期刊名： Signals

期刊主页：https://www.mdpi.com/journal/signals

音频与声学信号处理技术的持续演进正推动声音感知系统从传统固定场景采集向多源、跨域、鲁棒化的信号解析与智能识别方向发展。本专题汇集了发表于Signals的系列研究，系统展示了声学信号处理在音乐信号解析、语音技术、声学事件监测以及声学器件设计等多元场景的创新应用。研究涵盖了从时频掩蔽、迁移学习、图注意力网络、CNN-LSTM 与注意力增强模型等核心算法与声学建模突破，共同描绘了声学信号感知赋能智能音频、声学监测与语音健康应用的未来图景。

1. Adaptive Filtering for Multi-Track Audio Based on Time–Frequency Masking Detection

基于时频掩蔽检测的多轨音频自适应滤波

https://www.mdpi.com/2624-6120/5/4/35

Zhao, W.; Pérez-Cota, F. Adaptive Filtering for Multi-Track Audio Based on Time–Frequency Masking Detection. Signals 2024, 5, 633-641.

2. Interpretability of Methods for Switch Point Detection in Electronic Dance Music

电子舞曲切换点检测方法的可解释性研究

https://doi.org/10.3390/signals5040036

Zehren, M.; Alunno, M.; Bientinesi, P. Interpretability of Methods for Switch Point Detection in Electronic Dance Music. Signals 2024, 5, 642-658.

3. Acoustic Rocket Signatures Collected by Smartphones

智能手机采集的火箭声学特征

https://doi.org/10.3390/signals6010005

Popenhagen, S.K.; Garcés, M.A. Acoustic Rocket Signatures Collected by Smartphones. Signals 2025, 6, 5.

4. Speech Emotion Recognition: Comparative Analysis of CNN-LSTM and Attention-Enhanced CNN-LSTM Models

语音情感识别：CNN-LSTM 与注意力增强 CNN-LSTM 模型对比分析

https://doi.org/10.3390/signals6020022

Bhanbhro, J.; Memon, A.A.; Lal, B.; Talpur, S.; Memon, M. Speech Emotion Recognition: Comparative Analysis of CNN-LSTM and Attention-Enhanced CNN-LSTM Models. Signals 2025, 6, 22.

5. Multi-Instance Multi-Scale Graph Attention Neural Net with Label Semantic Embeddings for Instrument Recognition

面向乐器识别的带标签语义嵌入多实例多尺度图注意力神经网络

https://doi.org/10.3390/signals6030030

Bai, N.; Wu, Z.; Zhang, J. Multi-Instance Multi-Scale Graph Attention Neural Net with Label Semantic Embeddings for Instrument Recognition. Signals 2025, 6, 30.

6. Rocket Launch Detection with Smartphone Audio and Transfer Learning

基于智能手机音频与迁移学习的火箭发射检测

https://doi.org/10.3390/signals6030041

Popenhagen, S.K.; Takazawa, S.K.; Garcés, M.A. Rocket Launch Detection with Smartphone Audio and Transfer Learning. Signals 2025, 6, 41.

7. Vibro-Acoustic Characterization of Additively Manufactured Loudspeaker Enclosures: A Parametric Study of Material and Infill Influence

增材制造扬声器腔体的振声特性：材料与填充影响的参数化研究

https://doi.org/10.3390/signals6040073

Konopiński, J.; Sosiński, P.; Wanat, M.; Góral, P. Vibro-Acoustic Characterization of Additively Manufactured Loudspeaker Enclosures: A Parametric Study of Material and Infill Influence. Signals 2025, 6, 73.

8. Quantifying the Relationship Between Speech Quality Metrics and Biometric Speaker Recognition Performance Under Acoustic Degradation

声学劣化条件下语音质量指标与生物特征说话人识别性能的量化关系

https://doi.org/10.3390/signals7010007

Ahmed, A.; Imtiaz, M.H. Quantifying the Relationship Between Speech Quality Metrics and Biometric Speaker Recognition Performance Under Acoustic Degradation. Signals 2026, 7, 7.

9. Multitrack Music Transcription Based on Joint Learning of Onset and Frame Streams

基于起始点与帧流联合学习的多轨音乐转录

https://doi.org/10.3390/signals7010012

Matsunaga, T.; Saito, H. Multitrack Music Transcription Based on Joint Learning of Onset and Frame Streams. Signals 2026, 7, 12.

10. A Spectral Entropy-Based Metric for Evaluating Speech Perceptual Quality with Emphasis on Spectral Coherence

侧重谱相干性的基于谱熵的语音感知质量评价指标

https://doi.org/10.3390/signals7020027

Sarafnia, A.; Ahmad, M.O.; Swamy, M.N.S. A Spectral Entropy-Based Metric for Evaluating Speech Perceptual Quality with Emphasis on Spectral Coherence. Signals 2026, 7, 27.

11. Evaluating the Performance of eGeMAPS Features in Detecting Depression Using Resampling Methods

基于重采样方法评估 eGeMAPS 特征的抑郁识别性能

https://doi.org/10.3390/signals7030041

Turnipseed, J.; Fonseca, B.J.B., Jr. Evaluating the Performance of eGeMAPS Features in Detecting Depression Using Resampling Methods. Signals 2026, 7, 41

12. Investigating Sibilant Fricative Representation in Bangla Telemedicine Speech: A Cost-Aware Sampling Rate Optimization Study

孟加拉语远程医疗语音中擦音表征研究：兼顾成本的采样率优化

https://doi.org/10.3390/signals7030044

Paul, P.; Bouh, M.M.; Shah, M.V.; Hossain, F.; Ahmed, A. Investigating Sibilant Fricative Representation in Bangla Telemedicine Speech: A Cost-Aware Sampling Rate Optimization Study. Signals 2026, 7, 44.

13. Spectral Bandwidth Effects on Emotion Classification and Representation in Spoken and Sung Signals

谱带宽对语音与歌唱信号情感分类及表征的影响

https://doi.org/10.3390/signals7030050

Garlitz, R.; Shamsi, A.; Wayland, R. Spectral Bandwidth Effects on Emotion Classification and Representation in Spoken and Sung Signals. Signals 2026, 7, 50.

14. Real-Time Emergency Response for High-Speed Aircraft Explosions: An Acoustic Search Engine for Aliased Source Identification

高速飞行器爆炸实时应急响应：用于混叠声源识别的声学检索引擎

https://doi.org/10.3390/signals7030051

Shen, Y.; Liang, X.; Hu, X.; Wang, S. Real-Time Emergency Response for High-Speed Aircraft Explosions: An Acoustic Search Engine for Aliased Source Identification. Signals 2026, 7, 51.

15. Spectral Entropy-Based Design of a First-Order Differential Microphone Array

基于谱熵的一阶差分麦克风阵列设计

https://doi.org/10.3390/signals7040065

Sarafnia, A.; Ahmad, M.O.; Swamy, M.N.S. Spectral Entropy-Based Design of a First-Order Differential Microphone Array. Signals 2026, 7, 65.

16. Emotion Recognition Using Acoustic Features and Deep Learning: A Speaker-Independent Study

基于声学特征与深度学习的情感识别：说话人无关研究

https://www.mdpi.com/2624-6120/7/4/69

Kolodziej, M.; Majkowski, A.; Rywik, T. Emotion Recognition Using Acoustic Features and Deep Learning: A Speaker-Independent Study. Signals 2026, 7, 69.

期刊介绍

主编：Prof. Dr. Santiago Marco

Signals 是 MDPI 开放获取同行评审期刊，专注信号理论、信号处理及其跨学科应用。期刊接收原创论文、综述等文章，涵盖音频声学、语音感知、生物医学信号、智能传感等方向，重视算法创新与工程落地。期刊定期推出特色专题，成果发表后可免费在线阅览，为全球信号处理领域学者提供开放的学术交流平台。

2025 Impact Factor：2.9

2025 CiteScore：5.9

Time to First Decision：28.6 Days

Acceptance to Publication：14.8 Days