Real-world Noisy Environments Research Articles

Effects of entropy in real-world noise on speech perception in listeners with normal hearing and hearing lossa).

Hearing aids show more benefit in traditional laboratory speech-in-noise tests than in real-world noisy environments. Real-world noise comprises a large range of acoustic properties that vary randomly and rapidly between and within environments, making quantifying real-world noise and using it in experiments and clinical tests challenging. One approach is to use acoustic features and statistics to quantify acoustic properties of real-world noise and control for them or measure their relationship to listening performance. In this study, the complexity of real-world noise from different environments was quantified using entropy in both the time- and frequency-domains. A distribution of noise segments from low to high entropy were extracted. Using a trial-by-trial design, listeners with normal hearing and hearing loss (in aided and unaided conditions) repeated back sentences embedded in these noise segments. Entropy significantly affected speech perception, with a larger effect of entropy in the time-domain than the frequency-domain, a larger effect for listeners with normal hearing than for listeners with hearing loss, and a larger effect for listeners with hearing loss in the aided than unaided condition. Speech perception also differed between most environment types. Combining entropy with the environment type improved predictions of speech perception above the environment type alone.

An Empirical Study on Transmission Beamforming for Ultrasonic Guided-Wave Based Structural Health Monitoring.

The development of reliable structural health monitoring techniques is enabling a healthy transition from preventive to condition-based maintenance, hence leading to safer and more efficient operation of different industries. Ultrasonic guided-wave based beamforming is one of the most promising techniques, which supports the monitoring of large thin-walled structures. However, beamforming has been typically applied to the post-processing stage (also known as virtual or receiver beamforming) because transmission or physical beamforming requires complex hardware configurations. This paper introduces an electronic structural health monitoring system that carries out transmission beamforming experiments by simultaneously emitting and receiving ultrasonic guided-waves using several transducers. An empirical characterization of the transmission beamforming technique for monitoring an aluminum plate is provided in this work. The high signal-to-noise ratio and accurate angular precision of the physical signal obtained in the experiments suggest that transmission beamforming can increase the reliability and robustnessof this monitoring technique for large structures and in real-world noisy environments.

Contextual deep learning-based audio-visual switching for speech enhancement in real-world environments

Human speech processing is inherently multi-modal, where visual cues (e.g. lip movements) can help better understand speech in noise. Our recent work [1] has shown that lip-reading driven, audio-visual (AV) speech enhancement can significantly outperform benchmark audio-only approaches at low signal-to-noise ratios (SNRs). However, consistent with our cognitive hypothesis, visual cues were found to be relatively less effective for speech enhancement at high SNRs, or low levels of background noise, where audio-only (A-only) cues worked adequately. Therefore, a more cognitively-inspired, context-aware AV approach is required, that contextually utilises both visual and noisy audio features, and thus more effectively accounts for different noisy conditions. In this paper, we introduce a novel context-aware AV speech enhancement framework that contextually exploits AV cues with respect to different operating conditions, in order to estimate clean audio, without requiring any prior SNR estimation. In particular, an AV switching module is developed by integrating a convolutional neural network (CNN) and long-short-term memory (LSTM) network, that learns to contextually switch between visualonly (V-only), A-only and both AV cues at low, high and moderate SNR levels, respectively. For testing, the estimated clean audio features are utilised using an innovative, enhanced visually-derived Wiener filter (EVWF) for noisy speech filtering. The context-aware AV speech enhancement framework is evaluated in dynamic real-world scenarios (including cafe, street, bus, and pedestrians) at different SNR levels (ranging from low to high SNRs), using benchmark Grid and ChiME3 corpora. For objective testing, perceptual evaluation of speech quality (PESQ) is used to evaluate the quality of the restored speech. For subjective testing, the standard mean-opinion-score (MOS) method is used. Comparative experimental results show the superior performance of our proposed context-aware AV approach, over A-only, V-only, spectral subtraction (SS), and log-minimum mean square error (LMMSE) based speech enhancement methods, at both low and high SNRs. The preliminary findings demonstrate the capability of our novel approach to deal with spectro-temporal variations in real-world noisy environments, by contextually exploiting the complementary strengths of audio and visual cues. In conclusion, our contextual deep learning-driven AV framework is posited as a benchmark resource for the multi-modal speech processing and machine learning communities.

Degenerate unmixing estimation technique of speech mixtures in real environments using wavelets

ABSTRACT Humans are exceptionally good at focusing their attention on a particular person in a noisy environment, mentally muting all other voices and sounds known as cocktail party effect, and this capability comes naturally to them. Although human brain and auditory system can handle this problem with ease, it becomes very hard to solve with computational algorithms. A novel technique is proposed in this paper for separating speech signals, when the number of sources is more than the sensors. Here wavelets are used in initial pre-processing and time-frequency analysis of mixtures to extract the mixing variables which makes it useful in applications involving real-time scenario. The algorithm also converges at a faster rate as we use automatic peak tracking algorithm to track the peak and constructing binary masks. The simulation results on mixtures of speech signals not only show improvement in separation in reverberant conditions but also show better separation results and improved perceptual quality of separated sources in real-world noisy environments.

Broadband, large scale acoustic energy harvesting via synthesized electrical load: II. Electrical load

Existing acoustic energy harvesters are typically resonant structures operated with matched loads, yielding narrowband, and hence low, energy collection from broadband noise sources. Additionally, existing acoustic energy harvesters tend to exhibit MEMS-scale sizes, with correspondingly low power collection and outputs. In contrast, this paper presents the combined real and reactive electrical loading of a wide-area harvester which yields efficient broadband harvesting at higher power. Building on the harvester designed and modeled in Part I, this paper develops the reactive loading and its operational amplifier implementation, illuminating along the way several design issues critical to optimal performance and stability. The loading enables an experimental harvester capable of harvesting acoustic energy with an efficiency of 0.3%–3% over the frequency range of 50–500 Hz. The harvester is demonstrated in a real-world scenario, collecting approximately 2.3 μJ per aircraft takeoff event in an airport environment. This demonstrates the efficacy of acoustic energy harvesting energy and its potential for powering wireless sensor nodes in real-world noisy environments. While the loading is implemented here with lossy operational amplifier circuits, it is amenable to implementation with efficient power electronics.

Fuzzy Integral With Particle Swarm Optimization for a Motor-Imagery-Based Brain–Computer Interface

A brain-computer interface (BCI) system using elec-troencephalography signals provides a convenient means of communication between the human brain and a computer. Motor imagery (MI), in which motor actions are mentally rehearsed without engaging in actual physical execution, has been widely used as a major BCI approach. One robust algorithm that can successfully cope with the individual differences in MI-related rhythmic patterns is to create diverse ensemble classifiers using the subband common spatial pattern (SBCSP) method. To aggregate outputs of ensemble members, this study uses fuzzy integral with particle swarm optimization (PSO), which can regulate subject-specific parameters for the assignment of optimal confidence levels for classifiers. The proposed system combining SBCSP, fuzzy integral, and PSO exhibits robust performance for offline single-trial classification of MI and real-time control of a robotic arm using MI. This paper represents the first attempt to utilize fuzzy fusion technique to attack the individual differences problem of MI applications in real-world noisy environments. The results of this study demonstrate the practical feasibility of implementing the proposed method for real-world applications.

Feature Extraction Method for Improving Speech Recognition in Noisy Environments

The paper presents a feature extraction method, named as Normalized Gammachirp Cepstral Coefficients (NGCC) that incorporates the properties of the peripheral auditory system to improve robustness in noisy speech recognition. The proposed method is based on a second order low-pass filter and normalized gammachirp filterbank to emulate the mechanisms performed in the outer/middle ear and cochlea. The speech recognition performance of this method is conducted on the speech signals in real-world noisy environments. Experimental results demonstrate that method outperformed the classical feature extraction methods in terms of speech recognition rate. The used Hidden Markov Models based speech recognition system is employed on the HTK 3.4.1 platform (Hidden Markov Model Toolkit).

Noise Robust Speech Parameterization using Relative Spectra and Auditory Filterbank

In the present study, a new feature extraction method based on relative spectra and gammachirp auditory filterbank is proposed for robust noisy speech recognition. The relative spectra filtering are applied to the log of the output of the gammachirp filterbank which incorporates the properties of the cochlear filter in order to remove uncorrelated additive noise components. The performances of this method have been evaluated on the isolated speech word corrupted by real-world noisy environments using the continuous Gausian-Mixture density Hidden Markov Model. The evaluation of the experimental results shows that the proposed method achieves best recognition rates compared to the conventional techniques like Perceptual Linear Prediction (PLP), Linear Predictive Cepstral Coefficients (LPCC) and Mel-Frequency Cepstral Coefficients (MFCC).

Comparison of Speech Recognition With Adaptive Digital and FM Remote Microphone Hearing Assistance Technology by Listeners Who Use Hearing Aids

The purpose of this study was to compare the benefits of 3 types of remote microphone hearing assistance technology (HAT), adaptive digital broadband, adaptive frequency modulation (FM), and fixed FM, through objective and subjective measures of speech recognition in clinical and real-world settings. Participants included 11 adults, ages 16 to 78 years, with primarily moderate-to-severe bilateral hearing impairment (HI), who wore binaural behind-the-ear hearing aids; and 15 adults, ages 18 to 30 years, with normal hearing. Sentence recognition in quiet and in noise and subjective ratings were obtained in 3 conditions of wireless signal processing. Performance by the listeners with HI when using the adaptive digital technology was significantly better than that obtained with the FM technology, with the greatest benefits at the highest noise levels. The majority of listeners also preferred the digital technology when listening in a real-world noisy environment. The wireless technology allowed persons with HI to surpass persons with normal hearing in speech recognition in noise, with the greatest benefit occurring with adaptive digital technology. The use of adaptive digital technology combined with speechreading cues would allow persons with HI to engage in communication in environments that would have otherwise not been possible with traditional wireless technology.

Evaluations on underdetermined blind source separation in adverse environments using time-frequency masking

The successful implementation of speech processing systems in the real world depends on its ability to handle adverse acoustic conditions with undesirable factors such as room reverberation and background noise. In this study, an extension to the established multiple sensors degenerate unmixing estimation technique (MENUET) algorithm for blind source separation is proposed based on the fuzzy c-means clustering to yield improvements in separation ability for underdetermined situations using a nonlinear microphone array. However, rather than test the blind source separation ability solely on reverberant conditions, this paper extends this to include a variety of simulated and real-world noisy environments. Results reported encouraging separation ability and improved perceptual quality of the separated sources for such adverse conditions. Not only does this establish this proposed methodology as a credible improvement to the system, but also implies further applicability in areas such as noise suppression in adverse acoustic environments.

An Adaptive Methodology for Ubiquitous ASR System

Achieving and maintaining the performance of ubiquitous (Automatic Speech Recognition) ASR system is a real challenge. The main objective of this work is to develop a method that will improve and show the consistency in performance of ubiquitous ASR system for real world noisy environment. An adaptive methodology has been developed to achieve an objective with the help of implementing followings, Cleaning speech signal as much as possible while preserving originality / intangibility using various modified filters and enhancement techniques. Extracting features from speech signals using various sizes of parameter. Train the system for ubiquitous environment using multi-environmental adaptation training methods. Optimize the word recognition rate with appropriate variable size of parameters using fuzzy technique. The consistency in performance is tested using standard noise databases as well as in real world environment. A good improvement is noticed. This work will be helpful to give discriminative training of ubiquitous ASR system for better Human Computer Interaction (HCI) using Speech User Interface (SUI).

A HYBRID METHOD FOR AUTOMATIC SPEECH RECOGNITION PERFORMANCE IMPROVEMENT IN REAL WORLD NOISY ENVIRONMENT

It is a well known fact that, speech recognition sy stems perform well when the system is used in condi tions similar to the one used to train the acoustic model s. However, mismatches degrade the performance. In adverse environment, it is very difficult to predic t the category of noise in advance in case of real world environmental noise and difficult to achieve enviro nmental robustness. After doing rigorous experiment al study it is observed that, a unique method is not a vailable that will clean the noisy speech as well a s preserve the quality which have been corrupted by r eal natural environmental (mixed) noise. It is also observed that only back-end techniques are not suff icient to improve the performance of a speech recognition system. It is necessary to implement pe rformance improvement techniques at every step of back-end as well as front-end of the Automatic Spee ch Recognition (ASR) model. Current recognition systems solve this problem using a technique called adaptation. This study presents an experimental st udy that aims two points, first is to implement the hyb rid method that will take care of clarifying the sp eech signal as much as possible with all combinations of filters and enhancement techniques. The second poi nt is to develop a method for training all categories of noise that can adapt the acoustic models for a new environment that will help to improve the performan ce of the speech recognizer under real world environmental mismatched conditions. This experiment confirms that hybrid adaptation methods improve the ASR performance on both levels, (Signal-to-Noise Ratio) SNR improvement as well as word recognition accuracy in real world noisy environment.

A Robust Speech Recognition System for Communication Robots in Noisy Environments

The application range of communication robots could be widely expanded by the use of automatic speech recognition (ASR) systems with improved robustness for noise and for speakers of different ages. In past researches, several modules have been proposed and evaluated for improving the robustness of ASR systems in noisy environments. However, this performance might be degraded when applied to robots, due to problems caused by distant speech and the robot's own noise. In this paper, we implemented the individual modules in a humanoid robot, and evaluated the ASR performance in a real-world noisy environment for adults' and children's speech. The performance of each module was verified by adding different levels of real environment noise recorded in a cafeteria. Experimental results indicated that our ASR system could achieve over 80% word accuracy in 70-dBA noise. Further evaluation of adult speech recorded in a real noisy environment resulted in 73% word accuracy.

MODELING AUDITORY PATHWAY FOR INTELLIGENT INFORMATION ACQUISITION

An auditory model has been developed for an intelligent speech information acquisition system in real-world noisy environment. The developed mathematical model of the human auditory pathway consists of three components, i.e. the nonlinear feature extraction from cochlea to auditory cortex, the binaural processing at superior olivery complex, and the top-down attention from higher brain to the cochlea. The feature extraction is based on information-theoretic sparse coding throughout the auditory pathway. Also, the time-frequency masking is incorporated as a model of the lateral inhibition in both time and frequency domain. The binaural processing is modeled as the blind signal separation and adaptive noise canceling based on the independent component analysis with hundreds of time-delays for noisy reverberated signals. The Top-Down (TD) attention comes from familiarity and/or importance of the sensory information, i.e. the sound, and a simple but efficient TD attention model had been developed based on the error backpropagation algorithm. Also, the binaural processing and top-down attention are combined for speech signals with heavy noises. This auditory model requires extensive computing, and special hardware had been developed for real-time applications. Experimental results demonstrate much better recognition performance in real-world noisy environments.

Text-Independent Speaker Verification for Real Fast-Varying Noisy Environments

Investigating Speaker Verification in real-world noisy environments, a novel feature extraction process suitable for suppression of time-varying noise is compared with a fine-tuned spectral subtraction method. The proposed feature extraction process is based on approximating the clean speech and the noise spectral magnitude with a mixture of Gaussian probability density functions (pdfs) by using the Expectation-Maximization algorithm (EM). Subsequently, the Bayesian inference framework is applied to the degraded spectral coefficients, and by employing Minimum Mean Square Error Estimation (MMSE), a closed form solution for the spectral magnitude estimation task is derived. The estimated spectral magnitude finally is incorporated into the Mel-Frequency Cepstral Coefficients (MFCCs) front-end of a baseline text-independent speaker verification system, based on Probabilistic Neural Networks, which participated successfully in the 2002 NIST (National Institute of Standards and Technology of USA) Speaker Recognition Evaluation. A comparative study of the proposed technique for real-world noise types demonstrates a significant performance gain compared to the baseline speech features and to the spectral subtraction enhancement method. Improvements of the absolute speaker verification performance with more than 27% for 0 dB signal-to-noise ratio (SNR), compared to the MFCCs, and with more than 13% for −5 dB SNR, compared to the spectral subtraction version, were obtained in the case of a passing-by aircraft scenario.

The Relative Distance Vector Neural Network (RDVNN) Model: A Hybrid Approach to Speech Recognition

This paper introduces a novel insight to the problem of Automatic Speech Recognition (ASR). Worldwide many practical systems had been developed for ASR. Most of these systems were based on Hidden Markov Models (HMM). This is state-of-the-art paradigm in ASR. Despite the fact that HMMs are successful under a diversity of conditions, they do suffer from some limitations that limit their applicability to real-world noisy environments. As a result, several researchers moved to Artificial Neural Networks (ANNs) as an alternative technique for ASR, in order to overcome the limitations encountered in pure HMM implementation. Soon after, interest moved over to hybrid systems that combine HMMs and ANNs within a single unifying hybrid architecture. In this study a hybrid DTW/ANN ASR system will be introduced, explained, implemented and analyzed, which has been given the name Relative Distance Vector Neural Network (RDVNN) Model.Adequate experiments had been performed to reveal the main characteristics of the present novel hybrid ASR system. The results are believed to be encouraging and the system is easy to implement. For speaker dependent the accuracy is near perfect (error rate is less than 1%). For speaker independent models the results attained are comparable with most world-wide results known for the state-of-the-art ASR small task systems. Many aspects of the RDVNN technique are illustrated through experimental work to demonstrate these findings. One of the main advantages of the RDVNN method is that it can be applied to various other similar problem domains.

Top-down attention to complement independent component analysis for blind signal separation

For robust speech recognition in real-world noisy environments, we present an algorithm to incorporate blind signal separation based on independent component analysis (ICA) and top-down attention processing. While ICA-based unmixing networks learn the inverse of mixing characteristics in frequency domain, their performance is limited by mismatches between the real-world mixing characteristics and assumptions of the ICA algorithm. The top-down process from a multiplayer Perceptron (MLP) classifier provides additional information on the speech signal, and fine-tunes the networks to compensate for the mismatches. For noisy speech signals recorded in a real office environment, the developed algorithm demonstrated great improvements on recognition performance.

Auditory processing of speech signals for robust speech recognition in real-world noisy environments

This paper presents a new approach to an auditory model for robust speech recognition in noisy environments. The proposed model consists of cochlear bandpass filters and nonlinear operations in which frequency information of the signal is obtained by zero-crossing intervals. Intensity information is also incorporated by a peak detector and a compressive nonlinearity. The robustness of the zero-crossings in spectral estimation is verified by analyzing the variance of the level-crossing intervals as a function of the crossing level values. Compared with other auditory models, the proposed auditory model is computationally efficient, free from many unknown parameters, and able to serve as a robust front-end for speech recognition in noisy environments. Experimental results of speech recognition demonstrate the robustness of the proposed method in various types of noisy environments.

Auditory model for robust speech recognition in real world noisy environments

A computationally efficient and noise-robust auditory model is developed based on the detection of zero-crossings for speech recognition in real world noisy environments.