以三元組損失微調時延神經網路語者嵌入函數之語者辨識系統(Time Delay Neural Network-based Speaker Embedding Function Fine-tuned with Triplet Loss for Distance-based Speaker Recognition)

以三元組損失微調時延神經網路語者嵌入函數之語者辨識系統(Time Delay Neural Network-based Speaker Embedding Function Fine-tuned with Triplet Loss for Distance-based Speaker Recognition) Chih-Ting Yehn author Po-Chin Wang author Su-Yu Zhang author Chia-Ping Chen author Shan-Wen Hsiao author Bo-Cheng Chan author Chung-li Lu author 2019-10 text zho Proceedings of the 31st Conference on Computational Linguistics and Speech Processing (ROCLING 2019) Chen-Yu Chiag editor Min-Yuh Day editor Jen-Tzung Chien editor The Association for Computational Linguistics and Chinese Language Processing (ACLCLP) New Taipei City, Taiwan conference publication yehn-etal-2019-yi https://aclanthology.org/2019.rocling-1.29/ 2019-10 310 324