├── DatasetsScp ├── LSJ │ ├── ljs_audio_text_test_filelist.txt │ ├── ljs_audio_text_train_filelist.txt │ └── ljs_audio_text_val_filelist.txt └── noises │ └── DNS_48K.scp ├── LICENSE ├── Metrics ├── DNSMOS │ ├── DNSMOS │ │ ├── bak_ovr.onnx │ │ ├── model_v8.onnx │ │ ├── sig.onnx │ │ └── sig_bak_ovr.onnx │ ├── README.md │ ├── dnsmos_local.py │ └── pDNSMOS │ │ └── sig_bak_ovr.onnx ├── evaluate.py ├── evaluate_f0.py ├── f0 │ ├── __pycache__ │ │ └── f0.cpython-39.pyc │ └── f0.py ├── f0_rmse.py ├── lsd.py ├── mcd.py ├── mcd_utils.py ├── pesq_.py ├── snr.py ├── stoi.py └── utmos.py ├── Models ├── __init__.py ├── apnet.py ├── apnet2.py ├── bsrnn.py ├── bsrnn_24k.py ├── convtasnet.py ├── freeV.py ├── gcrn.py ├── hddemucas.py ├── hifigan.py ├── istftnet.py └── models.py ├── README.md ├── cfgs ├── apnet2_config.json ├── apnet_config.json ├── bsrnn_config.json ├── bsrnn_joint_denoise_vocoder_config.json ├── convtasnet_config.json ├── freeV_config.json ├── gcrn_config.json ├── hddemucas_config.json ├── hifigan_v1_config.json └── istftnet_config.json ├── dataset.py ├── dataset_joint_denoise_vocoder.py ├── env.py ├── figure ├── Joint_metrics.png ├── Results_comparisons.png └── deg_example.png ├── infers ├── inference_apnet.py ├── inference_apnet2.py ├── inference_bsrnn.py ├── inference_convtasnet.py ├── inference_freev.py ├── inference_hddemucas.py ├── inference_hifigan.py ├── inference_istftnet.py └── inference_joint_denoise_vocoder_bsrnn.py ├── requirements.txt ├── train_tf_wi_inv.py ├── train_tf_wi_inv_joint_denoise_vocoder.py ├── train_time_wi_inv.py └── utils.py /DatasetsScp/LSJ/ljs_audio_text_test_filelist.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/DatasetsScp/LSJ/ljs_audio_text_test_filelist.txt -------------------------------------------------------------------------------- /DatasetsScp/LSJ/ljs_audio_text_train_filelist.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/DatasetsScp/LSJ/ljs_audio_text_train_filelist.txt -------------------------------------------------------------------------------- /DatasetsScp/LSJ/ljs_audio_text_val_filelist.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/DatasetsScp/LSJ/ljs_audio_text_val_filelist.txt -------------------------------------------------------------------------------- /DatasetsScp/noises/DNS_48K.scp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/DatasetsScp/noises/DNS_48K.scp -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/LICENSE -------------------------------------------------------------------------------- /Metrics/DNSMOS/DNSMOS/bak_ovr.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/DNSMOS/DNSMOS/bak_ovr.onnx -------------------------------------------------------------------------------- /Metrics/DNSMOS/DNSMOS/model_v8.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/DNSMOS/DNSMOS/model_v8.onnx -------------------------------------------------------------------------------- /Metrics/DNSMOS/DNSMOS/sig.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/DNSMOS/DNSMOS/sig.onnx -------------------------------------------------------------------------------- /Metrics/DNSMOS/DNSMOS/sig_bak_ovr.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/DNSMOS/DNSMOS/sig_bak_ovr.onnx -------------------------------------------------------------------------------- /Metrics/DNSMOS/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/DNSMOS/README.md -------------------------------------------------------------------------------- /Metrics/DNSMOS/dnsmos_local.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/DNSMOS/dnsmos_local.py -------------------------------------------------------------------------------- /Metrics/DNSMOS/pDNSMOS/sig_bak_ovr.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/DNSMOS/pDNSMOS/sig_bak_ovr.onnx -------------------------------------------------------------------------------- /Metrics/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/evaluate.py -------------------------------------------------------------------------------- /Metrics/evaluate_f0.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/evaluate_f0.py -------------------------------------------------------------------------------- /Metrics/f0/__pycache__/f0.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/f0/__pycache__/f0.cpython-39.pyc -------------------------------------------------------------------------------- /Metrics/f0/f0.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/f0/f0.py -------------------------------------------------------------------------------- /Metrics/f0_rmse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/f0_rmse.py -------------------------------------------------------------------------------- /Metrics/lsd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/lsd.py -------------------------------------------------------------------------------- /Metrics/mcd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/mcd.py -------------------------------------------------------------------------------- /Metrics/mcd_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/mcd_utils.py -------------------------------------------------------------------------------- /Metrics/pesq_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/pesq_.py -------------------------------------------------------------------------------- /Metrics/snr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/snr.py -------------------------------------------------------------------------------- /Metrics/stoi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/stoi.py -------------------------------------------------------------------------------- /Metrics/utmos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Metrics/utmos.py -------------------------------------------------------------------------------- /Models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/__init__.py -------------------------------------------------------------------------------- /Models/apnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/apnet.py -------------------------------------------------------------------------------- /Models/apnet2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/apnet2.py -------------------------------------------------------------------------------- /Models/bsrnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/bsrnn.py -------------------------------------------------------------------------------- /Models/bsrnn_24k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/bsrnn_24k.py -------------------------------------------------------------------------------- /Models/convtasnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/convtasnet.py -------------------------------------------------------------------------------- /Models/freeV.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/freeV.py -------------------------------------------------------------------------------- /Models/gcrn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/gcrn.py -------------------------------------------------------------------------------- /Models/hddemucas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/hddemucas.py -------------------------------------------------------------------------------- /Models/hifigan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/hifigan.py -------------------------------------------------------------------------------- /Models/istftnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/istftnet.py -------------------------------------------------------------------------------- /Models/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/Models/models.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/README.md -------------------------------------------------------------------------------- /cfgs/apnet2_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/apnet2_config.json -------------------------------------------------------------------------------- /cfgs/apnet_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/apnet_config.json -------------------------------------------------------------------------------- /cfgs/bsrnn_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/bsrnn_config.json -------------------------------------------------------------------------------- /cfgs/bsrnn_joint_denoise_vocoder_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/bsrnn_joint_denoise_vocoder_config.json -------------------------------------------------------------------------------- /cfgs/convtasnet_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/convtasnet_config.json -------------------------------------------------------------------------------- /cfgs/freeV_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/freeV_config.json -------------------------------------------------------------------------------- /cfgs/gcrn_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/gcrn_config.json -------------------------------------------------------------------------------- /cfgs/hddemucas_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/hddemucas_config.json -------------------------------------------------------------------------------- /cfgs/hifigan_v1_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/hifigan_v1_config.json -------------------------------------------------------------------------------- /cfgs/istftnet_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/cfgs/istftnet_config.json -------------------------------------------------------------------------------- /dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/dataset.py -------------------------------------------------------------------------------- /dataset_joint_denoise_vocoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/dataset_joint_denoise_vocoder.py -------------------------------------------------------------------------------- /env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/env.py -------------------------------------------------------------------------------- /figure/Joint_metrics.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/figure/Joint_metrics.png -------------------------------------------------------------------------------- /figure/Results_comparisons.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/figure/Results_comparisons.png -------------------------------------------------------------------------------- /figure/deg_example.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/figure/deg_example.png -------------------------------------------------------------------------------- /infers/inference_apnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/infers/inference_apnet.py -------------------------------------------------------------------------------- /infers/inference_apnet2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/infers/inference_apnet2.py -------------------------------------------------------------------------------- /infers/inference_bsrnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/infers/inference_bsrnn.py -------------------------------------------------------------------------------- /infers/inference_convtasnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/infers/inference_convtasnet.py -------------------------------------------------------------------------------- /infers/inference_freev.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/infers/inference_freev.py -------------------------------------------------------------------------------- /infers/inference_hddemucas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/infers/inference_hddemucas.py -------------------------------------------------------------------------------- /infers/inference_hifigan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/infers/inference_hifigan.py -------------------------------------------------------------------------------- /infers/inference_istftnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/infers/inference_istftnet.py -------------------------------------------------------------------------------- /infers/inference_joint_denoise_vocoder_bsrnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/infers/inference_joint_denoise_vocoder_bsrnn.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/requirements.txt -------------------------------------------------------------------------------- /train_tf_wi_inv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/train_tf_wi_inv.py -------------------------------------------------------------------------------- /train_tf_wi_inv_joint_denoise_vocoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/train_tf_wi_inv_joint_denoise_vocoder.py -------------------------------------------------------------------------------- /train_time_wi_inv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/train_time_wi_inv.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers/HEAD/utils.py --------------------------------------------------------------------------------