On Data Sampling Strategies for Training Neural Network Speech Separation Models

Ravenscroft, William; Goetze, Stefan; Hain, Thomas

doi:10.23919/eusipco58844.2023.10289800

Search citation statements

Order By: Relevance

Paper Sections

Select...

Training Configuration1

Evaluation Metrics1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Other3

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Training signal lengths (TSLs) are limited to 4s and randomly sampled from the original training example [23]. The feature dimension of the conformers layers are the same as the TD-Conformer-XL model in [9], i.e.…”

Section: Training Configurationmentioning

confidence: 99%

See 1 more Smart Citation

Combining Conformer and Dual-Path-Transformer Networks for Single Channel Noisy Reverberant Speech Separation

Ravenscroft,

Goetze,

Hain

2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

Section: Training Configurationmentioning

confidence: 99%

“…The computational complexity of models is assessed using mutiply-accumulate operations (MACs). MACs are computed on a signal length of 5.79s, equal to the mean signal length in the WHAMR and WSJ0-2Mix corpora [23]. Model size is reported in number of parameters.…”

Section: Evaluation Metricsmentioning

confidence: 99%

Combining Conformer and Dual-Path-Transformer Networks for Single Channel Noisy Reverberant Speech Separation

Ravenscroft,

Goetze,

Hain

2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments

Ravenscroft,

Goetze,

Hain

2023

2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

View full text Add to dashboard Cite

show abstract

Multi-CMGAN+/+: Leveraging Multi-Objective Speech Quality Metric Prediction for Speech Enhancement

Close,

Ravenscroft,

Hain

et al. 2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Neural network based approaches to speech enhancement have shown to be particularly powerful, being able to leverage a data-driven approach to result in a significant performance gain versus other approaches. Such approaches are reliant on artificially created labelled training data such that the neural model can be trained using intrusive loss functions which compare the output of the model with clean reference speech. Performance of such systems when enhancing real-world audio often suffers relative to their performance on simulated test data. In this work, a non-intrusive multi-metric prediction approach is introduced, wherein a model trained on artificial labelled data using inference of an adversarially trained metric prediction neural network. The proposed approach shows improved performance versus state-of-the-art systems on the recent CHiME-7 challenge unsupervised domain adaptation speech enhancement (UDASE) task evaluation sets.

show abstract

On Data Sampling Strategies for Training Neural Network Speech Separation Models

Abstract: This is a repository copy of On data sampling strategies for training neural network speech separation models.

Cited by 3 publications

References 23 publications

Combining Conformer and Dual-Path-Transformer Networks for Single Channel Noisy Reverberant Speech Separation

Combining Conformer and Dual-Path-Transformer Networks for Single Channel Noisy Reverberant Speech Separation

On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments

Multi-CMGAN+/+: Leveraging Multi-Objective Speech Quality Metric Prediction for Speech Enhancement

Contact Info

Product

Resources

About