2015 · 15 citations · 15 references
ComputingComputer ScienceAcousticsComputer VisionMachine LearningAcoustic Signal ProcessingAudio RecordingDeep LearningSound RecordingDeep Learning DetectionDetectionDropoutDropout ModelingError Rate AnalysisSplicing Detection
Since the audio recapture can be used to assist audio splicing, it is important to identify whether a suspected audio recording is recaptured or not. However, few works on such detection have been reported. In this paper, we propose an method to detect the recaptured audio based on deep learning and we investigate two deep learning techniques, i.e., neural network with dropout method and stack auto-encoders (SAE). The waveform samples of audio frame is directly used as the input for the deep neural network. The experimental results show that error rate around 7.5% can be achieved, which indicates that our proposed method can successfully discriminate recaptured audio and original audio.
15
Extracting and composing robust features with denoising autoencoders
Pascal Vincent, Hugo Larochelle, Yoshua Bengio et al. · 2008 · 7.3K citations
Spoofing and countermeasures for speaker verification: A survey
Zhizheng Wu, Nicholas Evans, Tomi Kinnunen et al. · Speech Communication · 2014 · 599 citations
Prediction as a candidate for learning deep hierarchical models of data
Rasmus Palm · 2012 · 386 citations