Inverted Mel Frequency Cepstral Coefficient Research Articles

Speech stress recognition using semi-eager learning

Homo-sapiens suffer from psychogenic pain due to current day lifestyle. According to psychologists, stress is the most destructive form of psychalgia and it is a vicious companion for this species. Immoderate levels of stress may lead to the death of many individuals. Normally, the presence of stress gives rise to certain emotions which can be detected to predict stress levels of a person. This paper proposes the development of mechanized and efficient Speech Emotion Recognition (SER) for stress level analysis. The paper investigates the performance of perceptual based speech features like Revised Perceptual Linear Prediction Coefficients, Bark Frequency Cepstral Coefficients, Perceptual Linear Predictive Cepstrum, Gammatone Frequency Cepstral coefficient, Mel Frequency Cepstral Coefficient, Gammatone Wavelet Cepstral Coefficient and Inverted Mel Frequency Cepstral Coefficients on SER. The novelty of this work involves application of a SemiEager (SemiE) learning algorithm for evaluating auditory cues. SemiE offers advantages over eager and lazy based learning by reducing the computational cost. Stress level recognition being the main objective, the Speech Under Simulated and Actual Stress (SUSAS) benchmark database is used for performance analysis. A comparative analysis is presented to demonstrate the improvement in the SED performance. An overall accuracy of 90.66% recognition of stress related emotions is achieved.

Voice liveness detection under feature fusion and cross-environment scenario

Detecting playback spoofing attacks in speaker verification system is a big challenge. Recent studies on ASVspoof challenges show that replay attacks are the most difficult to recognize. Reasonable performance is expected from such antispoofing systems to avoid malicious access attempts on voice biometrics enabled systems for possible commercial deployment. We present a study on filterbank based short-term cepstral features for liveness detection to counter replay spoofing attacks on speaker verification systems. These systems are evaluated on ASVspoof 2017 version 2.0 dataset. Experimental investigation is carried out on standalone and fused features to assess the performance of the antispoofing systems using spoofing detection equal error rate (EER). Improvement of 20.47% and 21.51% is obtained over baseline system using standalone and fused approaches, respectively. We also explore the impact of proposed static inverted Mel frequency cepstral coefficients (IMFCC) based system under mismatched conditions by training and testing it in different environments (with different background conditions) alongwith other systems. Results show that the proposed system outperforms other systems used in this study in all experiments.

A Comparison of Features for Replay Attack Detection

Speaker verification (ASV) systems are still vulnerable to different kinds of spoofing attacks, especially replay attack due to high-quality playback devices. Many countermeasures have been developed recently. Most of the efforts focus on the search for more salient features and many new features have been proposed. Five kinds of features, namely Mel-frequency cepstral coefficients (MFCCs), linear frequency cepstral coefficients (LFCCs), inverted Mel-frequency cepstral coefficients (IMFCCs), constant Q cepstral coefficients (CQCCs) and bottleneck features were compared on the public ASVspoof 2017 and BTAS 2016 datasets in this paper. Our experimental results show that MFCCs and bottleneck features yield comparable results. Both of them significantly outperform others (including the recently proposed CQCCs). However, the number of filters and cepstral bins are essential to the success of MFCCs.

Enhanced speech emotion detection using deep neural networks

This paper focusses on investigation of the effective performance of perceptual based speech features on emotion detection. Mel frequency cepstral coefficients (MFCC’s), perceptual linear predictive cepstrum (PLPC), Mel frequency perceptual linear prediction cepstrum (MFPLPC), bark frequency cepstral coefficients (BFCC), revised perceptual linear prediction coefficient’s (RPLP) and inverted Mel frequency cepstral coefficients (IMFCC) are the perception features considered. The algorithm using these auditory cues is evaluated with deep neural networks (DNN). The novelty of the work involves analysis of the perceptual features to identify predominant features that contain significant emotional information about the speaker. The validity of the algorithm is analysed on publicly available Berlin database with seven emotions in 1-dimensional space termed categorical and 2-dimensional continuous space consisting of emotions in valence and arousal dimensions. Comparative analysis reveals that considerable improvement in the performance of emotion recognition is obtained using DNN with the identified combination of perceptual features.

Fused Mel Feature sets based Text-Independent Speaker Identification using Gaussian Mixture Model

This paper provides an efficient approach for text-independent speaker identification using a fused Mel feature sets and Gaussian Mixture Modeling (GMM). The individual Gaussian components of a GMM are shown to represent some speaker specific spectral shapes that are effective for modeling speaker identity. Two different set of features which are complement to each, other, Mel Frequency Cepstral Coefficient (MFCC) and Inverted Mel Frequency Cepstral Coefficient (MFCC) features are obtained for each speaker and are trained using Expectation Maximization algorithm. Two GMM models; one for MFCC feature sets, other one for IMFCC feature sets are created. During testing phase, the likelihood of unknown speaker's features with each of the GMM models is determined. By using a weighted sum of these likelihood values, a fused score is created for each speaker and speaker with maximum score is the identified speaker. The performance of this fusion GMM system is evaluated using a part of the TIMIT database consisting of 120 speakers and a maximum identification efficiency of 93.88% is achieved.

Vector Quantization Approach for Speaker Recognition using MFCC and Inverted MFCC

Front-end or feature extractor is the first component in an automatic speaker recognition system. Feature extraction transforms the raw speech signal into a compact but effective representation that is more stable and discriminative than the original signal. Since the front-end is the first component in the chain, the quality of the later components (speaker modeling and pattern matching) is strongly determined by the quality of the front-end. In other words, classification can be at most as accurate as the features. Over the years, MelFrequency Cepstral Coefficients (MFCC) modeled on the human auditory system has been used as a standard acoustic feature set for speech related applications. In this paper it has been shown that the inverted Mel-Frequency Cepstral Coefficients is one of the performance enhancement parameters for speaker recognition, which contains high frequency region complementary information in it. This paper introduces the Gaussian shaped filter (GF) while calculation MFCC and inverted MFCC in place of traditional triangular shaped bins. The main idea is to introduce a higher amount of correlation between subband outputs. The performance of both MFCC and inverted MFCC improve with GF over traditional triangular filter (TF) based implementation, individually as well as in combination. In this study the Vector Quantization (VQ) feature matching technique was used, due to high accuracy and its simplicity. The proposed investigation achieved 98.57% of efficiency with a very short test voice sample 2 seconds.