ZiyueZhao

Hey, thanks for your questions! Actually, there are 16 speech files (each contains 4 sentences) in the packing of American English from P.50 ITU-T test signal dataset. The originally provided...

你好， 在训练时需要补偿编码语音的时延（delay compensation），以对齐解码的语音与原始语音。在文章的IV-B节中有提到。 On Tue, 31 Mar 2020 at 15:39, ziphe wrote: > 您好： > 我没有在文章中找到关于编码延迟的处理，请问需要将解码的语音与原始语音对齐吗？ > > — > You are receiving this because you are subscribed to this...

Hi crankyz, I tried again the codes, and I didn't get this Error. It should work. Did you implement the .m files as the order part1->part2->part3? Best regards

Hi, Thanks for your interests in the work! The clean speech signals are from Grid corpus, as the link you find. Therein, the first column contains all the audio signals...

Yes, you may use other noise datasets (maybe open source or your own noise datasets) for your training and testing. Some modifications in the preparation of the mixture are therefore...