[ICASSP 2020] META LEARNING FOR END-TO-END LOW-RESOURCE SPEECH RECOGNITION (Speaker: Jui-Yang Hsu) Blog 12/06/2026 · 0 Comment [ICASSP 2020] META LEARNING FOR END-TO-END LOW-RESOURCE SPEECH RECOGNITION (Speaker: Jui-Yang Hsu)[ICASSP 2020] TOWARDS UNSUPERVISED SPEECH RECOGNITION AND SYNTHESIS (Speaker: Tao Tu)[ICASSP 2020] WHAMR!: Noisy and Reverberant Single-Channel Speech SeparationICASSP 2020 - Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer[ICASSP 2020] ONE-SHOT VOICE CONVERSION BY VECTOR QUANTIZATION (Speaker: Da-Yi Wu)[ICASSP 2020] End-to-End Multi-speaker Speech Recognition with TransformerSystems for Low-Resource Speech Recognition Tasks in Open Automatic Speech Recognition and Formo...[ICASSP 2020]Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory for End-To-End ASR[ICASSP 2020] ASR WITH WORD EMBEDDING REGULARIZATION AND FUSED DECODING (Speaker: Alexander H. Liu)[ICASSP 2020] WHAT DOES A NETWORK LAYER HEAR? (Speaker: Chung-Yi Li)12
![[ICASSP 2020] META LEARNING FOR END-TO-END LOW-RESOURCE SPEECH RECOGNITION (Speaker: Jui-Yang Hsu)](https://i.ytimg.com/vi/goav0eXKPwg/hq720.jpg?sqp=-oaymwEnCNAFEJQDSFryq4qpAxkIARUAAIhCGAHYAQHiAQoIGBACGAY4AUAB&rs=AOn4CLDPvUjJ0rQGEwZHJhTjOOACwmmEmw)
![[ICASSP 2020] TOWARDS UNSUPERVISED SPEECH RECOGNITION AND SYNTHESIS (Speaker: Tao Tu)](https://i.ytimg.com/vi/cnZdfLSqwiE/hqdefault.jpg?sqp=-oaymwEnCOADEI4CSFryq4qpAxkIARUAAIhCGAHYAQHiAQoIGBACGAY4AUAB&rs=AOn4CLBbGvIS3DKnnCyTnMteM1Q6ZGWHCQ)
![[ICASSP 2020] WHAMR!: Noisy and Reverberant Single-Channel Speech Separation](https://i.ytimg.com/vi/3tjmYgutM38/hq720.jpg?sqp=-oaymwEnCNAFEJQDSFryq4qpAxkIARUAAIhCGAHYAQHiAQoIGBACGAY4AUAB&rs=AOn4CLBHsNc0PlUBnCOcSYIAFu-l1U-VIQ)
![[ICASSP 2020] ONE-SHOT VOICE CONVERSION BY VECTOR QUANTIZATION (Speaker: Da-Yi Wu)](https://i.ytimg.com/vi/W3t8FHgV90M/hq720.jpg?sqp=-oaymwEnCNAFEJQDSFryq4qpAxkIARUAAIhCGAHYAQHiAQoIGBACGAY4AUAB&rs=AOn4CLA3GmWnzg3s50SD32FtRFCCJOr1tA)
![[ICASSP 2020] End-to-End Multi-speaker Speech Recognition with Transformer](https://i.ytimg.com/vi/Mo2RRNgfU4g/hqdefault.jpg?sqp=-oaymwEnCOADEI4CSFryq4qpAxkIARUAAIhCGAHYAQHiAQoIGBACGAY4AUAB&rs=AOn4CLCnOFWrgblV_4len3tpfjtKoVhOSQ)
![[ICASSP 2020]Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory for End-To-End ASR](https://i.ytimg.com/vi/Db-NtCEI4rQ/hq720.jpg?sqp=-oaymwEnCNAFEJQDSFryq4qpAxkIARUAAIhCGAHYAQHiAQoIGBACGAY4AUAB&rs=AOn4CLBlOy8yrxL4mrYNZ9_pSd_nI0a6SQ)
![[ICASSP 2020] ASR WITH WORD EMBEDDING REGULARIZATION AND FUSED DECODING (Speaker: Alexander H. Liu)](https://i.ytimg.com/vi/1j46kdawA4Q/hq720.jpg?sqp=-oaymwEnCNAFEJQDSFryq4qpAxkIARUAAIhCGAHYAQHiAQoIGBACGAY4AUAB&rs=AOn4CLCmReWcWwn84dhDhHefd8FW_fgUqg)
![[ICASSP 2020] WHAT DOES A NETWORK LAYER HEAR? (Speaker: Chung-Yi Li)](https://i.ytimg.com/vi/6gtn7H-pWr8/hq720.jpg?sqp=-oaymwEnCNAFEJQDSFryq4qpAxkIARUAAIhCGAHYAQHiAQoIGBACGAY4AUAB&rs=AOn4CLBdljHRBrWcx2l-gnfQfg0hi9pXww)