--- tags: - espnet - audio - audio-to-audio language: en datasets: - l3das22 license: cc-by-4.0 --- ## ESPnet2 ENH model ### `espnet/Yen-Ju_Lu_l3das22_enh_train_enh_ineube_valid.loss.ave` This model was trained by neillu23 using l3das22 recipe in [espnet](https://github.com/espnet/espnet/). ### Demo: How to use in ESPnet2 ```bash cd espnet git checkout 11d687844a544fcce6f6d0ce7a0a302e0e47d442 pip install -e . cd egs2/l3das22/enh1 ./run.sh --skip_data_prep false --skip_train true --download_model espnet/Yen-Ju_Lu_l3das22_enh_train_enh_ineube_valid.loss.ave ``` # RESULTS ## Environments - date: `Wed Jul 6 20:46:10 UTC 2022` - python version: `3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0]` - espnet version: `espnet 202205` - pytorch version: `pytorch 1.8.1` - Git hash: `77e36afdd3f069567dd33d4b5b997a26b634772b` - Commit date: `Fri Jun 17 18:32:56 2022 -0400` ## enh_train_enh_ineube_raw config: conf/tuning/train_enh_ineube.yaml |dataset|STOI|SAR|SDR|SIR|SI_SNR|WER|STOI|TASK 1 METRIC| |---|---|---|---|---|---|---|---|---| |enhanced_dev_multich|95.62|15.00|15.00|0.00|13.64|5.93|0.956|0.948| |enhanced_test_multich|95.70|14.59|14.59|0.00|13.34|4.85|0.957|0.954| ## ENH config
expand ``` config: conf/tuning/train_enh_ineube.yaml print_config: false log_level: INFO dry_run: false iterator_type: chunk output_dir: exp/enh_train_enh_ineube_raw ngpu: 1 seed: 0 num_workers: 4 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: 3 dist_rank: 0 local_rank: 0 dist_master_addr: localhost dist_master_port: 50409 dist_launcher: null multiprocessing_distributed: true unused_parameters: true sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 100 patience: 20 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 nbest_averaging_interval: 0 grad_clip: 5 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_matplotlib: true use_tensorboard: true use_wandb: false wandb_project: null wandb_id: null wandb_entity: null wandb_name: null wandb_model_log_interval: -1 detect_anomaly: false pretrain_path: null init_param: [] ignore_init_mismatch: false freeze_param: [] num_iters_per_epoch: null batch_size: 15 valid_batch_size: null batch_bins: 1000000 valid_batch_bins: null train_shape_file: - exp/enh_stats_16k/train/speech_mix_shape - exp/enh_stats_16k/train/speech_ref1_shape valid_shape_file: - exp/enh_stats_16k/valid/speech_mix_shape - exp/enh_stats_16k/valid/speech_ref1_shape batch_type: folded valid_batch_type: null fold_length: - 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/train_multich/wav.scp - speech_mix - sound - - dump/raw/train_multich/spk1.scp - speech_ref1 - sound valid_data_path_and_name_and_type: - - dump/raw/dev_multich/wav.scp - speech_mix - sound - - dump/raw/dev_multich/spk1.scp - speech_ref1 - 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: 1.0e-07 scheduler: reducelronplateau scheduler_conf: mode: min factor: 0.5 patience: 20 init: xavier_uniform model_conf: stft_consistency: false loss_type: mask_mse mask_type: null criterions: - name: snr conf: {} wrapper: fixed_order wrapper_conf: weight: 1.0 use_preprocessor: false speech_volume_normalize: null rir_scp: null rir_apply_prob: 1.0 noise_scp: null noise_apply_prob: 1.0 noise_db_range: '13_15' short_noise_thres: 0.5 use_reverberant_ref: false num_spk: 1 num_noise_type: 1 sample_rate: 8000 force_single_channel: false encoder: same encoder_conf: {} separator: ineube separator_conf: n_fft: 512 stride: 128 window: hann mic_channels: 8 decoder: same decoder_conf: {} mask_module: multi_mask mask_module_conf: {} required: - output_dir version: '202205' 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} } ```