wsj0_2mix_skim_small_causal Open-source Speech Enhancement Model - Free Deployment for Separating Mixed Speech Signals

Wsj0 2mix Skim Small Causal

Developed by lichenda

This is a speech enhancement model trained based on the ESPnet framework, specifically designed for speech separation tasks in the wsj0_2mix dataset.

Audio Enhancement English#Real-time speech enhancement #Causal model #Low-latency processing

Downloads 26

Release Time : 5/17/2023

Model Overview

The model adopts a skim architecture with causal processing capabilities, suitable for real-time speech enhancement scenarios, effectively separating different speaker signals from mixed speech.

Model Features

Causal processing capability

The model features a causal structure design, making it suitable for real-time speech processing applications

Lightweight architecture

Small skim architecture design reduces computational complexity while maintaining performance

Multi-speaker separation

Capable of effectively separating signals from two speakers in mixed speech

Model Capabilities

Speech enhancement

Speaker separation

Real-time speech processing

Use Cases

Voice communication

Conference speech enhancement

Separating voices of different speakers in multi-person meeting scenarios

STOI metric reaches 94.20, SDR metric 14.33

Speech recognition preprocessing

ASR front-end processing

Providing cleaner input signals for speech recognition systems

Improves speech recognition system accuracy in noisy environments

🚀 ESPnet2 ENH model

This is an ESPnet2 ENH model. It was trained by Chenda Li using the wsj0_2mix recipe in espnet, which is useful for audio - to - audio processing.

🚀 Quick Start

Demo: How to use in ESPnet2

Follow the ESPnet installation instructions if you haven't done that already.

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

📚 Documentation

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

@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:

@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}
}

📄 License

This model is under the cc-by-4.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご