Abstract
Deep learning residue echo suppression (RES) exhibits superior performance compared with traditional methods in recent years. However, a low-resource system or preemptive multi-tasking system requires low-complexity model that should be very computationally efficient to reduce race-condition issues which could cause system delay jitter and echo delay changes. In this paper we do an extensive study on low-complexity recurrent network models with different topologies, feed in with different combinations of the far-end signal, microphone signal, predicted linear echo and residue error signal. The proposed RES models can achieve comparable echo cancellation and noise reduction capabilities to the AEC Challenge 2022 baseline model at a complexity lower than 5% of the baseline model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sridhar, K., et al.: ICASSP 2021 acoustic echo cancellation challenge: datasets, testing framework, and results. In: ICASSP 2022, Singapore, Singapore, pp. 9107–9111 (2022)
Valin, J.-M., et al.: Low-complexity, real-time joint neural echo control and speech enhancement based on percepnet. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2021)
Peng, R., et al.: ICASSP 2021 acoustic echo cancellation challenge: integrated adaptive echo cancellation with time alignment and deep learning-based residual echo plus noise suppression. In: ICASSP 2021, Toronto, Canada, pp. 146–150 (2021)
Halimeh, M.M., et al.: Combining adaptive filtering and complex-valued deep postfiltering for acoustic echo cancellation. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2021)
Zhang, G., et al.: Multi-scale temporal frequency convolutional network with axial attention for speech enhancement. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2022)
Zhao, H., et al.: A deep hierarchical fusion network for fullband acoustic echo cancellation. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2022)
Zhang, S., et al.: Multi-task deep residual echo suppression with echo-aware loss. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2022)
Sun, X., et al.: Explore relative and context information with transformer for joint acoustic echo cancellation and speech enhancement. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2022)
Zhao, H., et al.: A low-latency deep hierarchical fusion network for fullband acoustic echo cancellation. In: ICASSP 2023–2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023)
Chen, Z., et al.: A progressive neural network for acoustic echo cancellation. In: ICASSP 2023–2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023)
Sun, J., et al.: Multi-task sub-band network for deep residual echo suppression. In: ICASSP 2023–2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023)
Xu, W., Guo, Z.: Tayloraecnet: a taylor style neural network for full-band echo cancellation. In: ICASSP 2023–2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023)
Zhang, Z., et al.: Two-step band-split neural network approach for full-band residual echo suppression. In: ICASSP 2023–2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023)
Chen, H., et al.: Ultra dual-path compression for joint echo cancellation and noise suppression. ar**v preprint ar**v:2308.11053 (2023)
Pfeifenberger, L., Pernkopf, F.: Nonlinear residual echo suppression using a recurrent neural network. In: Interspeech, pp. 3950–3954 (2020)
Valin, J.-M.: A hybrid DSP/deep learning approach to real-time full-band speech enhancement. In: 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP), Vancouver, BC, Canada, pp. 1–5 (2018)
Voelcker, B., Kleijn, W.B.: Robust and low complexity delay estimation. In: IWAENC 2012; International Workshop on Acoustic Signal Enhancement, Aachen, Germany, pp. 1–4 (2012)
Speex-dsp. Website. Accessed 12 Feb 2023. https://github.com/xiph/speexdsp
Loizou, P.C.: Speech Enhancement: Theory and Practice, pp. 1–394. CRC Press, Taylor Francis Group, Boca Raton (2007)
Sridhar, K., et al.: ICASSP 2021 acoustic echo cancellation challenge: Datasets, testing framework, and results. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhou, J., Gao, Y., Zhang, S. (2024). Ultra-Low Complexity Residue Echo and Noise Suppression Based on Recurrent Neural Network. In: Jia, J., Ling, Z., Chen, X., Li, Y., Zhang, Z. (eds) Man-Machine Speech Communication. NCMMSC 2023. Communications in Computer and Information Science, vol 2006. Springer, Singapore. https://doi.org/10.1007/978-981-97-0601-3_1
Download citation
DOI: https://doi.org/10.1007/978-981-97-0601-3_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0600-6
Online ISBN: 978-981-97-0601-3
eBook Packages: Computer ScienceComputer Science (R0)