Page 13 - 《应用声学》2025年第3期
P. 13

第 44 卷 第 3 期              雷菁等: 无人机搜救场景下语声增强技术进展综述                                           547


                 ics, Information, and Communication. IEEE, 2020: 1–5.  for improved speech capture using deep convolutional au-
             [27] Manamperi W N, Abhayapala T D, Samarasinghe P N, et  toencoder assisted multistage beamforming[C]//2022 25th
                 al. Drone audition: Audio signal enhancement from drone  International Conference on Information Fusion. IEEE,
                 embedded microphones using multichannel Wiener filter-  2022: 1–8.
                 ing and Gaussian-mixture based post-filtering[J]. Applied  [37] Morito T, Sugiyama O, Kojima R, et al.  Partially
                 Acoustics, 2024, 216: 109818.                     shared deep neural network in sound source separation
             [28] Tengan E, Dietzen T, Ruiz S, et al. Speech enhancement  and identification using a UAV-embedded microphone ar-
                 using ego-noise references with a microphone array em-  ray[C]//2016 IEEE/RSJ International Conference on In-
                 bedded in an unmanned aerial vehicle[C]//International  telligent Robots and Systems. IEEE, 2016: 1299–1304.
                 Congress on Acoustics, 2022: 133–143.          [38] Spadini T, Imai Aldeia G S, Barreto G, et al. On the ap-
             [29] Chun C J, Jeon K M, Kim T, et al. Drone noise reduction  plication of SEGAN for the attenuation of the ego-noise
                 using deep convolutional autoencoder for UAV acoustic  in the speech sound source localization problem[C]//2019
                 sensor networks[C]//2019 IEEE 16th International Con-  Workshop on Communication Networks and Power Sys-
                 ference on Mobile Ad Hoc and Sensor Systems Workshops.  tems. IEEE, 2019: 1–4.
                 IEEE, 2019: 168–169.                           [39] Wang L, Sanchez-Matilla R, Cavallaro A. Audio-visual
             [30] Chen X Y, Bi H W, Lai W T, et al. Monaural speech  sensing from a quadcopter: Dataset and baselines for
                 enhancement on drone via adapter based transfer learn-  source localization and sound enhancement[C]//2019
                 ing[C]//2024 18th International Workshop on Acoustic  IEEE/RSJ International Conference on Intelligent Robots
                 Signal Enhancement (IWAENC). IEEE, 2024: 85–89.   and Systems. IEEE, 2019: 5320–5325.
             [31] Zhao S K, Ma B, Watcharasupat K N, et al.  FR-  [40] Ruiz-Espitia O, Martinez-Carranza J, Rascon C. AIRA-
                 CRN: Boosting feature representation using frequency re-  UAS: An evaluation corpus for audio processing in un-
                 currence for monaural speech enhancement[C]//ICASSP  manned aerial system[C]//2018 International Conference
                 2022–2022 IEEE International Conference on Acoustics,  on Unmanned Aircraft Systems. IEEE, 2018: 836–845.
                 Speech and Signal Processing. IEEE, 2022: 9281–9285.  [41] Svanström F, Alonso-Fernandez F, Englund C. A dataset
             [32] Premachandra C, Kunisada Y. GAN based audio noise  for multi-sensor drone detection[J]. Data in Brief, 2021,
                 suppression for victim detection at disaster sites with  39: 107521.
                 UAV[J]. IEEE Transactions on Services Computing, 2024,  [42] Kolamunna H, Dahanayaka T, Li J Y, et al. DronePrint:
                 17(1): 183–193.                                   Acoustic signatures for open-set drone detection and iden-
             [33] Yen B, Hioka Y, Mace B. Improving power spectral den-  tification with online data[J]. Proceedings of the ACM on
                 sity estimation of unmanned aerial vehicle rotor noise by  Interactive, Mobile, Wearable and Ubiquitous Technolo-
                 learning from non-acoustic information[C]//2018 16th In-  gies, 2021, 5(1): 1–31.
                 ternational Workshop on Acoustic Signal Enhancement.  [43] Al-Emadi S, Al-Ali A, Mohammad A, et al.  Audio
                 IEEE, 2018: 545–549.                              based drone detection and identification using deep learn-
             [34] Yen B, Hioka Y, Schmid G, et al. Multi-sensory sound  ing[C]//2019 15th International Wireless Communica-
                 source enhancement for unmanned aerial vehicle record-  tions & Mobile Computing Conference.  IEEE, 2019:
                 ings[J]. Applied Acoustics, 2022, 189: 108590.    459–464.
             [35] Wang L, Cavallaro A. Deep learning assisted time-  [44] Sanchez-Matilla R, Wang L, Cavallaro A. Multi-modal
                 frequency processing for speech enhancement on drones[J].  localization and enhancement of multiple sound sources
                 IEEE Transactions on Emerging Topics in Computational  from a micro aerial vehicle[C]//Proceedings of the 25th
                 Intelligence, 2021, 5(6): 871–881.                ACM International Conference on Multimedia.  ACM,
             [36] Song Y J, Kindt S, Madhu N. Drone ego-noise cancellation  2017: 1591–1599.
   8   9   10   11   12   13   14   15   16   17   18