--- tags: - espnet - audio - audio-to-audio language: en datasets: - wsj0_2mix license: cc-by-4.0 --- ## ESPnet2 ENH model ### `lichenda/Chenda_Li_wsj0_2mix_enh_dprnn_tasnet` This model was trained by LiChenda using wsj0_2mix recipe in [espnet](https://github.com/espnet/espnet/). Imported from [zenodo](https://zenodo.org/record/4688000). ### Demo: How to use in ESPnet2 ```bash cd espnet git checkout 54919e2529d6f58f4550d4a72960f57b83f66dc9 pip install -e . cd egs2/wsj0_2mix/enh1 ./run.sh --skip_data_prep false --skip_train true --download_model lichenda/Chenda_Li_wsj0_2mix_enh_dprnn_tasnet ``` # RESULTS ## Environments - date: `Thu Apr 15 00:03:19 CST 2021` - python version: `3.7.10 (default, Feb 26 2021, 18:47:35) [GCC 7.3.0]` - espnet version: `espnet 0.9.8` - pytorch version: `pytorch 1.5.0` - Git hash: `2aa2f151b5929dc9ffa4df39a8d8c26ca4dbdb85` - Commit date: `Tue Mar 30 09:08:27 2021 +0900` ## enh_train_enh_dprnn_tasnet_raw config: conf/tuning/train_enh_dprnn_tasnet.yaml |dataset|STOI|SAR|SDR|SIR| |---|---|---|---|---| |enhanced_cv_min_8k|0.960037|19.0476|18.5438|29.1591| |enhanced_tt_min_8k|0.968376|18.8209|18.2925|28.929| ## ENH config
expand ``` config: conf/tuning/train_enh_dprnn_tasnet.yaml print_config: false log_level: INFO dry_run: false iterator_type: chunk output_dir: exp/enh_train_enh_dprnn_tasnet_raw ngpu: 1 seed: 0 num_workers: 4 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: 4 dist_rank: 0 local_rank: 0 dist_master_addr: localhost dist_master_port: 45126 dist_launcher: null multiprocessing_distributed: true unused_parameters: false sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 150 patience: 4 val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - si_snr - max - - valid - loss - min keep_nbest_models: 1 grad_clip: 5.0 grad_clip_type: 2.0 grad_noise: false accum_grad: 1 no_forward_run: false resume: true train_dtype: float32 use_amp: false log_interval: null use_tensorboard: true use_wandb: false wandb_project: null wandb_id: null detect_anomaly: false pretrain_path: null init_param: [] freeze_param: [] num_iters_per_epoch: null batch_size: 4 valid_batch_size: null batch_bins: 1000000 valid_batch_bins: null train_shape_file: - exp/enh_stats_8k/train/speech_mix_shape - exp/enh_stats_8k/train/speech_ref1_shape - exp/enh_stats_8k/train/speech_ref2_shape valid_shape_file: - exp/enh_stats_8k/valid/speech_mix_shape - exp/enh_stats_8k/valid/speech_ref1_shape - exp/enh_stats_8k/valid/speech_ref2_shape batch_type: folded valid_batch_type: null fold_length: - 80000 - 80000 - 80000 sort_in_batch: descending sort_batch: descending multiple_iterator: false chunk_length: 32000 chunk_shift_ratio: 0.5 num_cache_chunks: 1024 train_data_path_and_name_and_type: - - dump/raw/tr_min_8k/wav.scp - speech_mix - sound - - dump/raw/tr_min_8k/spk1.scp - speech_ref1 - sound - - dump/raw/tr_min_8k/spk2.scp - speech_ref2 - sound valid_data_path_and_name_and_type: - - dump/raw/cv_min_8k/wav.scp - speech_mix - sound - - dump/raw/cv_min_8k/spk1.scp - speech_ref1 - sound - - dump/raw/cv_min_8k/spk2.scp - speech_ref2 - sound allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 valid_max_cache_size: null optim: adam optim_conf: lr: 0.001 eps: 1.0e-08 weight_decay: 0 scheduler: reducelronplateau scheduler_conf: mode: min factor: 0.7 patience: 1 init: xavier_uniform model_conf: loss_type: si_snr use_preprocessor: false encoder: conv encoder_conf: channel: 64 kernel_size: 2 stride: 1 separator: dprnn separator_conf: num_spk: 2 layer: 6 rnn_type: lstm bidirectional: true nonlinear: relu unit: 128 segment_size: 250 dropout: 0.1 decoder: conv decoder_conf: channel: 64 kernel_size: 2 stride: 1 required: - output_dir version: 0.9.8 distributed: true ```
### Citing ESPnet ```BibTex @inproceedings{watanabe2018espnet, author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai}, title={{ESPnet}: End-to-End Speech Processing Toolkit}, year={2018}, booktitle={Proceedings of Interspeech}, pages={2207--2211}, doi={10.21437/Interspeech.2018-1456}, url={http://dx.doi.org/10.21437/Interspeech.2018-1456} } @inproceedings{ESPnet-SE, author = {Chenda Li and Jing Shi and Wangyou Zhang and Aswin Shanmugam Subramanian and Xuankai Chang and Naoyuki Kamo and Moto Hira and Tomoki Hayashi and Christoph B{"{o}}ddeker and Zhuo Chen and Shinji Watanabe}, title = {ESPnet-SE: End-To-End Speech Enhancement and Separation Toolkit Designed for {ASR} Integration}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {785--792}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383615}, doi = {10.1109/SLT48900.2021.9383615}, timestamp = {Mon, 12 Apr 2021 17:08:59 +0200}, biburl = {https://dblp.org/rec/conf/slt/Li0ZSCKHHBC021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ``` or arXiv: ```bibtex @misc{watanabe2018espnet, title={ESPnet: End-to-End Speech Processing Toolkit}, author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai}, year={2018}, eprint={1804.00015}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```