![[ICASSP2023] [Highlight] AudioDec: An Open-Source Streaming High-Fidelity Neural Audio Codec](/vi/aVJaKcuB5d0/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLCJ588lxEUhj8Pi5ce-GtBfCV8Y6Q)
Yi-Chiao Wu (吳宜樵)
[ICASSP2023] [Highlight] AudioDec: An Open-Source Streaming High-Fidelity Neural Audio Codec
6:13
![[INTERSPEECH 2021] Paper 806: Relational Data Selection for Neural Vocoder](/vi/oXDeeDAwtqA/hqdefault.jpg?sqp=-oaymwE9CNACELwBSFryq4qpAy8IARUAAAAAGAElAADIQj0AgKJDeAHwAQH4AbYXgALQD4oCDAgAEAEYZSBlKGUwDw==&rs=AOn4CLD-zlzhBKDRx3-_cZaS1yfrQH1V_w)
Yi-Chiao Wu (吳宜樵)
[INTERSPEECH 2021] Paper 806: Relational Data Selection for Neural Vocoder
8:58
![[INTERSPEECH 2021] [Highlight] Paper 806: Relational Data Selection for Neural Vocoder](/vi/1aeZTmtO0lI/hqdefault.jpg?sqp=-oaymwE9CNACELwBSFryq4qpAy8IARUAAAAAGAElAADIQj0AgKJDeAHwAQH4Af4OgAK4CIoCDAgAEAEYZSBlKGUwDw==&rs=AOn4CLDUAeLZaW9aaIO78c61yF3rLIUBjw)
Yi-Chiao Wu (吳宜樵)
[INTERSPEECH 2021] [Highlight] Paper 806: Relational Data Selection for Neural Vocoder
2:54
Yi-Chiao Wu (吳宜樵)
Incorporating prior knowledge on speech production mechanism into neural speech waveform generation
22:33
![[INTERSPEECH 2020] Paper 1070: QPPWG vocoder](/vi/yY4WOtPIH-4/hqdefault.jpg?sqp=-oaymwE9CNACELwBSFryq4qpAy8IARUAAAAAGAElAADIQj0AgKJDeAHwAQH4Af4JgALQBYoCDAgAEAEYZSBlKGUwDw==&rs=AOn4CLCq8H_ELwlj-1X0l3vLjp9ajPamdA)
Yi-Chiao Wu (吳宜樵)
[INTERSPEECH 2020] Paper 1070: QPPWG vocoder
12:21
![[INTERSPEECH 2020] Paper 1072: Neural-post-filter for TTS](/vi/O_FQvdNRtlo/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLAQ6C0PXwvp5YQCn6QXAlqOtNtxjA)
Yi-Chiao Wu (吳宜樵)
[INTERSPEECH 2020] Paper 1072: Neural-post-filter for TTS
10:11
![[INTERSPEECH 2020] [Highlight] Paper 1070: QPPWG vocoder](/vi/rmENecC-0wE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLAxm2_47oTn0K8vfg4v9faXivTt9g)
Yi-Chiao Wu (吳宜樵)
[INTERSPEECH 2020] [Highlight] Paper 1070: QPPWG vocoder
1:25
![[INTERSPEECH 2020] [Highlight] Paper 1072: Neural-post-filter for TTS](/vi/28kGUactIxQ/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLD2lbJxACjmLebyjZn513PwAz4DtQ)
Yi-Chiao Wu (吳宜樵)
[INTERSPEECH 2020] [Highlight] Paper 1072: Neural-post-filter for TTS
1:29
![[2020] Speech generation (0): Vocoder and RNN and CNN based speech generative model](/vi/TR4riFsNw80/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLCuTdNRV6_6Zs12Kty-6BtkW4PePA)
Yi-Chiao Wu (吳宜樵)
[2020] Speech generation (0): Vocoder and RNN and CNN based speech generative model
13:58
![[2020] Speech generation (1): Quasi periodic waveform generative model](/vi/nRahlEgywjg/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDSHoXE28VxWGyqMwh5T6oPIDKL0Q)
Yi-Chiao Wu (吳宜樵)
[2020] Speech generation (1): Quasi periodic waveform generative model
13:54
![[2020] 語音生成 (壹): Quasi Periodic 語音訊號生成模型](/vi/-HArsvY5ffE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLCFRuomX9PCLIKV9jRVGW3W25Jffw)
Yi-Chiao Wu (吳宜樵)
[2020] 語音生成 (壹): Quasi Periodic 語音訊號生成模型
19:27
![[2020] 語音生成 (零): 語音聲碼器, RNN 和 CNN 語音訊號生成模型](/vi/Up5Qn8YDObw/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLCkrBdtnhmPCoA5ocipMFBnE2nVtA)
Yi-Chiao Wu (吳宜樵)
[2020] 語音生成 (零): 語音聲碼器, RNN 和 CNN 語音訊號生成模型
15:35