speech recognition considering signal correlation approximated by taylor series. ICSLP Jia-Lin Shen, Jeih-weih Hung, Lin-Shan Lee
1998	Misc	`conf`	Improved robustness for speech recognition under noisy conditions using correlated parallel model combination. ICASSP Jeih-weih Hung, Jia-Lin Shen, Lin-Shan Lee
1998	—	`conf`	Robust entropy-based endpoint detection for speech recognition in noisy environments. ICSLP Jia-Lin Shen, Jeih-weih Hung, Lin-Shan Lee