Effects Of Reverberation Research Articles

Denoising Directional Room Impulse Responses with Spatially Anisotropic Late Reverberation Tails

Directional room impulse responses (DRIR) measured with spherical microphone arrays (SMA) enable the reproduction of room reverberation effects on three-dimensional surround-sound systems (e.g., Higher-Order Ambisonics) through multichannel convolution. However, such measurements inevitably contain a nondecaying noise floor that may produce an audible “infinite reverberation effect” upon convolution. If the late reverberation tail can be considered a diffuse field before reaching the noise floor, the latter may be removed and replaced with an extension of the exponentially-decaying tail synthesized as a zero-mean Gaussian noise. This has previously been shown to preserve the diffuse-field properties of the late reverberation tail when performed in the spherical harmonic domain (SHD). In this paper, we show that in the case of highly anisotropic yet incoherent late fields, the spatial symmetry of the spherical harmonics is not conducive to preserving the energy distribution of the reverberation tail. To remedy this, we propose denoising in an optimized spatial domain obtained by plane-wave decomposition (PWD), and demonstrate that this method equally preserves the incoherence of the late reverberation field.

Interaural Coherence Estimation for Speech Processing in Reverberant Environment

Interaural coherence is used to quantify the effects of reverberation on speech, and previous studies applied the conventional method using all previous time data in the form of an infinite impulse response filter to estimate interaural coherence. To consider a characteristic of speech that continuously changes over time, this paper proposes a new method of estimating interaural coherence using time data within a finite length of speech, which is called the quasi-steady interval. The length of the quasi-steady interval is determined with various frequency bands, reverberation times, and short-time Fourier transform (STFT) variables through numerical experiment, and it decreased as reverberation time decreased and the frequency increased. In this interval, a diffuse speech, which is an infinite sum of reflected speeches of different propagating paths, is uncorrelated between two microphones apart from each other; thus, the coherence is close to zero. However, a direct speech measured at the two microphones has steady amplitude and phase difference in this internal; thus, the coherence is close to one. Moreover, the new method is the form of a finite impulse response filter that has a linear phase delay or zero phase delay with respect to speech to frequency; thus, the same or zero time delay for each frequency is applied to the power spectral density. Therefore, the coherence estimation of the new method is closer to the ideal value than the conventional one, and the coherence is accurately estimated at the time–frequency bins of direct speech, which is time-varying according to speech variation.

Sensitivity of Pitch Frequency Estimation to Reverberation Effect

This paper investigates the effect of reverberation on pitch frequency estimation. The autocorrelation function (ACF) method is used for pitch frequency estimation with and without reverberation effect. This paper modeled the reverberation effect on speech signal using a comb filter. The estimation error percentage of a comb filter at the length mild 8, moderate 10, and severe 12 in these scenarios have been investigated. The accuracy of the pitch frequency estimation is evaluated for the different scenarios for further accurate speech processing and verification.

End-to-End Classification of Reverberant Rooms Using DNNs

Reverberation is present in our workplaces, our homes, concert halls and theatres. This article investigates how deep learning can use the effect of reverberation on speech to classify a recording in terms of the room in which it was recorded. Existing approaches in the literature rely on domain expertise to manually select acoustic parameters as inputs to classifiers. Estimation of these parameters from reverberant speech is adversely affected by estimation errors, impacting the classification accuracy. In order to overcome the limitations of previously proposed methods, this paper shows how DNNs can perform the classification by operating directly on reverberant speech spectra and a CRNN with an attention-mechanism is proposed for the task. The relationship is investigated between the reverberant speech representations learned by the DNNs and acoustic parameters. For evaluation, AIRs are used from the ACE-challenge dataset that were measured in 7 real rooms. The classification accuracy of the CRNN classifier in the experiments is 78% when using 5 hours of training data and 90% when using 10 hours.

A Comparative Study between Pitch Detection Techniques on Reverberant Speech Signals

Reverberation is one of the effects that occur regularly in closed room due to multiple reflections. This paper investigates the result of reverberation on both male and female speech signals. This effect is reflected in pitch frequency of speech signals. This parameter is important as it is usually used for speaker identification. Hence, several methods for pitch frequency estimation are investigated and compared on clear and reverberant male and female speech signals to select the one that is not affected so much by the reverberation effect.

Monaural Speech Dereverberation Using Temporal Convolutional Networks with Self Attention.

In daily listening environments, human speech is often degraded by room reverberation, especially under highly reverberant conditions. Such degradation poses a challenge for many speech processing systems, where the performance becomes much worse than in anechoic environments. To combat the effect of reverberation, we propose a monaural (single-channel) speech dereverberation algorithm using temporal convolutional networks with self attention. Specifically, the proposed system includes a self-attention module to produce dynamic representations given input features, a temporal convolutional network to learn a nonlinear mapping from such representations to the magnitude spectrum of anechoic speech, and a one-dimensional (1-D) convolution module to smooth the enhanced magnitude among adjacent frames. Systematic evaluations demonstrate that the proposed algorithm improves objective metrics of speech quality in a wide range of reverberant conditions. In addition, it generalizes well to untrained reverberation times, room sizes, measured room impulse responses, real-world recorded noisy-reverberant speech, and different speakers.

Effect of Reverberation Phenomena on Text- independent Speaker Recognition Based Deep Learning

Speaker recognition is one of many biometric authentications, due to its high importance in many applications of security considerations and telecommunications. The main aspiration of speaker recognition system is to know who is speaking depending on voice characteristics. Many current researches focuses on text-dependent speaker recognition which has a pre-knowledge of what utterance the speaker will say. In this paper text-independent speaker recognition system is used, where no prior knowledge is accessible in the context of the speakers’ utterances for all stages. A Convolutional Neural Network (CNN) based feature extraction is extended to a text-independent Speaker recognition task. Also the effect of reverberation on speaker recognition is addressed. All the speech signals are converted into images by obtaining their spectrograms. A proposed CNN model is presented to enhance the performance of the system in case of a reverberant signal. It depends on image processing concepts, and hence spectrograms of signals are used. The proposed model is compared with a conventional benchmark model. The performance of the recognition system is measured by the recognition rate in the case of clean and reverberant data.

Study for Speaker Identification Under Reverberation Effect

Speech is the way people interact with each other. With the development of computer technology, some researchers have sought to find techniques that allow the computer to understand natural speech. Smart systems are now trying to imitate the functions of the human brain by using neural networks. Reverberation represents interference noise on the original speech signal. The aim of the research is investigate of reverberation effect on speech signal and whether it affects the identification of the speaker or not to determine the best scenario for identifying the speaker in the presence of reverberation. This study is done using feature extraction with Mel-Frequency Capstral coefficients (MFCCs) and neural networks.

Scoring-Based ML Estimation and CRBs for Reverberation, Speech, and Noise PSDs in a Spatially Homogeneous Noise Field

Hands-free speech systems are subject to performance degradation due to reverberation and noise. Common methods for enhancing reverberant and noisy speech require the knowledge of the speech, reverberation and noise power spectral densities (PSDs). Most literature on this topic assumes that the noise power spectral density (PSD) matrix is known. However, in many practical acoustic scenarios, the noise PSD is unknown and should be estimated along with the speech and the reverberation PSDs. In this article, the noise is modeled as a spatially homogeneous sound field, with an unknown time-varying PSD multiplied by a known time-invariant spatial coherence matrix. We derive two maximum likelihood estimators (MLEs) for the various PSDs, including the noise: The first is a non-blocking-based estimator, that jointly estimates the PSDs of the speech, reverberation and noise components. The second MLE is a blocking-based estimator, that blocks the speech signal and estimates the reverberation and noise PSDs. Since a closed-form solution does not exist, both estimators iteratively maximize the likelihood using the Fisher scoring method. In order to compare both methods, the corresponding Cramer-Rao Bounds (CRBs) are derived. For both the reverberation and the noise PSDs, it is shown that the non-blocking-based CRB is lower than the blocking-based CRB. Performance evaluation using both simulated and real reverberant and noisy signals, shows that the proposed estimators outperform competing estimators, and greatly reduce the effect of reverberation and noise.

Impact of Background Noise Fluctuation and Reverberation on Response Time in a Speech Reception Task.

Purpose This study examines the effects of reverberation and noise fluctuation on the response time (RT) to the auditory stimuli in a speech reception task. Method The speech reception task was presented to 76 young adults with normal hearing in 3 simulated listening conditions (1 anechoic, 2 reverberant). Speechlike stationary and fluctuating noise were used as maskers, in a wide range of signal-to-noise ratios. The speech-in-noise tests were presented in a closed-set format; data on speech intelligibility and RT (time elapsed from the offset of the auditory stimulus to the response selection) were collected. A slowing down in RTs was interpreted as an increase in listening effort. Results RTs slowed down in the more challenging signal-to-noise ratios, with increasing reverberation and for stationary compared to fluctuating noise, consistently with a fluctuating masking release scheme. When speech intelligibility was fixed, it was found that the estimated RTs were similar or faster for stationary compared to fluctuating noise, depending on the amount of reverberation. Conclusions The current findings add to the literature on listening effort for listeners with normal hearing by indicating that the addition of reverberation to fluctuating noise increases RT in a speech reception task. The results support the importance of integrating noise and reverberation to provide accurate predictors of real-world performance in clinical settings.

Comparison of speech intelligibility of elderly aged 60–69 years and young adults in the noisy and reverberant environment

In contrast to young adults with the normal hearing ability, most of the elderly can difficultly hear the speech signals in an unfavorable noisy and reverberant environment. In this paper, the effect of noise and reverberation in a room environment on the Chinese speech intelligibility of elderly (60–69 years old persons) and young adults with the normal hearing ability at different reverberation time (RT), background noise level (BNL), and signal-to-noise ratio (SNR) is investigated by using the auralization method. The results show that the speech intelligibility scores of Chinese elderly and young adults decrease with the increase in RT but increase with the increase in SNR. The obtained speech intelligibility scores of the young adults are higher than those of the elderly under the same test conditions. The speech intelligibility scores of the elderly are poorer than those of the young adults at high BNL, long RT, and low SNR. Namely, it is found that the elderly are more sensitive to the changes in reverberation case and reverberation plus noise case than the young adults. Moreover, the difference in the speech intelligibility scores between the elderly and young adults decreases with the decrease in the BNL. Lastly, it is shown that a low BNL is beneficial for improving the Chinese speech intelligibility of the elderly in a noisy and reverberant room environment.

Effects of Reverberation on the Relation Between Compression Speed and Working Memory for Speech-in-Noise Perception.

Previous study has suggested that when listening in modulated noise, individuals benefit from different wide dynamic range compression (WDRC) speeds depending on their working memory ability. Reverberation reduces the modulation depth of signals and may impact the relation between WDRC speed and working memory. The purpose of this study was to examine this relation across a range of reverberant conditions. Twenty-eight older listeners with mild-to-moderate sensorineural hearing impairment were recruited in the present study. Individual working memory was measured using a Reading Span test. Sentences were combined with noise at two signal to noise ratios (2 and 5 dB SNR), and reverberation was simulated at a range of reverberation times (0.00, 0.75, 1.50, and 3.00 sec). Speech intelligibility was measured in listeners when listening to the sentences processed with simulated fast-acting and slow-acting WDRC conditions. There was a significant relation between WDRC speed and working memory with minimal or no reverberation. Consistent with previous research, this relation was such that individuals with high working memory had higher speech intelligibility with fast-acting WDRC, and individuals with low working memory performed better with slow-acting WDRC. However, at longer reverberation times, there was no relation between WDRC speed and working memory. Consistent with previous studies, results suggest that there is an advantage of tailoring WDRC speed based on an individual's working memory under anechoic conditions. However, the present results further suggest that there may not be such a benefit in reverberant listening environments due to reduction in signal modulation.

Moderate Reverberation Does Not Increase Subjective Fatigue, Subjective Listening Effort, or Behavioral Listening Effort in School-Aged Children.

Background noise and reverberation levels in typical classrooms have negative effects on speech recognition, but their effects on listening effort and fatigue are less well understood. Based on the Framework for Understanding Effortful Listening, noise and reverberation would be expected to increase both listening effort and fatigue. However, previous investigations of the effects of reverberation for adults have resulted in mixed findings. Some discrepancies in the literature might be accounted for by methodological differences; behavioral and subjective indices of listening effort do not often align in adults. The effects of sustained listening on self-reported fatigue in school-aged children are also not well understood. The purposes of this project were to (1) evaluate the effects of noise and reverberation on listening effort in school-aged children using behavioral and subjective measures, (2) compare subjective and behavioral indices of listening effort, and (3) evaluate the effects of reverberation on self-reported fatigue. Twenty typically developing children (10–17 years old) participated. Participants completed dual-task testing in two rooms that varied in terms of reverberation, an audiometric sound booth and a moderately reverberant room. In each room, testing was completed in quiet and in two levels of background noise. Participants provided subjective ratings of listening effort after completing the dual-task in each listening condition. Subjective ratings of fatigue were completed before and after testing in each level of reverberation. Results revealed background noise, not reverberation, increased behavioral and subjective listening effort. Subjective ratings of perceived performance, ease of listening, and desire to control the listening situation revealed a similar pattern of results as word recognition performance, making them poor candidates for providing an indication of behavioral listening effort. However, ratings of time perception were moderately correlated with behavioral listening effort. Finally, sustained listening for approximately 25 min increased self-reported fatigue, although changes in fatigue were comparable in low and moderately reverberant environments. In total, these data offer no evidence that a moderate level of reverberation increases listening effort or fatigue, but the data do support the reduction of background noise in classrooms.

A Hard Look at Thermal Reverberation and Optical/Ultraviolet Lags in NGC 5548

Abstract The ultraviolet (UV)/optical variations in many active galactic nuclei are very well correlated, showing delays that increase with increasing wavelength. It is thought that this is due to thermal reprocessing of the X-ray emission by the accretion disk. In this scenario, the variable X-ray flux from the corona illuminates the accretion disk where it is partially reflected, and partially absorbed and thermalized in the disk producing a UV/optical reverberation signal. This leads to time lags that increase with wavelength. However, although the shape of the observed time lags as a function of wavelength is consistent with the model predictions, their amplitude suggests the presence of a disk that is significantly hotter than expected. In this work, we estimate the response functions and the corresponding time lags assuming a standard Novikov–Thorne accretion disk illuminated by a point-like X-ray source. We take into account all relativistic effects in the light propagation from the X-ray source to the disk then to the observer. We also compute the disk reflection, accounting for its ionization profile. Our results show that thermal reverberation effects are stronger in sources with large X-ray source height and low accretion rate. We also found that the time lags increase with height and accretion rate. We apply our model to NGC 5548 and show that the observed lags in this source can be explained by the model for a source height of ∼60 r g and an accretion rate of a few percent of the Eddington limit for a maximally spinning black hole.

Effects of noise and reverberation on speech recognition with variants of a multichannel adaptive dynamic range compression scheme

Objective: Adaptive compression methods in hearing aids have been developed to maximise audibility while preserving temporal envelope modulations. Increasing the number of channels may improve listening comfort for loud sounds. However, the effects of this on speech recognition in different environmental conditions are unknown. This study evaluated the effects of different channel architectures and adaptive compression properties on speech recognition in noise and reverberation.Design: Sentences were mixed with steady or modulated noise at three signal-to-noise ratios (SNRs). These were processed with and without reverberation and amplified with four proprietary adaptive compression methods or linear amplification.Study sample: 36 listeners with mild to moderately-severe hearing loss.Results: Adaptive compression improved speech recognition over linear amplification to a small extent, with no significant differences among methods using 4 or 24 channels or a combination thereof. These effects remained across the different background noise and reverberation conditions.Conclusions: Increasing the number of channels does not negatively affect speech recognition in noise and reverberation when adaptive compression is used. If future research shows that increasing the number of channels improves listening comfort for loud sounds, these results indicate that adaptive compression methods with as many as 24 channels are viable options for hearing aids.

Receiver placement for speech enhancement using sound propagation optimization

A common problem in acoustic design is the placement of speakers or receivers for public address systems, telecommunications, and home smart speakers or digital personal assistants. We present a novel algorithm to automatically place a speaker or receiver in a room to improve the intelligibility of spoken phrases in a design. Our technique uses a sound propagation optimization formulation to maximize the Speech Transmission Index (STI) by computing an optimal location of the sound receiver. We use an efficient and accurate hybrid sound propagation technique on complex 3D models to compute the Room Impulse Responses (RIR) and evaluate their impact on the STI. The overall algorithm computes a globally optimal position of the receiver that reduces the effects of reverberation and noise over many source positions. We evaluate our algorithm on various indoor 3D models, all showing significant improvement in STI, based on accurate sound propagation.

Listening benefits in speech-in-speech recognition are altered under reverberant conditions.

In speech-in-speech recognition, listeners' performance improves when spatial and linguistic properties of background and target speech differ. However, it is unclear if these benefits interact or whether they persist under reverberant conditions typical of indoor listening. To address these issues, these benefits were tested together in the presence and absence of reverberation. Results demonstrate that, in the anechoic condition, both spatial and linguistic benefits are obtained but they do not constrain each other. Under reverberation, only the spatial benefit was obtained. This demonstrates the critical need to consider reverberation effects in order to fully characterize the challenges of speech-in-speech listening.

Tone language experience-dependent advantage in pitch representation in brainstem and auditory cortex is maintained under reverberation

Long-term language and music experience enhances neural representation of temporal attributes of pitch in the brainstem and auditory cortex in favorable listening conditions. Herein we examine whether brainstem and cortical pitch mechanisms—shaped by long-term language experience—maintain this advantage in the presence of reverberation-induced degradation in pitch representation. Brainstem frequency following responses (FFR) and cortical pitch responses (CPR) were recorded concurrently from Chinese and English-speaking natives, using a Mandarin word exhibiting a high rising pitch (/yi2/). Stimuli were presented diotically in quiet (Dry), and in the presence of Slight, Mild, and Moderate reverberation conditions. Regardless of language group, the amplitude of both brainstem FFR (F0) and cortical CPR (NaPb) responses decreased with increases in reverberation. Response amplitude for Chinese, however, was larger than English in all reverberant conditions. The Chinese group also exhibited a robust rightward asymmetry at temporal electrode sites (T8 > T7) across stimulus conditions. Regardless of language group, direct comparison of brainstem and cortical responses revealed similar magnitude of change in response amplitude with increasing reverberation. These findings suggest that experience-dependent brainstem and cortical pitch mechanisms provide an enhanced and stable neural representation of pitch-relevant information that is maintained even in the presence of reverberation. Relatively greater degradative effects of reverberation on brainstem (FFR) compared to cortical (NaPb) responses suggest relatively stronger top-down influences on CPRs.

The effect of reverberation on listening effort

The current study investigates whether long reverberation increases listening effort during speech recognition. Listening effort during word recognition in multi-talker babble noise was assessed with or without high levels of reverberation. A dual-task paradigm was adopted, in which the primary task was word recognition in noise at individually selected signal-to-noise ratio (SNR) that yielded an average performance level of 50% correct, and the secondary task was a visual-tracking task with individually adjusted difficulty level to yield an average performance level of 85% correct. In each 30-s trial, seven monosyllabic words were presented sequentially at a rate of four seconds per word. Young normal-hearing listeners were instructed to verbally repeat each word while performing the secondary task. In the reverberant condition, a cascade of all-pass filters was used to achieve a reverberation time of 1 s without altering the original spectrum of the speech. For the primary task in isolation, the reverberant condition required 10 dB or more in SNR to achieve the 50% target performance level. When the listeners performed the two tasks simultaneously, no consistent adverse effect of reverberation was found on the performance of the primary or secondary task compared to the no-reverberation condition.The current study investigates whether long reverberation increases listening effort during speech recognition. Listening effort during word recognition in multi-talker babble noise was assessed with or without high levels of reverberation. A dual-task paradigm was adopted, in which the primary task was word recognition in noise at individually selected signal-to-noise ratio (SNR) that yielded an average performance level of 50% correct, and the secondary task was a visual-tracking task with individually adjusted difficulty level to yield an average performance level of 85% correct. In each 30-s trial, seven monosyllabic words were presented sequentially at a rate of four seconds per word. Young normal-hearing listeners were instructed to verbally repeat each word while performing the secondary task. In the reverberant condition, a cascade of all-pass filters was used to achieve a reverberation time of 1 s without altering the original spectrum of the speech. For the primary task in isolation, the reverbe...

Speaker Tracking Based on Distributed Particle Filter and Iterative Covariance Intersection in Distributed Microphone Networks

Speaker tracking in distributed microphone networks is a challenging task due to the adverse effects of reverberation and noise. In this paper, a speaker tracking method based on distributed particle filter (DPF) and modified iterative covariance intersection (MICI) algorithm is proposed in distributed microphone networks. Specifically, the time difference of arrival (TDOA) of speech signals received by a pair of microphones at each node is first estimated using the generalized cross-correlation function. Next, multiple TDOAs are considered as the local measurement via a choice strategy and the multiple-hypothesis model is used as the local likelihood function of the DPF. Finally, the MICI algorithm is proposed to fuse local estimates to implement a global consistent speaker tracking where the local estimates at individual nodes are allowed to be unknown cross-correlations. The proposed method can successfully track the speaker in reverberant and noisy environments, and it is robust to the node faults and suitable to track speaker in networks with the unknown number of nodes. Simulation results demonstrate that the proposed method has better performance over the existing methods when SNR <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$&lt; $</tex-math></inline-formula> 10 dB. Real-world experiments reveal validity of the proposed method.