Advancing Auditory Processing by Detecting Frequency-Following Responses Through a Specialized Machine Learning Model.

In this study, we explore the feasibility and performance of detecting scalp-recorded frequency-following responses (FFRs) with a specialized machine learning (ML) model. By leveraging the strengths of feature extraction of the source separation non-negative matrix factorization (SSNMF) algorithm and its adeptness in handling limited training data, we adapted the SSNMF algorithm into a specialized ML model with a hybrid architecture to enhance FFR detection amidst background noise. We recruited 40 adults with normal hearing and evoked their scalp recorded FFRs using the English vowel/i/with a rising pitch contour. The model was trained on FFR-present and FFR-absent conditions, and its performance was evaluated using sensitivity, specificity, efficiency, false-positive rate, and false-negative rate metrics. This study revealed that the specialized SSNMF model achieved heightened sensitivity, specificity, and efficiency in detecting FFRs as the number of recording sweeps increased. Sensitivity exceeded 80% at 500 sweeps and maintained over 89% from 1000 sweeps onwards. Similarly, specificity and efficiency also improved rapidly with increasing sweeps. The progressively enhanced sensitivity, specificity, and efficiency of this specialized ML model underscore its practicality and potential for broader applications. These findings have immediate implications for FFR research and clinical use, while paving the way for further advancements in the assessment of auditory processing.

Effects of Silent Intervals on the Extraction of Human Frequency-Following Responses Using Non-Negative Matrix Factorization.

Source-Separation Non-Negative Matrix Factorization (SSNMF) is a mathematical algorithm recently developed to extract scalp-recorded frequency-following responses (FFRs) from noise. Despite its initial success, the effects of silent intervals on algorithm performance remain undetermined. Our purpose in this study was to determine the effects of silent intervals on the extraction of FFRs, which are electrophysiological responses that are commonly used to evaluate auditory processing and neuroplasticity in the human brain. We used an English vowel /i/ with a rising frequency contour to evoke FFRs in 23 normal-hearing adults. The stimulus had a duration of 150 ms, while the silent interval between the onset of one stimulus and the offset of the next one was also 150 ms. We computed FFR Enhancement and Noise Residue to estimate algorithm performance, while silent intervals were either included (i.e., the WithSI condition) or excluded (i.e., the WithoutSI condition) in our analysis. The FFR Enhancements and Noise Residues obtained in the WithoutSI condition were significantly better (p < .05) than those obtained in the WithSI condition. On average, the exclusion of silent intervals produced a 11.78% increment in FFR Enhancement and a 20.69% decrement in Noise Residue. These results not only quantify the effects of silent intervals on the extraction of human FFRs, but also provide recommendations for designing and improving the SSNMF algorithm in future research.

Non-negative matrix factorization improves the efficiency of recording frequency-following responses in normal-hearing adults and neonates.

OBJECTIVE: One challenge in extracting the scalp-recorded frequency-following response (FFR) is related to its inherently small amplitude, which means that the response cannot be identified with confidence when only a relatively small number of recording sweeps are included in the averaging procedure. DESIGN: This study examined how the non-negative matrix factorisation (NMF) algorithm with a source separation constraint could be applied to improve the efficiency of FFR recordings. Conventional FFRs elicited by an English vowel/i/with a rising frequency contour were collected. Study sample: Fifteen normal-hearing adults and 15 normal-hearing neonates were recruited. RESULTS: The improvements of FFR recordings, defined as the correlation coefficient and root-mean-square differences across a sweep series of amplitude spectrograms before and after the application of the source separation NMF (SSNMF) algorithm, were characterised through an exponential curve fitting model. Statistical analysis of variance indicated that the SSNMF algorithm was able to enhance the FFRs recorded in both groups of participants. CONCLUSIONS: Such improvements enabled FFR extractions in a relatively small number of recording sweeps, and opened a new window to better understand how speech sounds are processed in the human brain.

Learning-Based Image Damage Area Detection for Old Photo Recovery.

Most methods for repairing damaged old photos are manual or semi-automatic. With these methods, the damaged region must first be manually marked so that it can be repaired later either by hand or by an algorithm. However, damage marking is a time-consuming and labor-intensive process. Although there are a few fully automatic repair methods, they are in the style of end-to-end repairing, which means they provide no control over damaged area detection, potentially destroying or being unable to completely preserve valuable historical photos to the full degree. Therefore, this paper proposes a deep learning-based architecture for automatically detecting damaged areas of old photos. We designed a damage detection model to automatically and correctly mark damaged areas in photos, and this damage can be subsequently repaired using any existing inpainting methods. Our experimental results show that our proposed damage detection model can detect complex damaged areas in old photos automatically and effectively. The damage marking time is substantially reduced to less than 0.01 s per photo to speed up old photo recovery processing.

Multigenerational inspections of environmental thermal perturbations promote metabolic trade-offs in developmental stages of tropical fish.

Global warming both reduces global temperature variance and increases the frequency of extreme weather events. In response to these ambient perturbations, animals may be subject to trans- or intra-generational phenotype modifications that help to maintain homeostasis and fitness. Here, we show how temperature-associated transgenerational plasticity in tilapia affects metabolic trade-offs during developmental stages under a global warming scenario. Tropical tilapia reared at a stable temperature of 27 °C for a decade were divided into two temperature-experience groups for four generations of breeding. Each generation of one group was exposed to a single 15 °C cold-shock experience during its lifetime (cold-experienced CE group), and the other group was kept stably at 27 °C throughout their lifetimes (cold-naïve CN group). The offspring at early life stages from the CE and CN tilapia were then assessed by metabolomics-based profiling, and the results implied that parental cold-experience might affect energy provision during reproduction. Furthermore, at early life stages, progeny may be endowed with metabolic traits that help the animals cope with ambient temperature perturbations. This study also applied the feature rescaling and Uniform Manifold Approximation and Projection (UMAP) to visualize metabolic dynamics, and the result could effectively decompose the complex omic-based datasets to represent the energy trade-off variability. For example, the carbohydrate to free amino acid conversion and enhanced compensatory features appeared to be hypothermic-responsive traits. These multigenerational metabolic effects suggest that the tropical ectothermic tilapia may exhibit transgenerational phenotype plasticity, which could optimize energy allocation under ambient temperature challenges. Knowledge about such metabolism-related transgenerational plasticity effects in ectothermic aquatic species may allow us to better predict how adaptive mechanisms will affect fish populations in a climate with narrow temperature variation and frequent extreme weather events.

Optical properties evaluation of rapid sintered translucent zirconia with two dental colorimeters.

BACKGROUND/PURPOSE: The efficient rapid sintering technique has employed to dental zirconia ceramics for shortening the fabrication time of zirconia restorations. The purpose was to compare the optical properties of two generations of rapid sintered translucent zirconia using two dental colorimeters. MATERIALS AND METHODS: Two generations of translucent zirconia ceramics, 3 mol% yttria-tetragonal zirconia polycrystal (3Y-TZP): Copran Zr-i Ultra-T (UT) and Cercon HT (HT), and 5 mol% yttria-tetragonal zirconia polycrystal (5Y-TZP): Cercon xt (XT), of different thicknesses (0.5, 0.8, and 1.2 mm; n = 5) underwent rapid sintering (RS) or conventional sintering (CS). The CIELAB values were measured on the white and black backgrounds, respectively, by digital colorimeters, shadepilot, DeguDent (DD) and Easyshade V, Vita (Vita). Translucency parameter (TP), color difference (ΔE), surface morphology, and surface roughness were evaluated. RESULTS: RS resulted in reduced lightness, except in the XT group. The chromaticity increased slightly after RS. Translucency decreased with increasing material thickness. ΔE values differed between both sintering processes but were clinically acceptable (ΔE < 5). Grain size of XT decreased after RS. RS did not affect the surface roughness. CONCLUSION: RS is a feasible method for shortening the manufacturing time of zirconia restorations. A significant difference in TP value was only in the XT group between both sintering methods as measured on DD. Color differences in rapid sintered translucent zirconia materials are imperceptible and acceptable. The specimen thickness affected more in the TP values of Vita than DD. DD has higher sensitivity to translucency and color compared with Vita.

Sensing ecosystem dynamics via audio source separation: A case study of marine soundscapes off northeastern Taiwan.

Remote acquisition of information on ecosystem dynamics is essential for conservation management, especially for the deep ocean. Soundscape offers unique opportunities to study the behavior of soniferous marine animals and their interactions with various noise-generating activities at a fine temporal resolution. However, the retrieval of soundscape information remains challenging owing to limitations in audio analysis techniques that are effective in the face of highly variable interfering sources. This study investigated the application of a seafloor acoustic observatory as a long-term platform for observing marine ecosystem dynamics through audio source separation. A source separation model based on the assumption of source-specific periodicity was used to factorize time-frequency representations of long-duration underwater recordings. With minimal supervision, the model learned to discriminate source-specific spectral features and prove to be effective in the separation of sounds made by cetaceans, soniferous fish, and abiotic sources from the deep-water soundscapes off northeastern Taiwan. Results revealed phenological differences among the sound sources and identified diurnal and seasonal interactions between cetaceans and soniferous fish. The application of clustering to source separation results generated a database featuring the diversity of soundscapes and revealed a compositional shift in clusters of cetacean vocalizations and fish choruses during diurnal and seasonal cycles. The source separation model enables the transformation of single-channel audio into multiple channels encoding the dynamics of biophony, geophony, and anthropophony, which are essential for characterizing the community of soniferous animals, quality of acoustic habitat, and their interactions. Our results demonstrated the application of source separation could facilitate acoustic diversity assessment, which is a crucial task in soundscape-based ecosystem monitoring. Future implementation of soundscape information retrieval in long-term marine observation networks will lead to the use of soundscapes as a new tool for conservation management in an increasingly noisy ocean.

Listening forward: approaching marine biodiversity assessments using acoustic methods.

Ecosystems and the communities they support are changing at alarmingly rapid rates. Tracking species diversity is vital to managing these stressed habitats. Yet, quantifying and monitoring biodiversity is often challenging, especially in ocean habitats. Given that many animals make sounds, these cues travel efficiently under water, and emerging technologies are increasingly cost-effective, passive acoustics (a long-standing ocean observation method) is now a potential means of quantifying and monitoring marine biodiversity. Properly applying acoustics for biodiversity assessments is vital. Our goal here is to provide a timely consideration of emerging methods using passive acoustics to measure marine biodiversity. We provide a summary of the brief history of using passive acoustics to assess marine biodiversity and community structure, a critical assessment of the challenges faced, and outline recommended practices and considerations for acoustic biodiversity measurements. We focused on temperate and tropical seas, where much of the acoustic biodiversity work has been conducted. Overall, we suggest a cautious approach to applying current acoustic indices to assess marine biodiversity. Key needs are preliminary data and sampling sufficiently to capture the patterns and variability of a habitat. Yet with new analytical tools including source separation and supervised machine learning, there is substantial promise in marine acoustic diversity assessment methods.

Blind Monaural Source Separation on Heart and Lung Sounds Based on Periodic-Coded Deep Autoencoder.

Auscultation is the most efficient way to diagnose cardiovascular and respiratory diseases. To reach accurate diagnoses, a device must be able to recognize heart and lung sounds from various clinical situations. However, the recorded chest sounds are mixed by heart and lung sounds. Thus, effectively separating these two sounds is critical in the pre-processing stage. Recent advances in machine learning have progressed on monaural source separations, but most of the well-known techniques require paired mixed sounds and individual pure sounds for model training. As the preparation of pure heart and lung sounds is difficult, special designs must be considered to derive effective heart and lung sound separation techniques. In this study, we proposed a novel periodicity-coded deep auto-encoder (PC-DAE) approach to separate mixed heart-lung sounds in an unsupervised manner via the assumption of different periodicities between heart rate and respiration rate. The PC-DAE benefits from deep-learning-based models by extracting representative features and considers the periodicity of heart and lung sounds to carry out the separation. We evaluated PC-DAE on two datasets. The first one includes sounds from the Student Auscultation Manikin (SAM), and the second is prepared by recording chest sounds in real-world conditions. Experimental results indicate that PC-DAE outperforms several well-known separation works in terms of standardized evaluation metrics. Moreover, waveforms and spectrograms demonstrate the effectiveness of PC-DAE compared to existing approaches. It is also confirmed that by using the proposed PC-DAE as a pre-processing stage, the heart sound recognition accuracies can be notably boosted. The experimental results confirmed the effectiveness of PC-DAE and its potential to be used in clinical applications.

Using Soundscapes to Assess Deep-Sea Benthic Ecosystems.

Targets of deep-sea mining commonly coincide with biodiversity hotspots, such as hydrothermal vents. The resilience of these ecosystems relies on larval dispersal, which may be directed by habitat-specific soundscapes. We urge for a global effort to implement soundscape as a conservation tool to assess anthropogenic disruption to deep-sea benthic ecosystems.

Comparison of passive acoustic soniferous fish monitoring with supervised and unsupervised approaches.

Passive acoustics has been used to investigate behavior and relative abundances of soniferous fish. However, because of noise interferences, it remains challenging to accurately analyze acoustic activities of soniferous fish. This study proposes a multi-method approach, which combines rule-based detector, periodicity-coded non-negative matrix factorization, and Gaussian mixture models. Although the three methods performed well when used to detect croaker choruses in quiet conditions, inconsistent results are observed in noisy conditions. A consistency matrix can provide insights regarding the bias of acoustic monitoring results. The results suggest that the proposed approach can reasonably improve passive acoustic monitoring of soniferous fish.

The Effects of Continuous Acoustic Stress on ROS Levels and Antioxidant-related Gene Expression in the Black Porgy (Acanthopagrus schlegelii).

Hao-Yi Chang, Tzu-Hao Lin, Kazuhiko Anraku, and Yi Ta Shao (2018) Short-term exposure to strong underwater noise is known to seriously impact fish. However, the chronic physiological effects of continuous exposure to weak noise, i.e. the operation noise from offshore wind farms (OWF), remain unclear. Since more and more OWF will be built in the near future, their operation noise is an emerging ecological issue. To investigate the long-term physiological effects of such underwater noise on fish, black porgies (Acanthopagrus schlegelii) were exposed to two types of simulated wind farm noise-quiet (QC: 109 dB re 1 µPa / 125.4 Hz; approx. 100 m away from the wind turbine) and noisy (NC: 138 dB re 1 µPa / 125.4 Hz; near the turbine)-for up to 2 weeks. Measurement of auditory-evoked potentials showed that black porgies can hear sound stimuli under both NC and QC scenarios. Although no significant difference was found in plasma cortisol levels, the fish under NC conditions exhibited higher plasma reactive oxygen species (ROS) levels than the control group at week 2. Moreover, alterations were found in mRNA levels of hepatic antioxidant-related genes (sod1, cat and gpx), with cat downregulated and gpx upregulated after one week of QC exposure. Our results suggest that the black porgy may adapt to QC levels of noise by modulating the antioxidant system to keep ROS levels low. However, such antioxidant response was not observed under NC conditions; instead, ROS accumulated to measurably higher levels. This study suggests that continuous OWF operation noise represents a potential stressor to fish. Furthermore, this is the first study to demonstrate that chronic exposure to noise could induce ROS accumulation in fish plasma.

The effects of continuously acoustical stress on cortisol in milkfish (Chanos chanos).

Strong underwater acoustic noise has been known that may cause hearing loss and actual stress in teleost. However, the long-term physiological effects of relatively quiet but continuously noise on fish were less understood. In present study, milkfish, Chanos chanos, were exposed to the simulated-wind farm noise either quiet (109dB re 1µPa/125.4Hz; approx. 10-100m distant from the wind farm) or noisy (138dB re 1µPa/125.4Hz; nearby the wind farm) conditions for 24h, 3days and 1week. Comparing to the control group (80dB re 1µPa/125.4Hz), the fish exposed to noisy conditions had higher plasma cortisol levels in the first 24h. However, the cortisol levels of 24h spot returned to the resting levels quickly. The fish exposed under noisy condition had significantly higher head kidney star (steroidogenic acute regulatory) and hsd11b2 (11-ß-hydroxysteroid dehydrogenase 2) mRNA levels at the following treatment time points. In addition, noise exposure did not change hypothalamus crh (Corticotropin-releasing hormone) mRNA levels in this experiment. The results implied that the weak but continuously noise was a potential stressor to fish, but the impacts may be various depending on the sound levels and exposure time. Furthermore, this study showed that the continuous noise may up-regulate the genes that are related to cortisol synthesis and possibly make the fish more sensitive to ambient stressors, which may influence the energy allocation appearance in long-term exposures.

Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings.

Investigating the dynamics of biodiversity via passive acoustic monitoring is a challenging task, owing to the difficulty of identifying different animal vocalizations. Several indices have been proposed to measure acoustic complexity and to predict biodiversity. Although these indices perform well under low-noise conditions, they may be biased when environmental and anthropogenic noises are involved. In this paper, we propose a periodicity coded non-negative matrix factorization (PC-NMF) for separating different sound sources from a spectrogram of long-term recordings. The PC-NMF first decomposes a spectrogram into two matrices: spectral basis matrix and encoding matrix. Next, on the basis of the periodicity of the encoding information, the spectral bases belonging to the same source are grouped together. Finally, distinct sources are reconstructed on the basis of the cluster of the basis matrix and the corresponding encoding information, and the noise components are then removed to facilitate more accurate monitoring of biological sounds. Our results show that the PC-NMF precisely enhances biological choruses, effectively suppressing environmental and anthropogenic noises in marine and terrestrial recordings without a need for training data. The results may improve behaviour assessment of calling animals and facilitate the investigation of the interactions between different sound sources within an ecosystem.

Automatic classification of delphinids based on the representative frequencies of whistles.

Classification of odontocete species remains a challenging task for passive acoustic monitoring. Classifiers that have been developed use spectral features extracted from echolocation clicks and whistle contours. Most of these contour-based classifiers require complete contours to reduce measurement errors. Therefore, overlapping contours and partially detected contours in an automatic detection algorithm may increase the bias for contour-based classifiers. In this study, classification was conducted on each recording section without extracting individual contours. The local-max detector was used to extract representative frequencies of delphinid whistles and each section was divided into multiple non-overlapping fragments. Three acoustical parameters were measured from the distribution of representative frequencies in each fragment. By using the statistical features of the acoustical parameters and the percentage of overlapping whistles, correct classification rate of 70.3% was reached for the recordings of seven species (Tursiops truncatus, Delphinus delphis, Delphinus capensis, Peponocephala electra, Grampus griseus, Stenella longirostris longirostris, and Stenella attenuata) archived in MobySound.org. In addition, correct classification rate was not dramatically reduced in various simulated noise conditions. This algorithm can be employed in acoustic observatories to classify different delphinid species and facilitate future studies on the community ecology of odontocetes.

Dynamics of soundscape in a shallow water marine environment: a study of the habitat of the Indo-Pacific humpback dolphin.

The underwater acoustic field is an important ecological element for many aquatic animals. This research examines the soundscape of a critically endangered Indo-Pacific humpback dolphin population in the shallow water environment off the west coast of Taiwan. Underwater acoustic recordings were conducted between late spring and late fall in 2012 at Yunlin (YL), which is close to a shipping lane, and Waisanding (WS), which is relatively pristine. Site-specific analyses were performed on the dynamics of the temporal and spectral acoustic characteristics for both locations. The results highlight the dynamics of the soundscape in two major octave bands: 150-300 Hz and 1.2-2.4 kHz. The acoustic energy in the former frequency band is mainly associated with passing container vessels near YL, while the latter frequency band is from sonic fish chorus at nighttime in both recording sites. In addition, large variation of low frequency acoustic energy throughout the study period was noticed at WS, where the water depths ranged between 1.5 and 4.5 m depending on tidal cycle. This phenomenon suggests that besides certain sound sources in the environment, the coastal soundscape may also be influenced by its local bathymetry and the dynamics of the physical environment.

Passive acoustic monitoring of the temporal variability of odontocete tonal sounds from a long-term marine observatory.

The developments of marine observatories and automatic sound detection algorithms have facilitated the long-term monitoring of multiple species of odontocetes. Although classification remains difficult, information on tonal sound in odontocetes (i.e., toothed whales, including dolphins and porpoises) can provide insights into the species composition and group behavior of these species. However, the approach to measure whistle contour parameters for detecting the variability of odontocete vocal behavior may be biased when the signal-to-noise ratio is low. Thus, methods for analyzing the whistle usage of an entire group are necessary. In this study, a local-max detector was used to detect burst pulses and representative frequencies of whistles within 4.5-48 kHz. Whistle contours were extracted and classified using an unsupervised method. Whistle characteristics and usage pattern were quantified based on the distribution of representative frequencies and the composition of whistle repertoires. Based on the one year recordings collected from the Marine Cable Hosted Observatory off northeastern Taiwan, odontocete burst pulses and whistles were primarily detected during the nighttime, especially after sunset. Whistle usage during the nighttime was more complex, and whistles with higher frequency were mainly detected during summer and fall. According to the multivariate analysis, the diurnal variation of whistle usage was primarily related to the change of mode frequency, diversity of representative frequency, and sequence complexity. The seasonal variation of whistle usage involved the previous three parameters, in addition to the diversity of whistle clusters. Our results indicated that the species and behavioral composition of the local odontocete community may vary among seasonal and diurnal cycles. The current monitoring platform facilitates the evaluation of whistle usage based on group behavior and provides feature vectors for species and behavioral classification in future studies.

An automatic detection algorithm for extracting the representative frequency of cetacean tonal sounds.

Most studies on tonal sounds extract contour parameters from fundamental frequencies. The presence of harmonics and the frequency distribution of multiple tonal sounds have not been well researched. To investigate the occurrence and frequency modulation of cetacean tonal sounds, the procedure of detecting the instantaneous frequency bandwidth of tonal spectral peaks was integrated within the local-max detector to extract adopted frequencies. The adopted frequencies, considered the representative frequencies of tonal sounds, are used to find the presence of harmonics and overlapping tonal sounds. The utility and detection performance are demonstrated on acoustic recordings of five species from two databases. The recordings of humpback dolphins showed a 75% detection rate with a 5% false detection rate, and recordings from the MobySound archive showed an 85% detection rate with a 5% false detection rate. These detections were achieved in signal-to-noise ratios of -12 to 21 dB. The parameters that measured the distribution of adopted frequency, as well as the prominence of harmonics and overlaps, indicate that the modulation of tonal sounds varied among different species and behaviors. This algorithm can be applied to studies on cetacean communication signals and long-term passive acoustic monitoring.