APSIPA 2021 || Tokyo, Japan || 14-17 December 2021

WE2.OD-A.1: CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanism

Guochen Yu, Yutian Wang, Hui Wang, Qin Zhang, Communication University of China, China; Chengshi Zheng, Institute of Acoustics, Chinese Academy of Sciences, China

WE2.OD-A.2: A Robust Maximum Likelihood Distortionless Response Beamformer based on a Complex Generalized Gaussian Distribution

Weixin Meng, Chengshi Zheng, Xiaodong Li, Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Science, Beijing, 100190, China；University of Chinese Academy of Sciences, Beijing, China, China

WE2.OD-A.3: SPEECH ENHANCEMENT BASED ON MASKING APPROACH CONSIDERING SPEECH QUALITY AND ACOUSTIC CONFIDENCE FOR NOISY SPEECH RECOGNITION

Shih-Chuan Chu, Chung-Hsien Wu, Yun-Wen Lin, National Cheng Kung University, Taiwan

WE2.OD-A.4: DNN-BASED LINEAR PREDICTION RESIDUAL ENHANCEMENT FOR SPEECH DEREVERBERATION

Xinyang Feng, Nuo Li, Zunwen He, Yan Zhang, Wancheng Zhang, Beijing Institute of Technology, China

WE2.OD-A.5: Mandarin Electro-Laryngeal Speech Enhancement based on Statistical Voice Conversion and Manual Tone Control

Zhaopeng Qian, Haijun Niu, Shaochuan Zhang, Beihang University, China; Li Wang, Beijing Research Center of Urban System Engineering, China; Kazuhiro Kobayashi, Tomoki Toda, Nagoya University, Japan

WE2.OD-A.6: Incorporating Multi-Target in Multi-Stage Speech Enhancement Model for Better Generalization

Lu Zhang, Mingjiang Wang, Zehua Zhang, Xuyi Zhuang, Harbin Institute of Technology, Shenzhen, China; Andong Li, Institute of Acoustics, Chinese Academy of Sciences, China

WE2.OD-A.7: Low-Power Convolutional Recurrent Neural Network For Monaural Speech Enhancement

Fei Gao, Haixin Guan, Unisound AI Technology Co. Ltd, China; , ,

WE2.OD-A.8: Multi-channel Speech Enhancement with 2-D Convolutional Time-frequency Domain Features and a Pre-trained Acoustic Model

Quandong Wang, Junnan Wu, Zhao Yan, Sichong Qian, Liyong Guo, Lichun Fan, Weiji Zhuang, Peng Gao, Yujun Wang, Xiaomi Corporation, China

WE2.OD-A.9: Processing Phoneme Specific Segments for Cleft Lip and Palate Speech Enhancement

Protima Nomo Sudro, Rohit Sinha, Indian Institute of Technology Guwahati, India; S R Mahadeva Prasanna, Indian Institute of Technology Dharwad, India

WE2.OD-A.10: Speech Enhancement by Noise Self-Supervised Rank-Constrained Spatial Covariance Matrix Estimation via Independent Deeply Learned Matrix Analysis

Sota Misawa, Norihiro Takamune, Tomohiko Nakamura, Hiroshi Saruwatari, The University of Tokyo, Japan; Daichi Kitamura, National Institute of Technology, Japan; Masakazu Une, University of Tsukuba, Japan; Shoji Makino, Waseda University, Japan

WE2.OD-A.11: CAUSAL DISTORTIONLESS RESPONSE BEAMFORMING BY ALTERNATING DIRECTION METHOD OF MULTIPLIERS

Yoshiki Masuyama, Kouei Yamaoka, Yuma Kinoshita, Nobutaka Ono, Tokyo Metropolitan University, Japan

WE2.OD-A.12: STACKED U-NET WITH HIGH-LEVEL FEATURE TRANSFER FOR PARAMETER EFFICIENT SPEECH ENHANCEMENT

Jinyoung Lee, Hong-Goo Kang, Yonsei University, Korea, Republic of

WE2.OD-A.13: EXTENSION OF VIRTUAL MICROPHONE TECHNIQUE TO MULTIPLE REAL MICROPHONES AND INVESTIGATION OF THE IMPACT OF PHASE AND AMPLITUDE INTERPOLATION ON SPEECH ENHANCEMENT

Hanako Segawa, Takeshi Yamada, University of Tsukuba, Japan; Li Li, NTT Corporation, Japan; Shoji Makino, University of Tsukuba, Waseda University, Japan

WE2.OD-A.14: Comparative Study on DNN-based Minimum Variance Beamforming Robust to Small Movements of Sound Sources

Kohei Saijo, Tetsunori Kobayashi, Tetsuji Ogawa, Waseda University, Japan; Kazuhiro Katagiri, Masaru Fujieda, OKI Electric Industry Corporation, Japan

WE2.OD-A.15: IMPROVEMENTS TO NON-INTRUSIVE INTELLIGIBILITY PREDICTION FOR REVERBERANT SPEECH

Kazushi Nakazawa, Kazuhiro Kondo, Yamagata University, Japan