Semantic Communication Systems for Speech Transmission

计算机科学 语音识别 传输(电信) 频道(广播) 通信系统 失真(音乐) 人工神经网络 适应(眼睛) 人工智能 电信 带宽(计算) 放大器 物理 光学
作者
Zhenzi Weng,Zhijin Qin
出处
期刊:IEEE Journal on Selected Areas in Communications [Institute of Electrical and Electronics Engineers]
卷期号:39 (8): 2434-2444 被引量:490
标识
DOI:10.1109/jsac.2021.3087240
摘要

Semantic communications could improve the transmission efficiency significantly by exploring the semantic information. In this paper, we make an effort to recover the transmitted speech signals in the semantic communication systems, which minimizes the error at the semantic level rather than the bit or symbol level. Particularly, we design a deep learning (DL)-enabled semantic communication system for speech signals, named DeepSC-S. In order to improve the recovery accuracy of speech signals, especially for the essential information, DeepSC-S is developed based on an attention mechanism by utilizing a squeeze-and-excitation (SE) network. The motivation behind the attention mechanism is to identify the essential speech information by providing higher weights to them when training the neural network. Moreover, in order to facilitate the proposed DeepSC-S for dynamic channel environments, we find a general model to cope with various channel conditions without retraining. Furthermore, we investigate DeepSC-S in telephone systems as well as multimedia transmission systems to verify the model adaptation in practice. The simulation results demonstrate that our proposed DeepSC-S outperforms the traditional communications in both cases in terms of the speech signals metrics, such as signal-to-distortion ration and perceptual evaluation of speech distortion. Besides, DeepSC-S is more robust to channel variations, especially in the low signal-to-noise (SNR) regime.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
mingyu发布了新的文献求助10
1秒前
1秒前
1秒前
jgwang发布了新的文献求助10
1秒前
1秒前
1秒前
2秒前
小李完成签到,获得积分10
2秒前
2秒前
huangbs发布了新的文献求助20
2秒前
jgwang发布了新的文献求助10
3秒前
传奇3应助忧郁绿柏采纳,获得10
3秒前
jgwang发布了新的文献求助10
4秒前
4秒前
5秒前
jgwang发布了新的文献求助10
5秒前
shadow发布了新的文献求助10
6秒前
6秒前
jgwang发布了新的文献求助10
7秒前
7秒前
万能图书馆应助YoYo采纳,获得10
7秒前
小琳有福气发布了新的文献求助150
8秒前
jgwang发布了新的文献求助10
8秒前
王木山发布了新的文献求助10
8秒前
会飞的猪发布了新的文献求助30
9秒前
9秒前
orixero应助玉树临风采纳,获得10
10秒前
科研通AI6.4应助superbia采纳,获得10
10秒前
Cristina2024完成签到,获得积分10
11秒前
希望天下0贩的0应助henguai采纳,获得10
11秒前
11秒前
忧郁绿柏完成签到,获得积分10
13秒前
13秒前
李健的小迷弟应助Sulphates采纳,获得10
13秒前
14秒前
Akim应助传统的复天采纳,获得10
14秒前
和谐凌波发布了新的文献求助10
14秒前
超级的超短裙关注了科研通微信公众号
16秒前
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Autoparametric Resonance in Mechanical Systems 1000
Effects of Two Weeks of Red Light Therapy on Choroidal Thickness and Axial Length in Young Adults 700
2026人教社中小学心理健康教育读本高中全一册电子版 600
Cosmos as Art Object: Studies in Plato's Timaeus and Other Dialogues 600
Management and the Arts 510
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7665959
求助须知:如何正确求助?哪些是违规求助? 9235667
关于积分的说明 19875006
捐赠科研通 7234941
什么是DOI,文献DOI怎么找? 3283649
关于科研通互助平台的介绍 2442395
邀请新用户注册赠送积分活动 2284795