Voice activity detection for audio signal of voyage data recorder using residue network and attention mechanism

References

• Bai S, Yan X. 2021. Low SNR speech endpoint detection based on Mel scale frequency cepstrum coefficient and short time energy. J Nanjing Normal Univ (Nat Sci Ed). 44(2):117–120.
   Google Scholar
• Cheliotis M, Lazakis I, Theotokatos G. 2020. Machine learning and data-driven fault detection for ship systems operations. Ocean Eng. 216:107968.
   Web of Science ®Google Scholar
• Chen H, Tian D, Yang Z, Wu Z, Zhao K, Li D, Ma X. 2016. An improved position errors test method of image recorded by voyage data recorder. In: International Conference on Modelling, Identification and Control. Algiers (Algeria): IEEE. p. 80–84.
   Google Scholar
• Davis S, Mermelstein P. 1980. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans Audio Speech Lang Process. 28(4):357–366.
   Google Scholar
• Geng QS, Wang FH, Zhou DX. 2019. Mechanical fault diagnosis of power transformer by GFCC time-frequency map of acoustic signal and convolutional neural network. In: IEEE Sustainable Power and Energy Conference. Beijing (China): IEEE. p. 2106–2110.
   Google Scholar
• He K, Zhang X, Ren S, Sun J. 2016. Identity mappings in deep residual networks. In: European Conference on Computer Vision. Amsterdam (The Netherlands): Springer. p. 630–645.
   Google Scholar
• Hidayat R, Bejo A, Sumaryono S, Winursito A. 2018. Denoising speech for MFCC feature extraction using Wavelet transformation in speech recognition system. In: International Conference on Information Technology and Electrical Engineering. Bali (Indonesia): IEEE. p. 280–284.
   Google Scholar
• JP JISC. 2021. Ships and marine technology – guidelines for the operation and installation of voyage data recorder (VDR).
   Google Scholar
• Juvela L, Bollepalli B, Wang X, Kameoka H, Airaksinen M, Yamagishi J, Alku P. 2018. Speech waveform synthesis from MFCC sequences with generative adversarial networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing. Calgary (AB): IEEE. p. 5679–5683.
   Google Scholar
• Kingma DP, Ba J. 2015. Adam: a method for stochastic optimization. In: Bengio Y, LeCun Y, editors. International Conference on Learning Representations. San Diego (CA): ICLR.
   Google Scholar
• Lee Y, Min J, Han DK, Ko H. 2020. Spectro-temporal attention-based voice activity detection. IEEE Signal Proc Lett. 27:131–135.
   Web of Science ®Google Scholar
• Li Q, Zhu H, Qiao F, Wei Q, Liu X, Yang H. 2018. Energy-efficient MFCC extraction architecture in mixed-signal domain for automatic speech recognition. In: IEEE/ACM International Symposium on Nanoscale Architectures. Athens (Greece): IEEE. p. 1–3.
   Google Scholar
• Likitha MS, Gupta SRR, Hasitha K, Raju AU. 2017. Speech based human emotion recognition using MFCC. In: International Conference on Wireless Communications, Signal Processing and Networking. Xiamen (China): IEEE. p. 2257–2260.
   Google Scholar
• Liu S, Jiang N, Zhang L, Xu D. 2006. Research on the radar image compression of VDR based on SPIHT. In: International Conference on Mechatronics and Automation. Luoyang (China): IEEE. p. 2357–2361.
   Google Scholar
• Maurya A, Kumar D, Agarwal RK. 2018. Speaker recognition for Hindi speech signal using MFCC-GMM approach. Procedia Comput Sci. 125:880–887.
   Google Scholar
• Maya BND, Kurt RE. 2022. Marine accident learning with fuzzy cognitive maps: a method to model and weight human-related contributing factors into maritime accidents. Ships Offshore Struct. 17(3):555–563.
   Web of Science ®Google Scholar
• Mondal A, Prathosh A. 2020. RespVAD: voice activity detection via video-extracted respiration patterns. IEEE Sens Lett. 4(9):1–4.
   PubMedGoogle Scholar
• Ning Y, Zhao L, Zhang C, Yuan Z. 2022. STD-Yolov5: a ship-type detection model based on improved Yolov5. Ships Offshore Struct. 17:1–10.
   Google Scholar
• Pang J. 2017. Spectrum energy based voice activity detection. In: IEEE Annual Computing and Communication Workshop and Conference. Las Vegas (NV): IEEE. p. 1–5.
   Google Scholar
• Sasa K, Chen C, Fujimatsu T, Shoji R, Maki A. 2021. Speed loss analysis and rough wave avoidance algorithms for optimal ship routing simulation of 28, 000-DWT bulk carrier. Ocean Eng. 228:108800.
   Web of Science ®Google Scholar
• Shaw HJ, Lin CK. 2021. Marine big data analysis of ships for the energy efficiency changes of the hull and maintenance evaluation based on the ISO 19030 standard. Ocean Eng. 232:108953.
   Web of Science ®Google Scholar
• Tan X, Zhang XL. 2021. Speech enhancement aided end-to-end multi-task learning for voice activity detection. In: International Conference on Acoustics, Speech and Signal Processing. Toronto (ON): IEEE. p. 6823–6827.
   Google Scholar
• Tapkir PA, Patil AT, Shah N, Patil HA. 2018. Novel spectral root cepstral features for replay spoof detection. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Honolulu (HI): IEEE. p. 1945–1950.
   Google Scholar
• Teo JH, Cheng S, Alioto M. 2020. Low-energy voice activity detection via energy-quality scaling from data conversion to machine learning. IEEE Trans Circuits Syst I Fundam Theory Appl. 67(4):1378–1388.
   Google Scholar
• Unnikrishnan MV, Rajan R. 2017. Mimicking voice recognition using MFCC-GMM framework. In: International Conference on Trends in Electronics and Informatics. Tirunelveli (India): IEEE. p. 301–304.
   Google Scholar
• Valin JM. 2018. A hybrid DSP/deep learning approach to real-time full-band speech enhancement. In: IEEE 20th International Workshop on Multimedia Signal Processing. Vancouver (BC): IEEE. p. 1–5.
   Google Scholar
• Wang H. 2017. Two-step judgment algorithm for robust voice activity detection based on deep neural networks. In: International Conference on Computer Technology, Electronics and Communication. Dalian (China): IEEE. p. 452–455.
   Google Scholar
• Wang H, Xu Y, Li M. 2011. Study on the MFCC similarity-based voice activity detection algorithm. In: International Conference on Artificial Intelligence, Management Science and Electronic Commerce. Zhengzhou (China): IEEE. p. 4391–4394.
   Google Scholar
• Wu B, Li G, Wang T, Hildre HP, Zhang H. 2021. Sailing status recognition to enhance safety awareness and path routing for a commuter ferry. Ships Offshore Struct. 16(1):1–12.
   Google Scholar
• Yang Y, Chen P, Ding K, Chen Z, Hu K. 2022. Object detection of inland waterway ships based on improved SSD model. Ships Offshore Struct. 17(8):1–9.
   Google Scholar
• Yang Y, Ding K, Chen Z. 2022. Ship classification based on convolutional neural networks. Ships Offshore Struct. 17(12):2715–2721.
   Web of Science ®Google Scholar
• Yu H, Zhu WP, Champagne B. 2020. Speech enhancement using a DNN-augmented colored-noise Kalman filter. Speech Commun. 125:142–151.
   Web of Science ®Google Scholar
• Yu Y, Kim YJ. 2018. A voice activity detection model composed of Bidirectional LSTM and attention mechanism. In: International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management. Baguio City (Philippines): IEEE. p. 1–5.
   Google Scholar
• Zaw TH, War N. 2017. The combination of spectral entropy, zero crossing rate, short time energy and linear prediction error for voice activity detection. In: International Conference of Computer and Information Technology. Dhaka (Bangladesh): IEEE. p. 1–5.
   Google Scholar
• Zhang Y, Xing L. 2016. Research on speech endpoint detection algorithm based on Wavelet analysis and PSO-ELM. J North Univ of China (Nat Sci Ed). 37(1):33–38.
   Google Scholar
• Zhao X, Shao Y, Wang D. 2012. Research on speech endpoint detection algorithm based on wavelet analysis and PSO-ELM. IEEE/ACM Trans Audio Speech Lang Process. 20(5):1608–1616.
   Google Scholar
• Zhu M, Wu X, Lu Z, Wang T, Zhu X. 2019. Long-term speech information based threshold for voice activity detection in massive microphone network. Digit Signal Process. 94:156–164.
   Web of Science ®Google Scholar