Discriminative Auditory-Based Featuresfor Robust Speech Recognition

Speech recognition in noisy environments is one of the long-standing research themes but remains a very important challenge nowadays. Therefore, there is much research into all techniques and approaches to improve the performance of speech recognition systems, even in poor conditions. This paper presents a comparative study under various conditions based on two architectures (GMM-HMM and DNN-HMM), the Hybrid GMM-HMM models using the CMU Sphinx tools and the Hybrid DNN-HMM using the KALDI toolkit in noise environment. In this study, we compare the Hybrid GMM-HMM models and the Hybrid DNN-HMM models to evaluate the performance of the proposed system. The novelty of this paper is to test if the presented tools could be, with good accuracy, recognize the Arabic speech principally in noisy environment. In addition, we adopted the noisy training theory in this paper based on GMM-HMM and DNN-HMM model. We use the public Arabic Speech Corpus for Isolated Words (20 words), three noise levels, and three noise types. The implementation of our system consists of two phases: Features extraction using Mel-frequency Cepstral Coefficient (MFCC) and the classification phase will use separately the previous two models. In order to test the performance of these methods a simulation will presented for different SNR and for different district type of noise.

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.

This paper presents a feature domain approach to the problem of robust speaker verification in noisy acoustic environments. We derive a variational Bayesian algorithm that enhances the log spectra of noisy speech using speaker dependent priors. This algorithm extends prior work by Frey et al. where the Algonquin algorithm was introduced to enhance speech log spectra in order to improve speech recognition in noisy environments. Our work is built on the intuition that speaker dependent priors would work better than priors that attempt to capture global speech properties. Experimental results using the TIMIT data set and the MIT Mobile Device Speaker Verification Corpus (MDSVC) are presented to demonstrate the algorithms performance.

Most 22q11.2 deletion syndrome (22q11DS) patients have middle and outer ear anomalies, whereas some have inner ear malformations. Tbx1, a gene hemizygously deleted in 22q11DS patients and required for ear development, is expressed in multiple tissues during embryogenesis. To determine the role of Tbx1 in the first pharyngeal pouch (PPI) in forming outer and middle ears, we tissue-specifically inactivated the gene using Foxg1-Cre. In the conditional mutants, PPI failed to outgrow, preventing the middle ear bone condensations from forming. Tbx1 was also inactivated in the otic vesicle (OV), resulting in the failure of inner ear sensory organ formation, and in duplication of the cochleovestibular ganglion (CVG). Consistent with the anatomical defects, the sensory genes, Otx1 and Bmp4 were downregulated, whereas the CVG genes, Fgf3 and NeuroD, were upregulated. To delineate Tbx1 cell-autonomous roles, a more selective ablation, exclusively in the OV, was performed using Pax2-Cre. In contrast to the Foxg1-Cre mutants, Pax2-Cre conditional mutant mice survived to adulthood and had normal outer and middle ears but had the same inner ear defects as the Tbx1 null mice, with the same gene expression changes. These results demonstrate that Tbx1 has non-cell autonomous roles in PPI in the formation of outer and middle ears and cell-autonomous roles in the OV. Periotic mesenchymal markers, Prx2 and Brn4 were normal in both conditional mutants, whereas they were diminished in Tbx1-/- embryos. Thus, Tbx1 in the surrounding mesenchyme in both sets of conditional mutants cannot suppress the defects in the OV that occur in the null mutants.

In the world, almost 10% of people have a variety of hearing disorders. Nearly 500 million people live with deafness; more than 32 million of them are children. Therefore, the problem of studying the human hearing system to improve the theoretical and practical equipment of diagnosis for the further treatment of people with hearing impairments is extremely acute.This article is devoted to the analysis of experimentally obtained amplitude-frequency characteristics of the middle ear and to the development of theoretical foundations and the method of electromechanical analogies for the construction of middle ear frequency response.The main possible approaches for theoretical obtaining of the external and middle ear frequency response based on the results of the average frequency response of a healthy person are analyzed, namely: a mechanical model with concentrated parameters, a finite element method and an electromechanical analogy method.The first approach proposes a "mechanical model" in which each component of the system, namely: malleus, incus and stapes, ladder is described as an object having certain mechanical and physical characteristics. The simplest oscillatory system is the mass suspended on a spring. It is commonly believed that movement occurs in the absence of friction. This oscillatory system is a system with lumped parameters, however, this model is designed for objective diagnostic methods that involve the placement of an acoustic probe in the external auditory canal.A further development of mechanical analogies is the Finite Element Method (FEM). In this case, all the objects of the system are broken down into components in three-dimensional space, as a system with distributed parameters, each of which has strictly specified mechanical properties, its own way of connecting with the surrounding parts.Another approach is the method of electromechanical analogies, which is based on the similarity of equations describing oscillatory processes of mechanical and electrical nature. If the equations are similar, then their solutions are the same, so the solution of the mechanical problem can be replaced by the solution of similar electromechanical. By analogy to a mechanical system, the simplest electrical oscillating circuit is the connection of a coil and a capacitor. The oscillations in this circuit are the mutual conversion of the capacitor's electrical energy and the coil's magnetic energy.Electromechanical analogies were used to analyze the oscillations of the outer and middle ears. In this electrical quantities: voltage, capacitance, active resistance, inductance are mechanical: strength, flexibility, active mechanical resistance, mass. The equivalent circuit of the human middle ear was constructed and analyzed using the Simulink application package. The values of the resonant frequencies of the outer and middle ear (364, 748, 1430, 2390 Hz) obtained in this model are in good agreement with the experimental results.As a result, an equivalent electrical circuit is proposed that takes into account both the outer ear and the middle ear, and allows you to reproduce more of the characteristic resonances of the frequency response of the average healthy person.

This paper describes advances in the use of HMM based technology for speaker independent continuous speech recognition, in noisy environment, under hands free interaction mode. For this purpose an array of four omnidirectional microphones is employed as the acquisition system. The processing of phase information in the cross-power spectrum provides the capability both of locating the talker position and of reconstructing an enhanced speech spectrum. Two enhancement techniques are described, that provide recognition improvement in the case of clean input speech as well as under different adverse conditions. The results refer to the use of a new multichannel corpus, collected in a real environment by a microphone array as well as a close-talk microphone.

Many power based features have been proposed in previous studies as alternative to the conventional feature, i.e. MFCC, for speech recognition. These features are of interest because they are empirically shown to be more robust than MFCC in noisy environments. Some studies argue that the compressions of power functions which are less sensitive than log for low energy spectra is one of the reasons while others agree that their performances are heavily affected by their normalization techniques. In this paper, the author focuses on investigating the effect of two normalization methods on power based features for the robustness of speech recognition in noisy environments. The paper specifically addresses features based on the q-log function, an example of power functions widely used in Tsallis statistics. The analysis suggests subtracting the mean may not be the best normalization technique due to its non-additive properties which is confirmed by the experimental results on Aurora-2. The results also confirm that the normalization may contribute more to the robustness of the features than the effect of the q-log compression.

Users of hearing aid devices encounter great difficulty in speech recognition in noisy environments, and show inferior performance in situations with interfering background noise or competing speakers as compared to the case of a quiet background. In such devices, a pre‐processing stage, which first removes the background interference, should greatly boost the speech recognition performance in noisy environments. In this work, the performance of a previously reported speech extraction algorithm is investigated for the purpose of improving the speech intelligibility of hearing aid users. Recently, we performed segregation of speech mixtures using our speech extraction algorithm and showed improvement in the speech recognition performance of normal hearing listeners. In this work, we investigate the performance of our algorithm for users of hearing aids on the same perceptual task of recognizing speech in the presence of either interfering speech or noise. We focus on tuning the segregation algorithm for hearing aid users, and emphasize on the preservation of the appropriate envelope and fine structure cues which will prove most helpful in the recognition of the target speech signal.

Enhancing Robustness of Arabic Speech Recognition in Noisy Environments Using Advanced Feature Extraction and Denoising Techniques Based on Deep Learning Models

We investigate how dominant-frequency information can be used in speech feature extraction to increase the robustness of automatic speech recognition against additive background noise. First, we review several earlier proposed auditory-based feature extraction methods and argue that the use of dominant-frequency information might be one of the major reasons for their improved noise robustness. Furthermore, we propose a new feature extraction method, which combines subband power information with dominant subband frequency information in a simple and computationally efficient way. The proposed features are shown to be considerably more robust against additive background noise than standard mel-frequency cepstrum coefficients on two different recognition tasks. The performance improvement increased as we moved from a small-vocabulary isolated-word task to a medium-vocabulary continuous-speech task, where the proposed features also outperformed a computationally expensive auditory-based method. The greatest improvement was obtained for noise types characterized by a relatively flat spectral density.

In recent years a number of techniques have been proposed to improve the accuracy and the robustness of automatic speech recognition in noisy environments. Among these, suplementing the acoustic information with visual data, mostly extracted from speaker's lip shapes, has been proved to be successful. We have already demonstrated the effectiveness of integrating visual data at two different levels during speech decoding according to both direct and separate identification strategies (DI+SI). This paper outlines methods for reinforcing the visible speech recognition in the framework of separate identification. First, we define visual-specific units using a self-organizing mapping technique. Second, we complete a stochastic learning of these units with a discriminative neural-network-based technique for speech recognition purposes. Finally, we show on a connected-letter speech recognition task that using these methods improves performances of the DI+SI based system under varying noise-level conditions.

With the increase in computing power and the availability of large amounts of data, deep learning techniques, especially convolutional neural networks (CNNS) and recurrent neural networks (RNNS), have become important tools for processing complex signals. These methods show excellent performance in speech recognition, image processing, natural language processing and so on. In this paper, we explore the application of recurrent neural network (RNN) sequence algorithms in the field of computer digital signal processing, highlighting current artificial intelligence techniques and their capabilities in solving complex signal processing problems. First, the paper reviews the basic principles and development of deep learning and RNN sequence algorithms, highlighting the advances these advanced technologies have made in simulating the way the human brain processes information. The practical application and effect of RNN sequence algorithm in computer digital signal processing are demonstrated through experimental data. By comparing with traditional algorithms, we demonstrate the efficiency and accuracy of RNN in processing complex signals, such as speech recognition in noisy environments and real-time video data processing. The experimental data not only demonstrate the effectiveness of RNNS in this field, but also highlight the unique advantages of deep learning methods when dealing with large and high-dimensional data. Through these empirical studies, this paper aims to provide researchers and engineers with an in-depth understanding of the potential of RNNS in digital signal processing applications, and looks forward to the future development direction of artificial intelligence technology in this field.

The advent of artificial intelligence (AI) has revolutionized human-computer interaction, making it more natural and intuitive. This research paper presents the development and implementation of an AI Desktop Voice Assistant designed to enhance productivity and accessibility for users. The voice assistant leverages advanced speech recognition, natural language processing (NLP), and machine learning techniques to understand and execute user commands. Key functionalities include voice-activated application control, web searches, personalized reminders, and real-time information retrieval. Our system integrates with widely-used APIs and services, providing a seamless user experience across various tasks. The paper discusses the architecture of the voice assistant, detailing the integration of components such as the speech recognition engine, NLP models, and the dialogue management system. We explore the challenges encountered during development, including accurate speech recognition in noisy environments and handling ambiguous user commands. Solutions implemented to address these challenges are also presented. Furthermore, we conduct a usability study to evaluate the effectiveness and user satisfaction of the voice assistant. The results indicate a high level of user engagement and satisfaction, demonstrating the practical benefits of incorporating AI-driven voice interfaces into desktop environments. Our findings contribute to the ongoing research in human-computer interaction, suggesting pathways for future enhancements in AI voice assistants..

In this letter, we propose a novel approach to feature compensation for robust speech recognition in noisy environments. We employ the switching linear dynamic model (SLDM) as a parametric model for the clean speech distribution, which enables us to exploit temporal correlations inherent in speech signals. Both the background noise and clean speech components are simultaneously estimated by means of the interacting multiple model (IMM) algorithm.

While current speech recognisers give acceptable performance in carefully controlled environments, their performance degrades rapidly when they are applied in more realistic situations. Generally, the environmental noise may be classified into two classes: the wide-band noise and narrow band noise. While the multi-band model has been shown to be capable of dealing with speech corrupted by narrow-band noise, it is ineffective for wide-band noise. In this paper, we suggest a combination of the frequency-filtering technique with the probabilistic union model in the multi-band approach. The new system has been tested on the TIDIGITS database, corrupted by white noise, noise collected from a railway station, and narrow-band noise, respectively. The results have shown that this approach is capable of dealing with noise of narrow-band or wide-band characteristics, assuming no knowledge about the noisy environment.KeywordsHide Markov ModelDiscrete Cosine TransformSpeech RecognitionRailway StationClean SpeechThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.