论文标题
降低关节噪音和听力增强，以增强全端语音
Joint Noise Reduction and Listening Enhancement for Full-End Speech Enhancement
论文作者
论文摘要
语音增强（SE）方法主要集中于从嘈杂输入中恢复干净的语音。然而，在现实世界中的语音交流中，噪音不仅在说话者，而且在听众环境中存在。尽管SE方法可以抑制扬声器声音中包含的噪音，但它们无法处理侦听器侧面存在的噪音。为了解决这种复杂但常见的情况，我们研究了一个基于学习的基于学习的关节框架，将降噪（NR）与听力增强（LE）相结合，其中NR模块首先抑制了噪声，然后LE模块会修改DeNOCE的语音，即NR模块的输出，以进一步提高语音清晰度。因此，增强的语音对于听众来说可能不那么嘈杂，更可理解。实验结果表明，我们提出的方法可以实现有希望的结果，并在各种语音评估指标方面显着优于脱节处理方法。
Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input. In real-world speech communication, however, noises often exist in not only speaker but also listener environments. Although SE methods can suppress the noise contained in the speaker's voice, they cannot deal with the noise that is physically present in the listener side. To address such a complicated but common scenario, we investigate a deep learning-based joint framework integrating noise reduction (NR) with listening enhancement (LE), in which the NR module first suppresses noise and the LE module then modifies the denoised speech, i.e., the output of the NR module, to further improve speech intelligibility. The enhanced speech can thus be less noisy and more intelligible for listeners. Experimental results show that our proposed method achieves promising results and significantly outperforms the disjoint processing methods in terms of various speech evaluation metrics.
