OD-SLA-8: Speech Recognition and Spoken Language Processing
Fri, 17 Dec, 15:20 - 17:00 Japan Standard Time (UTC +9)
Fri, 17 Dec, 06:20 - 08:00 Coordinated Universal Time
Fri, 17 Dec, 01:20 - 03:00 Eastern Standard Time (UTC -5)
Thu, 16 Dec, 22:20 - 00:00 Pacific Standard Time (UTC -8)
Track: Speech, Language, and Audio (SLA)

OD-SLA-8.1: Enriching Under-Represented Named Entities for Improved Speech Recognition

Tingzhi Mao, Xinjiang University, China; Yerbolat Khassanov, Nazarbayev University, Kazakhstan; Van Tung Pham, Haihua Xu, Nanyang Technological University, Singapore, Singapore; Hao Huang, Aishan Wumaier, Xinjiang University, China; Eng Siong Chng, Nanyang Technological University, Singapore, Singapore

OD-SLA-8.2: Ensemble of One Model: Creating Model Variations for Transformer with Layer Permutation

Andrew Liaw, Jia-Hao Hsu, Chung-Hsien Wu, National Cheng Kung University, Taiwan

OD-SLA-8.5: Multilingual Approach to Joint Speech and Accent Recognition with DNN-HMM Framework

Yizhou Peng, Jicheng Zhang, Haobo Zhang, Xinjiang University, China; Haihua Xu, Nanyang Technological University, Singapore; Hao Huang, Xinjiang University, China; Sheng Li, National Institute of Information and Communications Technology, Japan; Eng Siong Chng, Nanyang Technological University, Singapore

OD-SLA-8.6: Improving End-To-End Modeling for Mispronunciation Detection with Effective Augmentation Mechanisms

Tien-Hong Lo, Yao-Ting Sung, Berlin Chen, National Taiwan Normal University, Taiwan

OD-SLA-8.7: Zero-shot Domain Adaptation with Inference Relation Paths for Spoken Language Understanding

Sixia Li, Jianwu Dang, Japan Advanced Institute of Science and Technology, Japan

OD-SLA-8.8: End to End Spoken Language Understanding Using Partial Disentangled Slot Embedding

Tan Liu, Wu Guo, University of Science and Technology of China, China

OD-SLA-8.9: MULTIPLE DEEP LEARNING MODELS AND ARCHITECTURES WITH DIFFERENT NUMBERS OF STATES USED TO IMPROVE RETRIEVAL ACCURACY OF QUERY-BY-EXAMPLE

Kazuki Hatakeyama, Iwate Prefectural University, Japan; Masahiro Nishino, TOYOTA SYSTEMS CORPORATION, Japan; Kazunori Kojima, Iwate Prefectural University, Japan; Shi-wook Lee, AIST, Japan; Yoshiaki Itoh, Iwate Prefectural University, Japan

OD-SLA-8.10: Separable Temporal Convolution plus Temporally Pooled Attention for Lightweight High-performance Keyword Spotting

Shenghua Hu, Jing Wang, Beijing Institute of Technology, China; Yujun Wang, Xiaomi Inc., China; Wenjing Yang, Beijing Institute of Technology, China

OD-SLA-8.11: END-TO-END SPONTANEOUS SPEECH RECOGNITION USING HESITATION LABELING

Koharu Horii, Toyohashi University of Technology, Japan; Meiko Fukuda, Tokushima University, Japan; Kengo Ohta, National Institute of Technology, Anan College, Japan; Ryota Nishimura, Tokushima University, Japan; Atsunori Ogawa, Nippon Telegraph and Telephone Corporation, Japan; Norihide Kitaoka, Toyohashi University of Technology, Japan

OD-SLA-8.12: UNSUPERVISED SPOKEN TERM DISCOVERY USING WAV2VEC 2.0

Yu Iwamoto, Takahiro Shinozaki, Tokyo Institute of Technology, Japan

OD-SLA-8.13: EFFECT OF PERCEPTUAL TRAINING WITH NOISE ON CHINESE LEARNERS’ ENGLISH CONSONANT RECEPTION THRESHOLDS

Jian Gong, Yameng Yu, William Bellamy, Feng Wang, Xiaoli Ji, Jiangsu University of Science and Technology, China

OD-SLA-8.14: MULTI-VIEW CONVOLUTION FOR LIPREADING

Tsubasa Maeda, Satoshi Tamura, Gifu university, Japan

OD-SLA-8.15: OLR 2021 CHALLENGE: DATASETS, RULES AND BASELINES

Binling Wang, Wenxuan Hu, Zheng Li, Qingyang Hong, Lin Li, Xiamen University, China; Dong Wang, Tsinghua University, China; Liming Song, Cheng Yang, Speechocean, China

OD-SLA-8.16: CROSS-UTTERANCE RERANKING MODELS WITH BERT AND GRAPH CONVOLUTIONAL NETWORKS FOR CONVERSATIONAL SPEECH RECOGNITION

Shih-Hsuan Chiu, Tien-Hong Lo, Berlin Chen, National Taiwan Normal University, Taiwan