The combination of spectral entropy, zero crossing rate, short time energy and linear prediction error for voice activity detection

Zaw, Thein Htay; War, Nu

doi:10.1109/iccitechn.2017.8281794

Cited by 20 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To enrich the experimental data and accurately reflect the impact of noise on the algorithms, we label the self-recorded speech files and relabel the CSTR database, which has a short duration. First, accurate voiced/unvoiced information of clean speech is obtained using a method for voice activity detection that combines short-time energy and spectral entropy [45]. Then, we use SWIPE' and BaNa, which have the best performance in [6], to extract the pitch in the voiced segments.…”

Section: B Obtaining Ground-truth Pitch Values and Noisy Speech Databasementioning

confidence: 99%

A Pitch Estimation Algorithm for Speech in Complex Noise Environments Based on the Radon Transform

Zhang

2023

IEEE Access

View full text Add to dashboard Cite

The pitch period as an essential feature is used in various speech-related works. Most actual projects collect speech signals in complex noise environments. Thus, the noise resistance of the algorithm for accurate pitch estimation has become more critical than ever. However, many state-of-the-art algorithms fail to obtain good results when dealing with noisy speech files at a low signal-to-noise ratio (SNR) value. This study presents a new noise-resistant pitch estimation algorithm based on the Radon transform and reduces the influence of formants with the modification of the classical equation. In addition, we use the difference between the pitch candidates of the consecutive frames as part of the criterion for the decoding of the Viterbi algorithm to strengthen the correlation of the pitch estimates and make the pitch contours smoother. We synthesized three noisy speech databases with 18 types of collected environmental noise and compared our algorithm with 7 state-of-the-art algorithms. The proposed algorithm has the best performance on CSTR and self-recorded databases and reduces Gross Pitch Error (GPE) rate by over 12% at 0 dB SNR against Bayesian Pitch Tracker. In particular, the GPE rate of our proposed algorithm can be maintained under 25% at 0 dB SNR, while BaNa only achieves 35%.

show abstract

Section: B Obtaining Ground-truth Pitch Values and Noisy Speech Databasementioning

confidence: 99%

A Pitch Estimation Algorithm for Speech in Complex Noise Environments Based on the Radon Transform

Zhang

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Time-domain methods include energy−based endpoint detectors [8,9], zero-crossing rate-based methods [10], Autocorrelation Function (ACF) based methods [11] and different feature combination detection methods [12][13][14][15]. Energy-based noise detection methods use differences in energy to distinguish noise and speech.…”

Section: Related Workmentioning

confidence: 99%

“…This reflects, in outline, the frequency characteristics of the signal. It is generally thought that a speech segment will have a short-time zero crossing rate that is lower than a certain threshold, while the noise will be higher than the threshold [13]. However, the zero-crossing rate of noise in laser detected speech can be low or high, because the causes of the noise differ.…”

Section: Related Workmentioning

confidence: 99%

Speckle Noise Detection and Removal for Laser Speech Measurement Systems

2021

View full text Add to dashboard Cite

Laser speech measurement is a new sound capture technology based on Laser Doppler Vibrometry (LDV). It avoids the need for contact, is easily concealed and is ideal for remote speech acquisition, which has led to its wide-scale adoption for military and security applications. However, lasers are easily affected by complex detection environments. Thus, speckle noise often appears in the measured speech, seriously affecting its quality and intelligibility. This paper examines all of the characteristics of impulsive noise in laser measured speech and proposes a novel automatic impulsive noise detection and removal method. This method first foregrounds noise using decorrelation based on a linear prediction (LP) model that improves the noise-to-signal ratio (NSR) of the measured signal. This makes it possible to detect the position of noise through a combination of the average short-time energy and kurtosis. The method not only precisely locates small clicks (with a duration of just a few samples), but also finds the location of longer bursts and scratches (with a duration of up to a hundred samples). The located samples can then be replaced by more appropriate samples whose coding is based on the LP model. This strategy avoids unnecessary processing and obviates the need to compromise the quality of the relatively large fraction of samples that are unaffected by speckle noise. Experimental results show that the proposed automatic speckle noise detection and removal method outperforms other related methods across a wide range of degraded audio signals.

show abstract

“…In the face of one-dimensional dynamic sound signals, how to perform better recognition and classification also comes down to how to choose a better feature representation. The currently commonly used feature representations can be divided into features directly extracted from the original signal in the time domain (such as autocorrelation, zero-crossing rate) [ 19 , 20 ] and features obtained by converting the signal into frequency (such as spectral centroid [ 21 ], Mel-scale frequency cepstral coefficient). The most widely used feature extraction technique is the Mel-scale frequency cepstral coefficient (MFCC) [ 22 ], but it also shows some limitations when dealing with low signal-to-noise ratio (SNR) sound signals.…”

Section: Introductionmentioning

confidence: 99%

An Automatic Classification System for Environmental Sound in Smart Cities

Zhang,

Zhong,

Xia

et al. 2023

Sensors

View full text Add to dashboard Cite

With the continuous promotion of “smart cities” worldwide, the approach to be used in combining smart cities with modern advanced technologies (Internet of Things, cloud computing, artificial intelligence) has become a hot topic. However, due to the non-stationary nature of environmental sound and the interference of urban noise, it is challenging to fully extract features from the model with a single input and achieve ideal classification results, even with deep learning methods. To improve the recognition accuracy of ESC (environmental sound classification), we propose a dual-branch residual network (dual-resnet) based on feature fusion. Furthermore, in terms of data pre-processing, a loop-padding method is proposed to patch shorter data, enabling it to obtain more useful information. At the same time, in order to prevent the occurrence of overfitting, we use the time-frequency data enhancement method to expand the dataset. After uniform pre-processing of all the original audio, the dual-branch residual network automatically extracts the frequency domain features of the log-Mel spectrogram and log-spectrogram. Then, the two different audio features are fused to make the representation of the audio features more comprehensive. The experimental results show that compared with other models, the classification accuracy of the UrbanSound8k dataset has been improved to different degrees.

show abstract

The combination of spectral entropy, zero crossing rate, short time energy and linear prediction error for voice activity detection

Cited by 20 publications

References 5 publications

A Pitch Estimation Algorithm for Speech in Complex Noise Environments Based on the Radon Transform

A Pitch Estimation Algorithm for Speech in Complex Noise Environments Based on the Radon Transform

Speckle Noise Detection and Removal for Laser Speech Measurement Systems

An Automatic Classification System for Environmental Sound in Smart Cities

Contact Info

Product

Resources

About