This repository contains the audio samples for "D2Former: A Fully Complex Dual-Path Dual-Decoder Conformer Network using Joint Complex Masking and Complex Spectral Mapping for Monaural Speech Enhancement" which is submitted to ICASSP 2023.
Hello, I would like to ask two questions
One is what python version are you running your model on, I'm running it with version 3.9 but there are many global declarations in compute_metrics_norm.py that report an error about not being defined.
Another question, the dataset VCTK-DEMAND is this one https://datashare.ed.ac.uk/handle/10283/2791, it's all 48Khz audio, I use sound.set_frame_rate(16000) to reduce it to 16Khz, but the code is still reporting an error Error: Unsupported sampling rate. how to regulate lower sampling rate?
Hello, I would like to ask two questions One is what python version are you running your model on, I'm running it with version 3.9 but there are many global declarations in compute_metrics_norm.py that report an error about not being defined. Another question, the dataset VCTK-DEMAND is this one https://datashare.ed.ac.uk/handle/10283/2791, it's all 48Khz audio, I use sound.set_frame_rate(16000) to reduce it to 16Khz, but the code is still reporting an error Error: Unsupported sampling rate. how to regulate lower sampling rate?