--- tags: - espnet - audio - audio-to-audio language: en datasets: - wsj0_2mix license: cc-by-4.0 --- ## ESPnet2 ENH model ### `lichenda/wsj0_2mix_skim_small_causal` This model was trained by Chenda Li using wsj0_2mix recipe in [espnet](https://github.com/espnet/espnet/). ### Demo: How to use in ESPnet2 Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html) if you haven't done that already. ```bash cd espnet git checkout 3897ed8380bfb526d5c5dd2197eccbffbba7d8f8 pip install -e . cd egs2/wsj0_2mix/enh1 ./run.sh --skip_data_prep false --skip_train true --download_model lichenda/wsj0_2mix_skim_small_causal ``` # RESULTS ## Environments - date: `Wed May 10 20:30:26 CST 2023` - python version: `3.9.16 (main, Mar 8 2023, 14:00:05) [GCC 11.2.0]` - espnet version: `espnet 202304` - pytorch version: `pytorch 2.0.1` - Git hash: `3897ed8380bfb526d5c5dd2197eccbffbba7d8f8` - Commit date: `Tue May 9 13:27:37 2023 +0800` ## enh_train_enh_skim_causal_small_raw config: conf/tuning/train_enh_skim_causal_small.yaml |dataset|STOI|SAR|SDR|SIR|SI_SNR| |---|---|---|---|---|---| |enhanced_cv_min_8k|93.41|15.54|14.92|24.87|14.51| |enhanced_tt_min_8k|94.20|15.00|14.33|24.18|13.92| ## ENH config
expand ``` config: conf/tuning/train_enh_skim_causal_small.yaml print_config: false log_level: INFO dry_run: false iterator_type: chunk output_dir: exp/enh_train_enh_skim_causal_small_raw ngpu: 1 seed: 0 num_workers: 4 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: null dist_rank: null local_rank: 0 dist_master_addr: null dist_master_port: null dist_launcher: null multiprocessing_distributed: false 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: 50 val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - si_snr_loss - min - - valid - loss - min keep_nbest_models: 1 nbest_averaging_interval: 0 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_matplotlib: true use_tensorboard: true create_graph_in_tensorboard: false 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: 16 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: 32000,16000,8000 chunk_shift_ratio: 0.5 num_cache_chunks: 1024 chunk_excluded_key_prefixes: [] 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 exclude_weight_decay: false exclude_weight_decay_conf: {} optim: adam optim_conf: lr: 0.001 eps: 1.0e-08 weight_decay: 0 scheduler: steplr scheduler_conf: step_size: 2 gamma: 0.97 init: xavier_uniform model_conf: stft_consistency: false loss_type: mask_mse mask_type: null criterions: - name: si_snr conf: {} wrapper: pit wrapper_conf: weight: 1.0 independent_perm: true 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 dynamic_mixing: false utt2spk: null dynamic_mixing_gain_db: 0.0 encoder: conv encoder_conf: channel: 128 kernel_size: 8 stride: 4 separator: skim separator_conf: causal: true num_spk: 2 layer: 3 nonlinear: relu unit: 384 segment_size: 50 dropout: 0.0 mem_type: hc seg_overlap: false decoder: conv decoder_conf: channel: 128 kernel_size: 8 stride: 4 mask_module: multi_mask mask_module_conf: {} preprocessor: null preprocessor_conf: {} required: - output_dir version: '202304' distributed: false ```
### 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} } @inproceedings{liSkimSkippingMemory2022, title = {Skim: {{Skipping Memory Lstm}} for {{Low-Latency Real-Time Continuous Speech Separation}}}, shorttitle = {Skim}, booktitle = {{{ICASSP}} 2022 - 2022 {{IEEE International Conference}} on {{Acoustics}}, {{Speech}} and {{Signal Processing}} ({{ICASSP}})}, author = {Li, Chenda and Yang, Lei and Wang, Weiqin and Qian, Yanmin}, year = {2022}, month = may, pages = {681--685}, issn = {2379-190X}, doi = {10.1109/ICASSP43922.2022.9746372}, } ``` 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} } ```