تقرير
TridentSE: Guiding Speech Enhancement with 32 Global Tokens
العنوان: | TridentSE: Guiding Speech Enhancement with 32 Global Tokens |
---|---|
المؤلفون: | Yin, Dacheng, Zhao, Zhiyuan, Tang, Chuanxin, Xiong, Zhiwei, Luo, Chong |
سنة النشر: | 2022 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound |
الوصف: | In this paper, we present TridentSE, a novel architecture for speech enhancement, which is capable of efficiently capturing both global information and local details. TridentSE maintains T-F bin level representation to capture details, and uses a small number of global tokens to process the global information. Information is propagated between the local and the global representations through cross attention modules. To capture both inter- and intra-frame information, the global tokens are divided into two groups to process along the time and the frequency axis respectively. A metric discriminator is further employed to guide our model to achieve higher perceptual quality. Even with significantly lower computational cost, TridentSE outperforms a variety of previous speech enhancement methods, achieving a PESQ of 3.47 on VoiceBank+DEMAND dataset and a PESQ of 3.44 on DNS no-reverb test set. Visualization shows that the global tokens learn diverse and interpretable global patterns. Comment: 5 pages, 2 figures, 3 tables |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2210.12995 |
رقم الأكسشن: | edsarx.2210.12995 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |