Speech Enhancement Using Convolutional Denoising Autoencoder

Shahriyar, Shaikh Akib; Akhand, M. A. H.; Siddique, Nazmul; Shimamura, Tetsuya

doi:10.1109/ecace.2019.8679106

Cited by 8 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of the CQT, Q is defined to be the number of cycles of oscillation in each basis vector. The corresponding equation for Q is shown in (15), where b is the number of bins per octave. Once Q is known, we can calculate the window size N kcq for each bin k cq by (16).…”

Section: Constant-q Transform 1) a Quick Overview Of The Constant-mentioning

confidence: 99%

“…Despite recent advances in end-to-end learning in the audio domain, such as WaveNet [8] and Sam-pleCNN [9], which make model training on raw audio data possible, many recent publications still use spectrograms as the input to their models for various applications [10]. These applications include speech recognition [11,12], speech emotion detection [13], speech-to-speech translation [14], speech enhancement [15], voice separation [16], singing voice conversion [17], music tagging [18], cover detection [19], melody extraction [20], and polyphonic music transcription [21]. One drawback of training an end-to-end model on raw audio data is the longer training time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

nnAudio: An on-the-Fly GPU Audio to Spectrogram Conversion Toolbox Using 1D Convolutional Neural Networks

Cheuk

Anderson²,

Agres

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we present nnAudio, a new neural network-based audio processing framework with graphics processing unit (GPU) support that leverages 1D convolutional neural networks to perform time domain to frequency domain conversion. It allows on-the-fly spectrogram extraction due to its fast speed, without the need to store any spectrograms on the disk. Moreover, this approach also allows backpropagation on the waveforms-to-spectrograms transformation layer, and hence, the transformation process can be made trainable, further optimizing the waveform-to-spectrogram transformation for the specific task that the neural network is trained on. All spectrogram implementations scale as Big-O of linear time with respect to the input length. nnAudio, however, leverages the compute unified device architecture (CUDA) of 1D convolutional neural network from PyTorch, its short-time Fourier transform (STFT), Mel spectrogram, and constant-Q transform (CQT) implementations are an order of magnitude faster than other implementations using only the central processing unit (CPU). We tested our framework on three different machines with NVIDIA GPUs, and our framework significantly reduces the spectrogram extraction time from the order of seconds (using a popular python library librosa) to the order of milliseconds, given that the audio recordings are of the same length. When applying nnAudio to variable input audio lengths, an average of 11.5 hours are required to extract 34 spectrogram types with different parameters from the MusicNet dataset using librosa. An average of 2.8 hours is required for nnAudio, which is still four times faster than librosa. Our proposed framework also outperforms existing GPU processing libraries such as Kapre and torchaudio in terms of processing speed.

show abstract

Section: Constant-q Transform 1) a Quick Overview Of The Constant-mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

nnAudio: An on-the-Fly GPU Audio to Spectrogram Conversion Toolbox Using 1D Convolutional Neural Networks

Cheuk

Anderson²,

Agres

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The effect of noise on the sound signal quality is an important issue for many communication companies due to the demand for the best quality in voice and video technology. The speech signal is hampered by many types of noise, including white noise, traffic noise, babble noise, additive noise, and channel noise [1]. Noise reduction or speech enhancement are common terms used to describe how to deal with background noise [2].…”

Section: Introductionmentioning

confidence: 99%

Convolutional Deep Neural Network and Full Connectivity for Speech Enhancement

Alameri¹,

Kadhim²,

Hadi³

et al. 2023

Int. J. Onl. Eng.

View full text Add to dashboard Cite

The speech signal that is received in real-time has background noise and reverberations, which have an impact on the quality of speech. Therefore, it is crucial to reduce or eliminate the noise and increase the intelligibility and quality of speech signals. In this study, a proposed method that is the most effective and challenging in a low SNR environment for three types of noise are removed, including washing machine, traffic noise, and electric fan noise, and clean speech is recovered. with three samples of noise which are mixed and added to the clean speech signal with a lower level of SNR value fixed at (-5, 0, 5) dBs, that noise source takes equal weights. The enhancement of the corrupted speech signal is done by applying a fully connected and convolutional neural network-based denoising algorithm and comparing their performance. The proposed network shows that a fully connected network (FCN) has less elapsed time than a convolutional network (CNN) while still achieving better performance, demonstrating its applicability for an embedded system. Also, the results obtained show that, overall, the CNN is better than the FCN regarding maximum coloration, PSNR, MES, and STOI.

show abstract