For: The paper aims to improve speech intelligibility in noisy environments for individuals with severe sensorineural hearing loss using bilateral cochlear implants (BiCI).* Methods: The authors propose a deep-learning-based bilateral speech enhancement model that shares information between both hearing sides, connecting two monaural end-to-end deep denoising sound coding techniques through intermediary latent fusion layers.* Results: The proposed fused BiCI sound coding strategy achieves higher interaural coherence, superior noise reduction, and enhanced predicted speech intelligibility scores compared to the baseline methods, with speech-in-noise intelligibility results in BiCI users revealing scores similar to those achieved in quiet conditions.Here’s the information in Simplified Chinese text:* For: 这篇论文目标是为患有严重感觉听力障碍的人群提高噪音环境中的语音理解能力，使用双侧听力Implant（BiCI）。* Methods: 作者提议一种基于深度学习的双侧语音提升模型，将两侧听力端的端到端深度噪音减除技术相互连接，通过中间潜在融合层。* Results: 提议的融合BiCI声码策略比基线方法更高的interaural coherence、更好的噪音减除和提高预测语音理解能力分数，在BiCI用户中的语音在噪音环境中的理解能力也达到了静音环境的水平。Abstract
Cochlear implants (CIs) provide a solution for individuals with severe sensorineural hearing loss to regain their hearing abilities. When someone experiences this form of hearing impairment in both ears, they may be equipped with two separate CI devices, which will typically further improve the CI benefits. This spatial hearing is particularly crucial when tackling the challenge of understanding speech in noisy environments, a common issue CI users face. Currently, extensive research is dedicated to developing algorithms that can autonomously filter out undesired background noises from desired speech signals. At present, some research focuses on achieving end-to-end denoising, either as an integral component of the initial CI signal processing or by fully integrating the denoising process into the CI sound coding strategy. This work is presented in the context of bilateral CI (BiCI) systems, where we propose a deep-learning-based bilateral speech enhancement model that shares information between both hearing sides. Specifically, we connect two monaural end-to-end deep denoising sound coding techniques through intermediary latent fusion layers. These layers amalgamate the latent representations generated by these techniques by multiplying them together, resulting in an enhanced ability to reduce noise and improve learning generalization. The objective instrumental results demonstrate that the proposed fused BiCI sound coding strategy achieves higher interaural coherence, superior noise reduction, and enhanced predicted speech intelligibility scores compared to the baseline methods. Furthermore, our speech-in-noise intelligibility results in BiCI users reveal that the deep denoising sound coding strategy can attain scores similar to those achieved in quiet conditions.
摘要
针对严重的感觉肾膜听力损伤，听力导管（CI）提供了一种解决方案，帮助人们恢复听力能力。当患者双侧听力都受到损伤时，可以安装两个独立的CI设备，通常会进一步提高CI的效果。这种空间听力特别重要，因为听力损伤者在噪声环境中理解语音是一个普遍的问题。目前，研究人员正在努力开发自动过滤噪声的算法，以提高CI用户对语音的理解能力。在这种情况下，我们提出了一种基于深度学习的双侧语音增强模型，该模型将两个单侧的听力侧连接起来，共享信息。具体来说，我们将两个独立的末端到端深度减噪听音编码技术相互 multiply ogether，以实现更好地减少噪声和提高学习普遍性。对比基eline方法，我们的提议的融合BiCI听力编码策略得到了更高的同耳相关性、更好的噪声减少和更高的预测语音认知度。此外，我们的BiCI用户语音在噪声环境中的认知结果表明，深度减噪听音编码策略可以达到类似于静音环境下的成绩。