Double Compressed Wideband AMR Speech Detection Using Deep Neural Networks

被引:0
|
作者
Buker, Aykut [1 ]
Hanilci, Cemal [1 ]
机构
[1] Bursa Tech Univ, Dept Elect & Elect Engn, TR-16310 Bursa, Turkiye
关键词
Audio forensics; Wideband AMR codec; Double compressed AMR detection; Deep neural networks;
D O I
10.1007/s00034-024-02668-4
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Detecting double compressed (DC) speech signals is an important audio forensics task since it is highly related to the integrity and the authenticity of the recording. Adaptive multi-rate (AMR) speech codec is a popular audio compression technique specifically optimized for speech signals and it is a standard audio recording format in the vast majority of the smart phones. All of the previous studies addressing the detection of DC AMR signals report their findings for the speech signals compressed using the narrowband AMR codec (AMR-NB). Meanwhile, wideband AMR codec (AMR-WB) has been used by several mobile phone manufacturers, but DC AMR-WB speech signal detection performance remains unknown. To the best of our knowledge, this is the first study focusing on detecting the DC signals compressed using the AMR-WB speech codec. To this end, we propose three different deep neural network-based DC AMR-WB signal detection systems where the spectrogram representations of the speech signals are used as the input features. Experimental results conducted on TIMIT database provide several important findings regarding the DC AMR-WB speech detection. Firstly, DC AMR-WB detection is found to be a more challenging task than detecting the AMR-NB signals. For example, convolutional neural network (CNN)-based system yields 74.83% and 99.93% detection rates on AMR-WB and AMR-NB coded signals, respectively. Secondly, capturing the temporal information using long short-term memory (LSTM) network with the DC AMR-WB signal detection accuracy of 86.25% is found to be superior to the CNN system. Thirdly, combining the deep feature representations learned by CNN and LSTM networks further improves the performance. Fourthly, the detection rates are found to deteriorate when the signals are first encoded using different audio codecs prior to AMR-WB compression. Finally, applying score level or decision level fusion to the proposed three systems improves the detection rates, in general.
引用
收藏
页码:4528 / 4546
页数:19
相关论文
共 50 条
  • [31] Automatic Recognition of Kazakh Speech Using Deep Neural Networks
    Mamyrbayev, Orken
    Turdalyuly, Mussa
    Mekebayev, Nurbapa
    Alimhan, Keylan
    Kydyrbekova, Aizat
    Turdalykyzy, Tolganay
    INTELLIGENT INFORMATION AND DATABASE SYSTEMS, ACIIDS 2019, PT II, 2019, 11432 : 465 - 474
  • [32] Binaural Speech Intelligibility Estimation Using Deep Neural Networks
    Kondo, Kazuhiro
    Taira, Kazuya
    Kobayashi, Yosuke
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1858 - 1862
  • [33] STATISTICAL PARAMETRIC SPEECH SYNTHESIS USING DEEP NEURAL NETWORKS
    Zen, Heiga
    Senior, Andrew
    Schuster, Mike
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7962 - 7966
  • [34] PERCEPTUALLY GUIDED SPEECH ENHANCEMENT USING DEEP NEURAL NETWORKS
    Zhao, Yan
    Xu, Buye
    Giri, Ritwik
    Zhang, Tao
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5074 - 5078
  • [35] Speech Recognition Using Deep Neural Networks: A Systematic Review
    Nassif, Ali Bou
    Shahin, Ismail
    Attili, Imtinan
    Azzeh, Mohammad
    Shaalan, Khaled
    IEEE ACCESS, 2019, 7 : 19143 - 19165
  • [36] Enhancing analysis of diadochokinetic speech using deep neural networks
    Segal-Feldman, Yael
    Hitczenko, Kasia
    Goldrick, Matthew
    Buchwald, Adam
    Roberts, Angela
    Keshet, Joseph
    COMPUTER SPEECH AND LANGUAGE, 2025, 90
  • [37] Event Detection and Classification Using Deep Compressed Convolutional Neural Network
    Swapnika, K.
    Vasumathi, D.
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2022, 13 (12) : 312 - 322
  • [38] Speech Emotion Recognition using Convolution Neural Networks and Deep Stride Convolutional Neural Networks
    Wani, Taiba Majid
    Gunawan, Teddy Surya
    Qadri, Syed Asif Ahmad
    Mansor, Hasmah
    Kartiwi, Mira
    Ismail, Nanang
    PROCEEDING OF 2020 6TH INTERNATIONAL CONFERENCE ON WIRELESS AND TELEMATICS (ICWT), 2020,
  • [39] Event Detection and Classification Using Deep Compressed Convolutional Neural Network
    Swapnika, K.
    Vasumathi, D.
    International Journal of Advanced Computer Science and Applications, 2022, 13 (12): : 312 - 322
  • [40] The Representation of Speech in Deep Neural Networks
    Scharenborg, Odette
    van der Gouw, Nikki
    Larson, Martha
    Marchiori, Elena
    MULTIMEDIA MODELING, MMM 2019, PT II, 2019, 11296 : 194 - 205