Gammatone Frequency Cepstral Coefficients Research Articles

New Feature Vectors using GFCC for Speaker Identification

The feature vectors of speaker identification system plays a crucial role in the overall performance of the system. There are many new feature vectors extraction methods based on MFCC, but ultimately we want to maximize the performance of SID system. The objective of this paper to derive Gammatone Frequency Cepstral Coefficients (GFCC) based a new set of feature vectors using Gaussian Mixer model (GMM) for speaker identification. The MFCC are the default feature vectors for speaker recognition, but they are not very robust at the presence of additive noise. The GFCC features in recent studies have shown very good robustness against noise and acoustic change. The main idea is GFCC features based on GMM feature extraction is to improve the overall speaker identification performance in low signal to noise ratio (SNR) conditions.

GFCC based discriminatively trained noise robust continuous ASR system for Hindi language

A statistically designed Automatic Speech Recognition (ASR) system extracts features from speech signals using feature extraction methods, links the extracted features with the expected phonetics of the hypothesis using acoustic models, uses language model to add prior information about the structure of the target language. For many years, Mel-frequency Cepstral coefficients (MFCC), n-gram, and Hidden Markov Model (HMM) approaches have been used predominantly for feature extraction, language modeling and acoustic modeling, respectively. However, performance degradation of MFCC in noisy conditions and inaccuracy of HMMs while handling large vocabularies have made researchers to propose more efficient methods. The proposed work uses noise robust method Gammatone Frequency Cepstral Coefficients(GFCC) for feature extraction, trigram language modeling, and HMM-Gaussian mixture model (GMM) based acoustic modeling to implement a continuous Hindi language ASR system. Also, it applies Differential Evolution (DE) technique to refine the GFCC features and discriminative techniques to enhance performance of the acoustic model. The performance of the implemented system has been evaluated by using different feature extraction methods, variants of n-gram language modeling techniques and different discriminative techniques in clean as well as noisy conditions. Initially, the results reveal that DE optimized GFCC with HMM-Gaussian Mixture Model (GMM) acoustic modeling performs better than MFCC, PLP and MF-PLP feature extraction methods. Secondly, the experimental results show that the Minimum Phone Error (MPE) outperforms Maximum Mutual Information (MMI) and Maximum Likelihood Estimation (MLE) and trigram based language modeling gives more accurate results than unigram and bigram language modeling. Finally, it has been concluded that the continuous Hindi language ASR system implemented using DE refined GFFC feature extraction method with MPE discriminative training technique and trigram based language modeling gives better accuracy in clean as-well-as noisy environments.

Radon transform of auditory neurograms: a robust feature set for phoneme classification

Classification of speech phonemes is challenging, especially under noisy environments, and hence traditional speech recognition systems do not perform well in the presence of noise. Unlike traditional methods in which features are mostly extracted from the properties of the acoustic signal, this study proposes a new feature for phoneme classification using neural responses from a physiologically based computational model of the auditory periphery. The two-dimensional neurogram was constructed from the simulated responses of auditory-nerve fibres to speech phonemes. Features of neurogram images were extracted using the Discrete Radon Transform, and the dimensionality of features was reduced using an efficient feature selection technique. A standard classifier, Support Vector Machine, was employed to model and test the phoneme classes. Classification performance was evaluated in quiet and under noisy conditions in which test data were corrupted with various environmental distortions such as additive noise, room reverberation, and telephone-channel noise. Performances were also compared with the results from existing methods such as the Mel-frequency cepstral coefficient, Gammatone frequency cepstral coefficient, and frequency-domain linear prediction-based phoneme classification methods. In general, the proposed neural feature exhibited a better classification accuracy in quiet and under noisy conditions compared with the performance of most existing acoustic-signal-based methods.

Singing voice separation using mono-channel mask

Separating singing voice from monaural song recording is a highly difficult task. Still it is important because it has many applications such as singer identification, lyrics recognition, and melody extraction. Difficulty arises due to many musical instruments involved and time-varying spectral overlap between singing voice and music. The goal of singing voice separation is to extract singing voice from the given monaural song recording with minimum artefacts and musical interference. We propose a three stage system for singing voice separation which helps to improve intelligibility and perceptual quality of the separated output. In the first stage, modified sub-harmonic summation algorithm finds pitch of the singing voice and its harmonic components. Here, we create a binary mask. In the second stage, frames i.e. the masked spectral amplitudes are classified as singing and non-singing frames by using a combination of Gammatone frequency cepstral coefficients (GFCC) and Mel-frequency cepstral coefficients (MFCC) features. Lastly, mono-channel mask is created and signal amplitude correction is done using kurtosis measure. We synthesize the estimate of singing voice using both binary mask and mono-channel mask. It is observed that the singing voice separated using mono-channel mask improves the GNSDR score. Performance of the proposed system is compared with the other methods, where it presents excellent improvement in terms of GNSDR. It produces higher GNSDR scores in case of two different datasets.

Performance evaluation of Hindi speech recognition system using optimized filterbanks

An Automatic Speech Recognition (ASR) system implementation uses a conventional pattern recognition technique that stores a set of training patterns in classes and compares the test patterns with training patterns to place them in the best matched pattern class. Most state-of-the-art ASR systems use Mel Frequency Cepstral Coefficient (MFCC) and Perceptual Linear Prediction (PLP) to extract features in training phase of the ASR system. However, sensitivity of MFCC & PLP to background noise has resulted in use of noise robust features Gammatone Frequency Cepstral Coefficient (GFCC) and Basilar-membrane Frequency-band Cepstral Coefficient (BFCC). But many issues associated with these feature extraction methods, like accepted bandwidth and standard number of filters are unresolved till date. This paper proposes a novel approach to use Differential Evolution (DE) algorithm to optimize the number and spacing of filters used in MFCC, GFCC and BFCC techniques. It also evaluates the performance of the said feature extraction methods with and without DE optimization in clean as well as in noisy environments. The results conclude that BFCC based ASR systems performs 0.4% to 1.0% better than GFCC and 7% to 10% better than MFCC in different conditions.

An Unsupervised Two-Talker Speech Separation System Based on CASA

On the basis of the theory about blind separation of monaural speech based on computational auditory scene analysis (CASA), a two-talker speech separation system combining CASA and speaker recognition was proposed to separate speech from other speech interferences in this paper. First, a tandem algorithm is used to organize voiced speech, then based on the clustering of gammatone frequency cepstral coefficients (GFCCs), an object function is established to recognize the speaker, and the best group is achieved through exhaustive search or beam search, so that voiced speech is organized sequentially. Second, unvoiced segments are generated by estimating onset/offset, and then unvoiced–voiced (U–V) segments and unvoiced–unvoiced (U–U) segments are separated respectively. The U–V segments are managed via the binary mask of the separated voiced speech, while the U–V segments are separated evenly. So far the unvoiced segments are separated. The simulation and performance evaluation verify the feasibility and effectiveness of the proposed algorithm.

Discriminative Training Using Noise Robust Integrated Features and Refined HMM Modeling

Abstract The classical approach to build an automatic speech recognition (ASR) system uses different feature extraction methods at the front end and various parameter classification techniques at the back end. The Mel-frequency cepstral coefficients (MFCC) and perceptual linear prediction (PLP) techniques are the conventional approaches used for many years for feature extraction, and the hidden Markov model (HMM) has been the most obvious selection for feature classification. However, the performance of MFCC-HMM and PLP-HMM-based ASR system degrades in real-time environments. The proposed work discusses the implementation of discriminatively trained Hindi ASR system using noise robust integrated features and refined HMM model. It sequentially combines MFCC with PLP and MFCC with gammatone-frequency cepstral coefficient (GFCC) to obtain MF-PLP and MF-GFCC integrated feature vectors, respectively. The HMM parameters are refined using genetic algorithm (GA) and particle swarm optimization (PSO). Discriminative training of acoustic model using maximum mutual information (MMI) and minimum phone error (MPE) is preformed to enhance the accuracy of the proposed system. The results show that discriminative training using MPE with MF-GFCC integrated feature vector and PSO-HMM parameter refinement gives significantly better results than the other implemented techniques.

Bag-of-Features Methods for Acoustic Event Detection and Classification

The detection and classification of acoustic events in various environments is an important task. Its applications range from multimedia analysis to surveillance of humans or even animal life. Several of these tasks require the capability of online processing. Besides many approaches that tackle the task of acoustic event detection, methods that are based on the well known bag-of-features principle also emerged into the field. Acoustic features are calculated for all frames in a given time window. Then, applying the bag-of-features concept, these features are quantized with respect to a learned codebook and a histogram representation is computed. Bag-of-features approaches are particularly interesting for online processing as they have a low computational cost. In this paper, the bag-of-features principle and various extensions are reviewed, including soft quantization, supervised codebook learning, and temporal modeling. Furthermore, Mel and Gammatone frequency cepstral coefficients that originate from psychoacoustic models are used as the underlying feature set for the bag-of-features. The possibility of fusing the results of multiple channels in order to improve the robustness is shown. Two databases are used for the experiments: The DCASE 2013 office live dataset and the ITC-IRST multichannel dataset.

Text Independent Amharic Language Speaker Identification in Noisy Environments using Speech Processing Techniques

<p>In Ethiopia, the largest ethnic and linguistic groups are the Oromos, Amharas and Tigrayans. This paper presents the performance analysis of text-independent speaker identification system for the Amharic language in noisy environments. VQ (Vector Quantization), GMM (Gaussian Mixture Models), BPNN (Back propagation neural network), MFCC (Mel-frequency cepstrum coefficients), GFCC (Gammatone Frequency Cepstral Coefficients), and a hybrid approach had been use as techniques for identifying speakers of Amharic language in noisy environments. For the identification process, speech signals are collected from different speakers including both sexes; for our data set, a total of 90 speakers’ speech samples were collected, and each speech have 10 seconds duration from each individual. From these speakers, 59.2%, 70.9% and 84.7% accuracy are achieved when VQ, GMM and BPNN are used on the combined feature vector of MFCC and GFCC. </p>

A Robust Speaker Identification System Using the Responses from a Model of the Auditory Periphery.

Speaker identification under noisy conditions is one of the challenging topics in the field of speech processing applications. Motivated by the fact that the neural responses are robust against noise, this paper proposes a new speaker identification system using 2-D neurograms constructed from the responses of a physiologically-based computational model of the auditory periphery. The responses of auditory-nerve fibers for a wide range of characteristic frequency were simulated to speech signals to construct neurograms. The neurogram coefficients were trained using the well-known Gaussian mixture model-universal background model classification technique to generate an identity model for each speaker. In this study, three text-independent and one text-dependent speaker databases were employed to test the identification performance of the proposed method. Also, the robustness of the proposed method was investigated using speech signals distorted by three types of noise such as the white Gaussian, pink, and street noises with different signal-to-noise ratios. The identification results of the proposed neural-response-based method were compared to the performances of the traditional speaker identification methods using features such as the Mel-frequency cepstral coefficients, Gamma-tone frequency cepstral coefficients and frequency domain linear prediction. Although the classification accuracy achieved by the proposed method was comparable to the performance of those traditional techniques in quiet, the new feature was found to provide lower error rates of classification under noisy environments.

Speaker Identification System using Gaussian Mixture Model and Support Vector Machines (GMM-SVM) under Noisy Conditions

Background: Automatic Speaker Identification (SID) systems has been a major breakthrough and crucial in many real world applications. Methods: This work addresses the SID task based on GMM-SVM in a three stage process. Firstly, the Gammatone Frequency Cepstral Coefficients (GFCC) and Mean Hilbert Envelope Coefficients (MHEC) of the speakers are extracted. Secondly, these features are modeled using Gaussian Mixture Model (GMM), on adapting the extracted acoustic features by mean, the corresponding super vectors are found and these vectors are trained using Support Vector Machine (SVM). Finally, the actual recognition is done by feeding the super vectors of them asked noisy test utterance by Ideal Binary Mask (IBM) into SVM model and their accuracy of recognition is compared for GFCC, MHEC and RASTA-MFCC in different noisy conditions. Findings: Evaluation results show that SID performance carried out with MHEC is extensively better than the performance of other two features. Applications: Major areas that implements automatic SIDs are forensics, surveillance and audio biometrics etc.

A robust BFCC feature extraction for ASR system

An auditory-based feature extraction algorithm naming the Basilar-membrane Frequency-band Cepstral Coefficient (BFCC) is proposed to increase the robustness for automatic speech recognition. Compared to Fourier spectrogram based of the Mel-Frequency Cepstral Coefficient (MFCC) method, the proposed BFCC method engages an auditory spectrogram based on agammachirp wavelet transform to simulate the auditory response of human inner ear to improve the noise immunity. In addition, the Hidden Markov Model (HMM) is used for evaluating the proposed BFCC in phases of training and testing purposes conducted by AURORA-2 corpus with different Signal-to-Noise Ratios (SNRs) degrees of datasets. The experimental results indicate the proposed BFCC, compared with MFCC, Gammatone Wavelet Cepstral Coefficient (GWCC), and Gammatone Frequency Cepstral Coefficient (GFCC), improves the speech recognition rate by 13%, 17%, and 0.5% respectively, on average given speech samples with SNRs ranging from -5 to 20 dB.

Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks

Speech signal degradation in real environments mainly results from room reverberation and concurrent noise. While human listening is robust in complex auditory scenes, current speech segregation algorithms do not perform well in noisy and reverberant environments. We treat the binaural segregation problem as binary classification, and employ deep neural networks (DNNs) for the classification task. The binaural features of the interaural time difference and interaural level difference are used as the main auditory features for classification. The monaural feature of gammatone frequency cepstral coefficients is also used to improve classification performance, especially when interference and target speech are collocated or very close to one another. We systematically examine DNN generalization to untrained spatial configurations. Evaluations and comparisons show that DNN-based binaural classification produces superior segregation performance in a variety of multisource and reverberant conditions.

Simplified supervised i-vector modeling with application to robust and efficient language identification and speaker verification

This paper presents a simplified and supervised i-vector modeling approach with applications to robust and efficient language identification and speaker verification. First, by concatenating the label vector and the linear regression matrix at the end of the mean supervector and the i-vector factor loading matrix, respectively, the traditional i-vectors are extended to label-regularized supervised i-vectors. These supervised i-vectors are optimized to not only reconstruct the mean supervectors well but also minimize the mean square error between the original and the reconstructed label vectors to make the supervised i-vectors become more discriminative in terms of the label information. Second, factor analysis (FA) is performed on the pre-normalized centered GMM first order statistics supervector to ensure each gaussian component's statistics sub-vector is treated equally in the FA, which reduces the computational cost by a factor of 25 in the simplified i-vector framework. Third, since the entire matrix inversion term in the simplified i-vector extraction only depends on one single variable (total frame number), we make a global table of the resulting matrices against the frame numbers’ log values. Using this lookup table, each utterance's simplified i-vector extraction is further sped up by a factor of 4 and suffers only a small quantization error. Finally, the simplified version of the supervised i-vector modeling is proposed to enhance both the robustness and efficiency. The proposed methods are evaluated on the DARPA RATS dev2 task, the NIST LRE 2007 general task and the NIST SRE 2010 female condition 5 task for noisy channel language identification, clean channel language identification and clean channel speaker verification, respectively. For language identification on the DARPA RATS, the simplified supervised i-vector modeling achieved 2%, 16%, and 7% relative equal error rate (EER) reduction on three different feature sets and sped up by a factor of more than 100 against the baseline i-vector method for the 120s task. Similar results were observed on the NIST LRE 2007 30s task with 7% relative average cost reduction. Results also show that the use of Gammatone frequency cepstral coefficients, Mel-frequency cepstral coefficients and spectro-temporal Gabor features in conjunction with shifted-delta-cepstral features improves the overall language identification performance significantly. For speaker verification, the proposed supervised i-vector approach outperforms the i-vector baseline by relatively 12% and 7% in terms of EER and norm old minDCF values, respectively.

Singer identification based on computational auditory scene analysis and missing feature methods

A major challenge for the identification of singers from monaural popular music recording is to remove or alleviate the influence of accompaniments. Our system is realized in two stages. In the first stage, we exploit computational auditory scene analysis (CASA) to segregate the singing voice units from a mixture signal. First, the pitch of singing voice is estimated to extract the pitch-based features of each unit in an acoustic vector. These features are then exploited to estimate the binary time-frequency (T-F) masks, where 1 indicates that the corresponding T-F unit is dominated by the singing voice, and 0 indicates otherwise. These regions dominated by the singing voice are considered reliable, and other units are unreliable or missing. Thus the acoustic vector is incomplete. In the second stage, two missing feature methods, the reconstruction of acoustic vector and the marginalization, are used to identify the singer by dealing with the incomplete acoustic vectors. For the reconstruction of acoustic vector, the complete acoustic vector is first reconstructed and then converted to obtain the Gammatone frequency cepstral coefficients (GFCCs), which are further used to identify the singer. For the marginalization, the probabilities that the voice belonging to a certain singer are computed on the basis of only the reliable components. We find that the reconstruction method outperforms the marginalization method, while both methods have significantly good performances, especially at signal-to-accompaniment ratios (SARs) of 0 dB and ??3 dB, in contrast to another system.

Exploring Monaural Features for Classification-Based Speech Segregation

Monaural speech segregation has been a very challenging problem for decades. By casting speech segregation as a binary classification problem, recent advances have been made in computational auditory scene analysis on segregation of both voiced and unvoiced speech. So far, pitch and amplitude modulation spectrogram have been used as two main kinds of time-frequency (T-F) unit level features in classification. In this paper, we expand T-F unit features to include gammatone frequency cepstral coefficients (GFCC), mel-frequency cepstral coefficients, relative spectral transform (RASTA) and perceptual linear prediction (PLP). Comprehensive comparisons are performed in order to identify effective features for classification-based speech segregation. Our experiments in matched and unmatched test conditions show that these newly included features significantly improve speech segregation performance. Specifically, GFCC and RASTA-PLP are the best single features in matched-noise and unmatched-noise test conditions, respectively. We also find that pitch-based features are crucial for good generalization to unseen environments. To further explore complementarity in terms of discriminative power, we propose to use a group Lasso approach to select complementary features in a principled way. The final combined feature set yields promising results in both matched and unmatched test conditions.

Blind source extraction for robust speech recognition in multisource noisy environments

This paper proposes and describes a complete system for Blind Source Extraction (BSE). The goal is to extract a target signal source in order to recognize spoken commands uttered in reverberant and noisy environments, and acquired by a microphone array. The architecture of the BSE system is based on multiple stages: (a) TDOA estimation, (b) mixing system identification for the target source, (c) on-line semi-blind source separation and (d) source extraction. All the stages are effectively combined, allowing the estimation of the target signal with limited distortion.While a generalization of the BSE framework is described, here the proposed system is evaluated on the data provided for the CHiME Pascal 2011 competition, i.e. binaural recordings made in a real-world domestic environment. The CHiME mixtures are processed with the BSE and the recovered target signal is fed to a recognizer, which uses noise robust features based on Gammatone Frequency Cepstral Coefficients. Moreover, acoustic model adaptation is applied to further reduce the mismatch between training and testing data and improve the overall performance. A detailed comparison between different models and algorithmic settings is reported, showing that the approach is promising and the resulting system gives a significant reduction of the error rate.

CASA-Based Robust Speaker Identification

Conventional speaker recognition systems perform poorly under noisy conditions. Inspired by auditory perception, computational auditory scene analysis (CASA) typically segregates speech by producing a binary time-frequency mask. We investigate CASA for robust speaker identification. We first introduce a novel speaker feature, gammatone frequency cepstral coefficient (GFCC), based on an auditory periphery model, and show that this feature captures speaker characteristics and performs substantially better than conventional speaker features under noisy conditions. To deal with noisy speech, we apply CASA separation and then either reconstruct or marginalize corrupted components indicated by a CASA mask. We find that both reconstruction and marginalization are effective. We further combine the two methods into a single system based on their complementary advantages, and this system achieves significant performance improvements over related systems under a wide range of signal-to-noise ratios.