Librosa 0.5.0

McFee, Brian; McVicar, Matt; Nieto, Oriol; Balke, Stefan; Thome, Carl; Liang, Dawen; Battenberg, Eric; Moore, Josh; Bittner, Rachel M.; Yamamoto, Ryōichi; Ellis, Dan; Stöter, Fabian-Robert; Repetto, Douglas; Waloschek, Simon; Carr, CJ; Kranzler, Seth; Choi, Keunwoo; Viktorin, Petr; Santos, Joao Felipe; Holovaty, Adrian; Pimenta, Waldir; Lee, Ho-Jin

doi:10.5281/zenodo.293021

Cited by 15 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Audio processing was mostly carried out using librosa [27] with the exception of CWT for which pyWavelets [28] was used.…”

Section: B Pre-processingmentioning

confidence: 99%

Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks

Huzaifah

2017

Preprint

View full text Add to dashboard Cite

Recent successful applications of convolutional neural networks (CNNs) to audio classification and speech recognition have motivated the search for better input representations for more efficient training. Visual displays of an audio signal, through various time-frequency representations such as spectrograms offer a rich representation of the temporal and spectral structure of the original signal. In this letter, we compare various popular signal processing methods to obtain this representation, such as short-time Fourier transform (STFT) with linear and Mel scales, constant-Q transform (CQT) and continuous Wavelet transform (CWT), and assess their impact on the classification performance of two environmental sound datasets using CNNs. This study supports the hypothesis that time-frequency representations are valuable in learning useful features for sound classification. Moreover, the actual transformation used is shown to impact the classification accuracy, with Mel-scaled STFT outperforming the other discussed methods slightly and baseline MFCC features to a large degree. Additionally, we observe that the optimal window size during transformation is dependent on the characteristics of the audio signal and architecturally, 2D convolution yielded better results in most cases compared to 1D.

show abstract

“…Audio processing was mostly carried out using librosa [27] with the exception of CWT for which pyWavelets [28] was used.…”

Section: B Pre-processingmentioning

confidence: 99%

Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks

Huzaifah

2017

Preprint

View full text Add to dashboard Cite

show abstract

“…• STFT in [18]: 6000/129=46. [18] and our work: 35.9 Hz for frequency < 1 kHz (96 mel-bins and by [19] and [7])…”

Section: Time-frequency Representationsmentioning

confidence: 73%

“…N refers to the number of feature maps (which is set to 32 for all layers in this paper) while W refers to the weights matrix of the fully-connected output layer.) (3,3)) and (4, 4) Fully-connected layer (50) output (50) [7] and Kapre [8]. Total 224,242 tracks are used and split into train/validation/test sets, 201,672/12,633/28,537 tracks respectively.…”

Section: Experiments and Discussionmentioning

confidence: 99%

A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging

Choi

Fazekas

Sandler

et al. 2018

2018 26th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.

show abstract

“…The same FFT size (256) is used for both offline (32 and 8 ms frame length) and online deep clustering (8 ms frame length) frameworks, i.e., During the training process, the 'Adam' optimizer is utilized [24]. The Keras [25] and Tensorflow [26] libraries are used for network training, and Librosa library [27] is used for feature extraction and signal reconstruction in this paper. In order to reduce overfitting, early stopping method is used [28] by monitoring the loss on validation data and stopping the training when no decrease in it is observed for 30 epochs.…”

Section: Experiments Setupmentioning

confidence: 99%

Low-latency Deep Clustering for Speech Separation

Wang

Naithani

Virtanen

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper proposes a low algorithmic latency adaptation of the deep clustering approach to speaker-independent speech separation. It consists of three parts: a) the usage of longshort-term-memory (LSTM) networks instead of their bidirectional variant used in the original work, b) using a short synthesis window (here 8 ms) required for low-latency operation, and, c) using a buffer in the beginning of audio mixture to estimate cluster centres corresponding to constituent speakers which are then utilized to separate speakers within the rest of the signal. The buffer duration would serve as an initialization phase after which the system is capable of operating with 8 ms algorithmic latency. We evaluate our proposed approach on two-speaker mixtures from Wall Street Journal (WSJ0) corpus. We observe that the use of LSTM yields around one dB lower SDR as compared to the baseline bidirectional LSTM in terms of source to distortion ratio (SDR). Moreover, using an 8 ms synthesis window instead of 32 ms degrades the separation performance by around 2.1 dB as compared to the baseline. Finally, we also report separation performance with different buffer durations noting that separation can be achieved even for buffer duration as low as 300 ms.

show abstract

Librosa 0.5.0

Cited by 15 publications

References 0 publications

Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks

Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks

A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging

Low-latency Deep Clustering for Speech Separation

Contact Info

Product

Resources

About