Integrating Dilated Convolution into DenseLSTM for Audio Source Separation

• Main Authors: Woon-Haeng Heo, Hyemi Kim, Oh-Wook Kwon
• Format: Article
• Language: English
• Published: MDPI AG 2021-01-01
• Series: Applied Sciences
• Subjects: dilated convolution; audio source separation; speech enhancement; speech recognition; music signal separation; music identification
• Online Access: https://www.mdpi.com/2076-3417/11/2/789

Herein, we proposed a multi-scale multi-band dilated time-frequency densely connected convolutional network (DenseNet) with long short-term memory (LSTM) for audio source separation. Because the spectrogram of the acoustic signal can be thought of as images as well as time series data, it is suitable for convolutional recurrent neural network (CRNN) architecture. We improved the audio source separation performance by applying the dilated block with a dilated convolution to CRNN architecture. The dilated block has the role of effectively increasing the receptive field in the spectrogram. In addition, it was designed in consideration of the acoustic characteristics that the frequency axis and the time axis in the spectrogram are changed by independent influences such as speech rate and pitch. In speech enhancement experiments, we estimated the speech signal using various deep learning architectures from a signal in which the music, noise, and speech were mixed. We conducted the subjective evaluation on the estimated speech signal. In addition, speech quality, intelligibility, separation, and speech recognition performance were also measured. In music signal separation, we estimated the music signal using several deep learning architectures from the mixture of the music and speech signal. After that, the separation performance and music identification accuracy were measured using the estimated music signal. Overall, the proposed architecture shows the best performance compared to other deep learning architectures not only in speech experiments but also in music experiments.