This letter introduces a Frame Relevance Score (FRS) to improve the classification of environmental acoustic sources from noisy speech signals. The importance of each short-time frame for the classification results is objectively interpreted by SHapley Additive exPlanations (SHAP) values. The FRS enables the selection of frames that are more appropriate to improve the discrimination power of the acoustic models. The FRS-based frame selection can be used as a pre-training strategy to any classification approach. Evaluation experiments consider the recognition of ten background sources from noisy speech signals. The classical system based on MFCC and GMM is adopted to prove that the selected frames can better distinguish the acoustic classes. Moreover, the proposed solution outperforms a surrogate-based adaptive learning technique and a competing frame selection method. Experiments are also conducted with a recently proposed pre-trained neural network that achieves high classification rates. For this scenario, the FRS-based selection improves the overall classification accuracy from 51.5% to 58.8%.

This paper introduces a novel (HDAG - Harmonic Detection for Auditory Gain) method for speech intelligibility enhancement in noisy scenarios. In the proposed scheme, a series of selective Gammachirp filters are adopted to emphasize the harmonic components of speech reducing the masking effects of acoustic noises. The fundamental frequency values are estimated by the HHT-Amp (Amplitude-based Hilbert Huang Transform) technique. Harmonic components estimated with low accuracy are detected and adjusted according to the FSFFE (Frequency Separation for Fundamental Frequency Estimation) low/high pitch separation. The central frequencies of the filterbank are defined considering the third-octave subbands which are best suited to cover the regions most relevant to intelligibility. Before signal reconstruction, the gammachirp filtered components are amplified by gain factors regulated by FSFFE classification. The proposed HDAG solution and three baseline techniques are examined considering six background noises with four signal-to-noise ratios. Three objective measures are adopted for the evaluation of speech intelligibility and quality. Several experiments are conducted to demonstrate that the proposed scheme achieves better speech intelligibility improvement when compared to the competing approaches. A perceptual listening test is further considered and corroborates the objective results.

This paper introduces a novel signal enhancement method to mitigate the effects of underwater acoustic ambient noises. The combination of ensemble empirical mode decomposition (EEMD) and iterative filtering (IF) is adopted to analyze the underwater speech and chirp noisy signals. The main novelty relies on the estimation and selection of the noise components using the index of non-stationarity of each decomposition mode. The idea is to better suppress the noise components, especially for highly non-stationary environments. The proposed method is compared to four baseline approaches to enhance speech and chirp signals. For this purpose, signals of interest are corrupted by three underwater ambient noises with different non-stationarity degrees. Experiments results demonstrate that the proposal achieves the best results, especially in the presence of severe non-stationary noisy conditions. In this situation, the reduction in the root mean square error achieves 11.2%.

This paper introduces a novel method to separate voiced frames of noisy speech signals into low-frequency or high-frequency. This separation improves the accuracy of fundamental frequency (F0) estimators. In this proposal, the target signal is analyzed by means of the ensemble empirical mode decomposition. Next, the pitch information is extracted from the first decomposition modes. This feature indicates the frequency region where the speech F0 should be located, thus separating the frames into low-frequency or high-frequency. The frames separation is then applied to correct pitch candidates extracted from a F0 detection method, improving the estimation accuracy. The proposed method and a baseline separation approach are evaluated considering four different F0 estimation algorithms. Experiments are conducted with the CSTR and TIMIT databases, and six noises with various signal-to-noise ratios. The Gross Error (GE) and Mean Absolute Error (MAE) metrics are adopted to evaluate the solutions in terms of F0 estimation errors. Results show that the proposed method outperforms the baseline, in terms of low/high frequency separation accuracy. Moreover, the novel solution is able to better improve F0 detection accuracy under different noisy conditions.

This letter proposes a novel blind acoustic mask (BAM) designed to adaptively detect noise components and preserve target speech segments in time domain. A robust standard deviation estimator is applied to the non-stationary noisy speech to identify noise masking elements. The main contribution of the proposed solution is the use of this noise statistics to derive an adaptive information to define and select samples with lower noise proportion. Thus, preserving speech intelligibility. Additionally, no information of the target speech and noise signals statistics is previously required to this non-ideal mask. The BAM and three competitive methods, Ideal Binary Mask (IBM), Target Binary Mask (TBM), and Non-stationary Noise Estimation for Speech Enhancement (NNESE), are evaluated considering speech signals corrupted by three non-stationary acoustic noises and six values of signal-to-noise ratio (SNR). Results demonstrate that the BAM technique achieves intelligibility gains comparable to ideal masks while maintaining good speech quality.

This letter proposes a time-domain method to improve speech intelligibility in noisy scenarios. In the proposed approach, a series of Gammatone filters are adopted to detect the harmonic components of speech. The filters outputs are amplified to emphasize the first harmonics, reducing the masking effects of acoustic noises. The proposed GTFF0solution and two baseline techniques are examined considering four background noises with different non-stationarity degrees. Three intelligibility measures (ESTOI, ESII and ASIIST) are adopted for objective evaluation. The experiments results show that the proposed scheme leads to expressive speech intelligibility gain when compared to the competing approaches. Furthermore, the PESQ and OQCM objective scores demonstrate that the proposed technique also provides interesting quality improvement.

This paper introduces a novel single channel speech enhancement method in the time domain to mitigate the effects of acoustic impulsive noises. The ensemble empirical mode decomposition is applied to analyze the noisy speech signal. The estimation and selection of noise components is based on the impulsiveness index of decomposition modes. An adaptive threshold is proposed to define the criterion to select the noise components. The proposed method is evaluated in speech enhancement experiments considering four acoustic noises with different impulsiveness indices and non-stationarity degrees under various signal-to-noise ratios. Four speech enhancement algorithms are adopted as baseline in the evaluation analysis considering spectral and time domains. Seven objective measures are adopted to compare the proposed and baseline approaches in terms of speech quality and intelligibility. Results show that the proposed solution outperforms the competing algorithms for most of the noisy scenarios. The novel method shows particularly interesting performance when speech signals are corrupted by highly impulsive acoustic noises.

This study presents a widespread analysis of affective vocal expression classification systems. In this study, the Hilbert–Huang–Hurst coefficient (HHHC) vector is proposed as a non‐linear vocal source feature to represent the emotional states according to their effects on the speech production mechanism. Affective states are highlighted by the empirical mode decomposition‐based method, which exploits the non‐stationarity of the acoustic variations. Hurst coefficients are then estimated from the decomposition modes to form the feature vector. Additionally, a vector of the index of non‐stationarity (INS) is introduced as dynamic information to the HHHC. The proposed feature vector is evaluated in speech emotion classification experiments with three databases in German and English languages. Three state‐of‐the‐art acoustic feature vectors are adopted as a baseline. The ‐integrated Gaussian mixture model ( ‐GMM) is also introduced for the emotion representation and classification. Its performance is compared to competing for stochastic and machine learning classifiers. Results demonstrate that the HHHC leads to significant classification improvement when compared to the baseline acoustic feature vectors. Moreover, results also show that the ‐GMM outperforms the competing classification methods. Finally, the complementarity aspects of HHHC and INS are also evaluated for the GeMAPS and eGeMAPS feature sets.

This letter proposes a new time domain absorption approach designed to reduce masking components of speech signals under noisy-reverberant conditions. In this method, the nonstationarity of corrupted signal segments is used to detect masking distortions based on a defined threshold. The non-stationarity is objectively measured and is also adopted to determine the absorption procedure. Additionally, no prior knowledge of speech statistics or room information is required for this technique. Two intelligibility measures (ESII and ASIIST) are used for objective evaluation. The results show that the proposed scheme leads to a higher intelligibility improvement when compared to competing methods. A perceptual listening test is further considered and corroborates these results. Furthermore, the updated version of the SRMR quality measure (SRMRnorm) demonstrates that the proposed technique also attains quality improvement.

This letter introduces a method based on the Hilbert-Huang transform (HHT) to estimate the fundamental frequency of nonstationary noisy speech signals. For this purpose, the target signals are analyzed by means of the ensemble empirical mode decomposition and the Hilbert transform. The main contribution of the proposed solution, namely HHT-Amp, relies on the extraction of pitch information from the instantaneous amplitude of the first decomposition modes. The HHT-Amp and four competitive algorithms are evaluated considering speech signals corrupted by five acoustic noises with different nonstationarity degrees. The HHT-Amp achieves the lowest gross error rate and mean absolute error for the most severe noisy conditions. This demonstrates that the proposed approach outperforms the baseline methods in estimating the fundamental frequency of noisy speech.

This letter proposes a new time domain speech enhancement technique for signals corrupted by nonstationary acoustic noises. In this method, the noise components are detected and attenuated directly from the corrupted speech samples. They are obtained with a robust estimation of the noise standard deviation considering any speech and noise amplitude distribution. These values are used to define a noise selection threshold. Additionally, this solution does not require the usage of any spectral analysis or temporal decomposition as a pre-processing phase. The experiments results show that the proposed scheme leads to significant improvement in the speech quality and intelligibility when compared to competing enhancement approaches.

In this letter, the pH time-frequency vocal source feature is proposed for multistyle emotion identification. A binary acoustic mask is also used to improve the emotion classification accuracy. Emotional and stress conditions from the Berlin Database of Emotional Speech (EMO-DB) and Speech under Simulated and Actual Stress (SUSAS) databases are investigated in the experiments. In terms of emotion identification rates, the pH outperforms the mel-frequency cepstral coefficients (MFCC) and a Teager-Energy-Operator (TEO) based feature. Moreover, the acoustic mask achieves accuracy improvement for both the MFCC and the pH feature.

This paper investigates the fusion of Mel-frequency cepstral coefficients (MFCC) and statistical pH features to improve the performance of speaker verification (SV) in non-stationary noise conditions. The$\alpha $-integrated Gaussian Mixture Model ($\alpha $-GMM) classifier is adopted for speaker modeling. Two different approaches are applied to reduce the effects of noise corruption in the SV task: speech enhancement and multi-style training (MT). The spectral subtraction with minimum statistics (MS/SS) and the optimally-modified log-spectral amplitude with improved minima controlled recursive averaging (IMCRA/OMLSA) are examined for the speech enhancement procedure. The MT techniques are based on colored (Colored-MT), white (White-MT) and narrow-band (Narrow-MT) noises. Six real non-stationary noises, collected from different acoustic sources, are used to corrupt the TIMIT speech database in four different signal-to-noise ratios (SNR). The index of non-stationarity (INS) is chosen for the stationarity tests of the acoustic noises. Complementary SV experiments are conducted in realistic noisy conditions using the MIT database. The results show that the best SV accuracy was obtained with the MFCC + pH features fusion, the MS/SS and the Colored-MT.

This paper presents a speech enhancement technique for signals corrupted by nonstationary acoustic noises. The proposed approach applies the empirical mode decomposition (EMD) to the noisy speech signal and obtains a set of intrinsic mode functions (IMF). The main contribution of the proposed procedure is the adoption of the Hurst exponent in the selection of IMFs to reconstruct the speech. This EMD and Hurst-based (EMDH) approach is evaluated in speech enhancement experiments considering environmental acoustic noises with different indices of nonstationarity. The results show that the EMDH improves the segmental signal-to-noise ratio and an overall quality composite measure, encompassing the perceptual evaluation of speech quality (PESQ). Moreover, the short-time objective intelligibility (STOI) measure reinforces the superior performance of EMDH. Finally, the EMDH is also examined in a speaker identification task in noisy conditions. The proposed technique leads to the highest speaker identification rates when compared to the baseline speech enhancement algorithms and also to a multicondition training procedure.

This study proposes a method for generating acoustic noise sequences with different distributions and coloured spectra. The noise samples are obtained by passing a non-Gaussian white noise through a finite impulse response filter. The resulting power spectral density is proportional to 1/fβ, where β is a positive power-law exponent. The noise samples pattern is determined by the Kurtosis ratio. The proposed generator is evaluated by comparing real and artificial acoustic noises statistics in the time and frequency domains. The results show that the generated coloured sequences achieved the PSD decaying rate and also the non-Gaussian pattern of the real environmental acoustic noises.

This letter proposes a colored noise based multicondition training technique for robust speaker identification in unknown noisy environments. The colored noise samples generation is based on filtering a white Gaussian sequence that leads to a power spectral density (PSD) proportional to 1/fβ, where β ∈ [0, 2]. Gaussian mixture models (GMM) are applied to obtain the speaker models using the noisy speech signals with a single signal-to-noise ratio (SNR). The colored noise based multicondition training is evaluated for the speaker identification task considering the test utterances corrupted with real acoustic noises and different values of SNR. The results show that the proposed technique outperforms the white noise based multicondition and the clean-speech training approaches.

In this paper, a text-independent automatic speaker recognition (ASkR) system is proposed-the SR/sub Hurst/-which employs a new speech feature and a new classifier. The statistical feature pH is a vector of Hurst (H) parameters obtained by applying a wavelet-based multidimensional estimator (M/spl I.bar/dim/spl I.bar/wavelets ) to the windowed short-time segments of speech. The proposed classifier for the speaker identification and verification tasks is based on the multidimensional fBm (fractional Brownian motion) model, denoted by M/spl I.bar/dim/spl I.bar/fBm. For a given sequence of input speech features, the speaker model is obtained from the sequence of vectors of H parameters, means, and variances of these features. The performance of the SR/sub Hurst/ was compared to those achieved with the Gaussian mixture models (GMMs), autoregressive vector (AR), and Bhattacharyya distance (dB) classifiers. The speech database-recorded from fixed and cellular phone channels-was uttered by 75 different speakers. The results have shown the superior performance of the M/spl I.bar/dim/spl I.bar/fBm classifier and that the pH feature aggregates new information on the speaker identity. In addition, the proposed classifier employs a much simpler modeling structure as compared to the GMM.

A periodic allocation protocol, called anticipated traffic allocation protocol (ATAP) for real time VBR traffic is proposed. The main objective of this protocol is to dynamically allocate the available bandwidth to real-time VBR sources, i.e. to be more efficient than the CBR allocation and at the same time more secure that the "walk-in" allocation. The ATAP unit is located at the network entry node between the real-time encoder and the applied bandwidth allocation protocol in the network, the fast reservation protocol FRP/DT. This reservation protocol cannot satisfy the real-time requirements, since the source would have to wait at least a round trip delay to reserve a required bandwidth increase. Hence, the ATAP proposes to anticipate and allocate the bandwidth one period in advance. This permits the encoder to adjust its coding bit rate according to the network loading condition. Doing so, a congestion will gracefully degrade the subjective quality of the signal, instead of "blindly" loosing cells at the network entry node. A minimum bit rate negotiated at the connection set-up is always guaranteed to assure the connection continuity in the case of the case of bandwidth reservation refusal. On the network side, the ATAP interacts with the FRP/DT. Reservation failures are used as congestion indicators to control the entering traffic and to adjust the cell priority. A simulation analysis investigates the performance of the ATAP and its interaction with the FRP/DT for two real MPEG VBR audio sequences under different bit rate anticipation approaches.

Multimedia traffic is a special traffic consisting of different components (video, voice and data) belonging all to the same application and hence being strictly temporarily bounded. The jitter impact on multimedia (MM) traffic in ATM networks is analyzed. The inter-flows jitter (IFJ) parameter, that defines the jitter between several associated traffic flows is introduced. Furthermore, the jitter and IFJ are studied under two different multiplexing schemes namely, "all in one virtual path (VP)" and "one VP for each". An IFJ recovery mechanism (IFJ-rm) is finally proposed to restore the original traffic. Simulation results for the IFJ-rm under different scheduling disciplines are presented and discussed.