A comparative study for Arabic speech recognition system in noisy environments

Automatic speech recognition (ASR) system is used to recognize the text transcript from the given speech signal. Such speech signal can contain either isolated words or large vocabulary continuous speech (LVCS). Isolated words can be recognized with high accuracy in clean environment, but recognizing continuous words involves various parameters like speech corpus, speaker, environment noise, etc., that affects the accuracy of automatic speech recognition system directly. In the proposed work, hybrid feature extraction technique combines the perceptual linear predictive (PLP) and mel frequency cepstral coefficient (MFCC) to improve the accuracy of ASR in noisy environment. Voice activity and detection (VAD)-based frame dropping is used for improving the phonemes modeling by removing the pauses and distorted elements from the given speech signal. The proposed hybrid model with VAD is implemented by using self-generated speech corpus and shows relatively 12% increase in recognition rate compared with the state-of-the-art methodology.KeywordsAutomatic speech recognition (ASR)Perceptual linear predictive (PLP)Mel frequency cepstral coefficient (MFCC)Voice activity and detection (VAC)

This paper describes the work done in improving the performance of Tamil speech recognition system by using Time Scale Modification (TSM) and Vocal Tract Length Normalization (VTLN) techniques. The speech recognition system for Tamil language was developed using a new approach of text independent speech segmentation, with a phoneme based language model for recognition. There is degradation in the performance of speech recognition due to variations in the speaking rate and vocal tract shape among different speakers. In order to improve the performance of speech recognition system, both TSM and VTLN normalization techniques were used in this work. The TSM was implemented using the Phase vocoder approach and the VTLN was implemented using speaker specific bark/mel scale in bark/mel domain. The performance of Tamil speech recognition system was improved by performing both TSM and VTLN normalization techniques.

Combined speech enhancement and auditory modelling for robust distributed speech recognition

Speech production knowledge has been used to enhance the phonetic representation and the performance of automatic speech recognition (ASR) systems successfully. Representations of speech production make simple explanations for many phenomena observed in speech. These phenomena can not be easily analyzed from either acoustic signal or phonetic transcription alone. One of the most important aspects of speech production knowledge is the use of articulatory knowledge, which describes the smooth and continuous movements in the vocal tract. In this paper, we present a new articulatory model to provide available information for rescoring the speech recognition lattice hypothesis. The articulatory model consists of a feature front-end, which computes a voicing feature based on a spectral harmonics correlation (SHC) function, and a back-end based on the combination of deep neural networks (DNNs) and hidden Markov models (HMMs). The voicing features are incorporated with standard Mel frequency cepstral coefficients (MFCCs) using heteroscedastic linear discriminant analysis (HLDA) to compensate the speech recognition accuracy rates. Moreover, the advantages of two different models are taken into account by the algorithm, which retains deep learning properties of DNNs, while modeling the articulatory context powerfully through HMMs. Mandarin speech recognition experiments show the proposed method achieves significant improvements in speech recognition performance over the system using MFCCs alone.

A mismatch between the training and testing in noisy circumstance often causes a drastic decrease in the performance of speech recognition system. The robust feature coefficients might suppress this sensitivity of mismatch during the recognition stage. In this paper, we investigate the noise robustness of LPC Cepstral Coefficients (LPCC) by using speech enhancement with feature post-processing. At front-end, speech enhancement in the wavelet domain is used to remove noise components from noisy signals. This enhanced processing adopts the combination of discrete wavelet transform (DWT), wavelet packet decomposition (WPD), multi-thresholds processing etc to obtain the estimated speech. The feature post-processing employs cepstral mean normalization (CMN) to compensate the signal distortion and residual noise of enhanced signals in the cepstral domain. The performance of digit speech recognition systems is evaluated under noisy environments based on NOISEX-92 database. The experimental results show that the presented method exhibits performance improvements in the adverse noise environment compared with the previous features.

The performance of the speech recognition system for English classroom teaching is largely affected by the surrounding environment. These interference signals will seriously reduce the quality and intelligibility of the speech signal, thereby greatly reducing the performance of the far-field speech recognition system. Aiming at word order detection in English classroom teaching, this paper proposes an analysis model based on block coding and improved genetic algorithm. Moreover, for DNN-based single-channel speech enhancement algorithms, this paper proposes PDNNs and PLSTMs to solve the problem of serious performance degradation of prototype DNN speech enhancement under low signal-to-noise ratio. This method decomposes the entire enhancement task into multiple subtasks to complete, and the previously completed subtasks will provide prior knowledge for the subsequent subtasks, so that the subsequent subtasks can learn its goals better. In general, the experimental results prove the reliability of the model constructed in this paper.

This paper describes a study of a set of features based on cepstral mean and variance normalization (CMVN) plus auto regressive moving average (ARMA) filtering technique which is called MVA and on histogram equalization (HEQ) for robust speech recognition. First, we use MVA then HEQ in combination with CMVN and ARMA filtering as a post-processing module to mel frequency cepstral coefficients (MFCC), Relative Spectral-Perceptual linear prediction (RASTA-PLP) and power normalized cepstral coefficients (PNCC) features to improve the performance of the automatic speech recognition (ASR) system. The results on the Arabic database task have shown that both methods MVA and HEQ+ARMA improves the success rate for all features compared to the baseline system however HEQ was not found to perform better than MVA. The results also provide that RASTA-PLP outperforms PNCC and MFCC features.

With the continuous development of science and technology in recent years, there are more and more ways of human-computer interaction, and its technology is becoming more and more mature. Among them, the human-computer voice interaction mode occupies an important position, which is gradually integrated into our lives. However, through reviewing and summarizing previous studies, it is found that speech recognition still has some shortcomings in noise reduction processing [2]. Therefore, to design a system that is immune to ambient noise and can perform voice human-computer interaction more accurately, based on spatial filtering technology and CI1103 speech recognition module, a new type of noise reduction speech recognition system using a unique anti-noise processing microphone is proposed. In this new system, combined with the built-in anti-noise filter of CI1103, the noise reduction process during speech recognition is realized with the help of the spatial filtering technology where the new digital signal is used to process IC “BU8332KV-M” [3]. Its peripheral control interfaces such as built-in CPU core and Audio Codec module with high performance and low power, integrated multiple UART, IIC, SPI, PWM, and GPIO can develop all kinds of cost-effective and single-chip intelligent voice products. Experimental results show that the new noise reduction speech recognition system has higher speech recognition accuracy than that of the traditional speech recognition systems in noisy environments, which has the function of rejecting false recognition, and is suitable for various speech systems with environmental noise interference.

This paper presents the effect of mean normalization to various types of cepstral coefficients for robust speech recognition in noisy environments. Although the cepstral mean normalization (CMN) technique was originally designed to compensate channel distortion, it has also been proved that the CMN also improves recognition accuracy in additive noisy environment. However, no one has yet considered the interaction of CMN with spectral mapping functions required for extracting cepstral features. This paper investigates the impact of CMN to the speech recognition system depending on the types of spectral mapping function by mathematically analyzing the amount of spectral distortion between clean and noisy conditions. The analytic result is also confirmed by comparing the type of recognition error patterns in automatic speech recognition experiment with Aurora 2 database. Experimental results show that the performance improvement by adopting CMN becomes significant if the logarithmic function is replaced with the appropriate setting of fractional power mapping function. Especially, the deletion errors are dramatically reduced.

A novel method for improving the accuracy of automatic speech recognition system by adding non-acoustic parameters are discussed in this paper. The gestural features which are commonly co-expressive with speech is considered for improving the accuracy of ASR system in noisy environment. Both dynamic and static gestures are integrated with speech recognition system and tested in various environmental conditions, i.e., noise levels. The accuracy of continuous speech recognition system and isolated word recognition system are tested with and without gestures under various noise conditions. The addition of visual features provides stable recognition accuracy under different environmental noise conditions for acoustic signals.

In the noisy environment, the performance of speech recognition system may become worse to some extent. In order to solve this problem, this paper used the zero-crossings with peak amplitudes (ZCPA) features as speech feature parameters, which are based on human hearings property. The extraction method of ZCPA features is that calculating the unward zero-crossing rate of speech signal gets frequency information, compressing amplitudes non-linearly incorporates intensity information, and form finally output features. This paper also used the support vector machine as recognition machine, realized a speech recognition system of non-specific person and isolated words with Visual C++ programming, and got the recognition results in different SNRs and in different words. Experiments indicate that the recognition correct rates based on ZCPA features and support vector machine are much higher than those of based on traditional hidden Markov model, and also have better robustness.

In this paper, we present a novel approach for front-end speech parameterization that is more robust towards pitch variations than the most commonly used technique. Earlier works have shown that, insufficient smoothing of magnitude spectrum leads to pitch-induced distortions. This, in turn, results in poor performance of speech recognition system especially for high-pitched child speakers. To overcome this shortcoming, the short-time magnitude spectrum is first decomposed into several components using a modified version of empirical mode decomposition (EMD). Next, the lowest-order component is discarded and the spectrum is reconstructed using the rest of the higherorder modes for sufficiently smoothing the spectrum. The Mel-frequency cepstral coefficients (MFCC) are then extracted using the smoothed spectra. The signal domain analyses presented in this paper demonstrate that the ill-effects of pitch variations get significantly reduced by the inclusion of proposed spectral smoothing module. In order to statistically validate the same, an automatic speech recognition system is developed using speech data from adult speakers. To simulate large pitch differences, evaluations are performed on a test set which consists of speech data from child speakers. Inclusion of proposed spectral smoothing module leads to a relative improvement of 12% over the baseline system employing acoustic modeling based on deep neural network.

Performance evaluation of Hindi speech recognition system using optimized filterbanks

Improved likelihood ratio test based voice activity detector applied to speech recognition

Presence of additive noise in speech signals deteriorates the performance of automatic speech recognition systems in cars. For a speech recognition system, we must know where speech and nonspeech segments are. In this paper a new Band Partitioning Spectral Entropy endpoint detection (BPSE) method is used to get the speech start and end point of speech precisely. After that Band Spectral Subtraction (BSS) methods provide in this paper can decrease additive noise obviously. Mel Frequency Cepstral Coefficients (MFCC) are extracted from segmented speech signals. The coefficients are recognized by Hidden Markov Model. The results show that the recognition accuracy can be improved from 39.3% to 95.5%.