Adversarial Learning For End-To-End Cochlear Speech Denoising Using Lightweight Deep Learning Models
Gajecki, T.; Nogueira, W.
Show abstract
This paper investigates an end-to-end speech signal denoising approach for cochlear implants (CIs). Building on previous work, we first explore the effect of relocating the deep envelope detector within the deep learning-based CI sound coding strategy, moving it from the skip connection to the output of the masking operation. This modification enables high-resolution time-frequency masking and optimizes noise reduction. Next, we introduce a discriminator network to further enhance the model by enforcing the generation of higher-quality electrodograms (i.e., the electric pulse patterns that stimulate the auditory nerve). This adversarial learning approach improves the generation of electrodograms and has the potential to enhance speech understanding for CI users. Objective evaluations, including signal-to-noise ratio improvement and linear cross-correlation coefficients, demonstrate that these enhancements significantly boost the performance of the end-to-end CI speech-denoising algorithm while reducing its parameter count, making it suitable for real-time applications.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Linear versus deep learning methods for noisy speech separation for EEG-informed attention decoding 98%
- 'Are you even listening?' - EEG-based decoding of absolute auditory attention to natural speech 96%
- Speech decoding from a small set of spatially segregated minimally invasive intracranial EEG electrodes with a compact and interpretable neural network 96%
Similar papers in this journal
- 3 Directional Inception-ResUNet: deep spatial feature learning for multichannel singing voice separation with distortion 97%
- DISCO: A deep learning ensemble for uncertainty-aware segmentation of acoustic signals 95%
- Exploring the distribution of statistical feature parameters for natural sound textures 95%
Similar papers in this journal
- Chirp analyzer for estimating amplitude and latency of steady-state auditory envelope following responses 94%
- Adaptive single-channel EEG artifact removal with applications to clinical monitoring 93%
- ScoreNet: A Neural network-based post-processing model for identifying epileptic seizure onset and offset in EEGs 93%
Similar papers in this journal
- Deep Learning Restores Speech Intelligibility in Multi-Talker Interference for Cochlear Implant Users 96%
- Comparison of Two-Talker Attention Decoding from EEG with Nonlinear Neural Networks and Linear Methods 96%
- Bridging Auditory Perception and Natural Language Processing with Semantically informed Deep Neural Networks 94%
Similar papers in this journal
- Algorithms for Estimating Time-Locked Neural Response Components in Cortical Processing of Continuous Speech 93%
- Resource-efficient Neural Network Architectures forClassifying Nerve Cuff Recordings on Implantable Devices 92%
- Assessing the robustness of deep learning based brain age prediction models across multiple EEG datasets 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.