Sound Acquisition Research Articles

Input, Universals, and Transfer in Developing Rhotics: A Sketch in Bilingualism

Understanding the role of input in bilingual phonological acquisition is revealing for deciphering the workings of language acquisition processes. Input and usage distributional frequencies guide and differentiate speech sound acquisition patterns cross-linguistically. Such processes are operant in first- and second-language acquisition. There is an under-representation of investigations on how context-specific input in bilingualism influences the early acquisition of rhotics in child developmental speech longitudinally. This study addresses the gap by tracing a Greek/English bilingual girl’s rhotic development between ages 2;7 and 3;11, utilizing naturalistic data during daily interactions with an adult interlocutor. The study reports and schematically illustrates the child’s bilingual usage frequencies, informing language choice in her production variables, which demonstrate, quantitatively and qualitatively, the effects of context-specific input on rhotic accuracy levels and substitution patterns in both languages. Specifically, distributional frequencies in the input govern the child’s phonemic and phonetic tendencies in the languages. Findings are compared with previous reports in the literature and enhance language acquisition theory, revealing the pivotal role of input in the dynamic interplay with developmental universals, language-specific tendencies, transfer, and individual variation.

Noise annoyance and application of the Harmonica index at short time intervals

The Harmonica index (HRM) is aimed to quantify the perceived noisiness of environmental sounds on an hourly basis by a score on a linear scale from quiet to very noisy. The index is computed as the sum of the background noise (BGN) and the sound events (EVT) emerging from BGN and has been developed to facilitate communication with the public and to help local authorities in the decision-making process. In this paper, the HRM index has been applied to short time intervals, providing an increase in the time resolution of sound level acquisition from 1 s to 0.1 s. Six sound recordings were considered, taken in different urban contexts (i.e., parks, road traffic noise, construction sites), each lasting two minutes and divided into four sequential soundtracks of 30 s each. The tracks were played back randomly in laboratory listening tests to collect ratings of perceived annoyance given by participants after each soundtrack and, at the end of the four soundtrack sequences, the annoyance rating of the whole sound. The results show that the short-time application of the index is sensitive to the qualitative characteristics of the background and events, and needs improving before being used.

Bowel Sounds Detection Method Based on ResNet-BiLSTM and Attention Mechanism

Bowel sounds can reflect the movement and health status of the gastrointestinal tract. However, the traditional manual auscultation method has subjective deviation and is time-consuming and labor-intensive. In order to better assist doctors in diagnosing bowel sounds and improve the reliability and efficiency of bowel sound detection, this study proposed a deep neural network model that combines a residual neural network (ResNet), a bidirectional long short-term memory network (BiLSTM), and an attention mechanism. Firstly, a large number of labeled clinical data was collected using the self-developed multi-channel bowel sound acquisition system, and the multi-scale wavelet decomposition and reconstruction method was used to preprocess the bowel sounds. Then, log Mel spectrogram features were extracted and sent to the network for training. Finally, the performance and effectiveness of the model were evaluated and verified by 10-fold cross-validation and an ablation experiment. The experimental results showed that the precision, recall, and F 1 score of the model reached 83%, 76%, and 79%, respectively, and it could effectively detect bowel sound segments and locate their start and end times, performing better than previous algorithms. This algorithm can not only provide auxiliary information for doctors in clinical practice but also offer technical support for further analysis and research of bowel sounds.

Phonological development of children with cochlear implants

ABSTRACT Phonological processes are examples of normal simplified articulation seen in all children during the language and speech sound acquisition phase, and their frequency decreases and disappears with age. They are of concern when they are used beyond the expected time frames or when the simplification processes do not follow the typical substitutions. The aim of this study was to examine the phonological development and consonant acquisition of Turkish-speaking children with CI and compare the results with normative data. Comparisons were made according to the duration of CI use and also according to the age of CI. Therefore, 52 participants were analysed, first divided into 4 groups according to duration of CI use and then into 2 groups according to age of CI. Phonology skills were evaluated with the Bankson-Bernthal Phonology Test. In children with CI, 1373 consonant production errors were detected. There were 28 phonological processes corresponding to these errors. The most common phonological processes were Initial Consonant Deletion, Cluster Reduction, Final Consonant Deletion, Vowel Lengthening, Devoicing, Assimilation, Nasalization and Dentalization. The most errors occurred in fricative and voiced sounds, and the fewest errors occurred in bilabial consonants (/b,/p,/m/). This study demonstrated that CI performed before the age of three years and continued use of CI over an extended period of time have beneficial impacts on the development of phonological skills. This study is thought to enhance the existing research on the acquisition of consonants and phonological development in Turkish-speaking children with CI, a topic that currently lacks sufficient information.

The heart sound classification of congenital heart disease by using median EEMD-Hurst and threshold denoising method.

Heart sound signals are vital for the machine-assisted detection of congenital heart disease. However, the performance of diagnostic results is limited by noise during heart sound acquisition. A limitation of existing noise reduction schemes is that the pathological components of the signal are weak, which have the potential to be filtered out with the noise. In this research, a novel approach for classifying heart sounds based on median ensemble empirical mode decomposition (MEEMD), Hurst analysis, improved threshold denoising, and neural networks are presented. In decomposing the heart sound signal into several intrinsic mode functions (IMFs), mode mixing and mode splitting can be effectively suppressed by MEEMD. Hurst analysis is adopted for identifying the noisy content of IMFs. Then, the noise-dominated IMFs are denoised by an improved threshold function. Finally, the noise reduction signal is generated by reconstructing the processed components and the other components. A database of 5000 heart sounds from congenital heart disease and normal volunteers was constructed. The Mel spectral coefficients of the denoised signals were used as input vectors to the convolutional neural network for classification to verify the effectiveness of the preprocessing algorithm. An accuracy of 93.8%, a specificity of 93.1%, and a sensitivity of 94.6% were achieved for classifying the normal cases from abnormal one.

No clear benefit of transcutaneous auricular vagus nerve stimulation for non-native speech sound learning

IntroductionLearning to understand and speak a new language can be challenging and discouraging for adults. One potential tool for improving learning is transcutaneous auricular vagus nerve stimulation (taVNS), which modulates perception, memory, and attention systems. It has recently been reported that taVNS can improve English speakers' ability to perceive unfamiliar Mandarin tones. The current project explored the potential benefits of taVNS for language learning beyond tone perception.MethodsWe studied adults' ability to perceive and produce unfamiliar speech sounds as well as any potential change in language learning motivation from pre- to post-training. Forty-five native English speakers were divided into three groups and were trained to perceive German sounds: one group received stimulation during easier-to-learn sounds (vowels), one group received stimulation during harder-to-learn sounds (fricatives), and a control group received no stimulation.Results and discussionWe did not find evidence that taVNS improved perception or production of the German sounds, but there was evidence that it did improve some aspects of motivation. Specifically, the group that received taVNS during easier sounds showed a significant decrease in feelings of tension/pressure about language learning, while the other groups did not. Overall, the present study does not find that taVNS holds benefits for the acquisition of new speech sounds; however, the field is nascent, and so the potential applications of taVNS for language learning remain to be clarified.

BOSHLANG‘ICH SINFLARDA FONETIK MASHQLARNI O‘RGATISHDA INNOVATSION TEXNOLOGIYALARNING O‘RNI

This article discusses the importance of innovative technologies in strengthening students' phonetic knowledge, promoting correct speech acquisition and correct pronunciation of sounds, creating an interactive, interesting and effective educational environment, as well as increasing the effectiveness of the educational process with the help of such technologies. and manufacturing methods are widely covered.

How Dialects of Chinese Language Influence L1-Speakers Phonological and Phonetic Acquisition of English

There have been many studies concerning Chinese dialects influence on the learning of English sounds. However, it is widely believed that Chinese dialect speakers always face greater difficulties when learning English than Mandarin speakers, which is rebutted through this research, to some degree. The study tests the English repeating ability of speakers native to Wenzhou Wu, a dialect with a significant difference, and native to Tianjin Mandarin, which is very similar to Putonghua. The study compares the phonology of these two dialects and English and assumes that both of these dialects influence the acquisition of certain sounds of English. L1 speakers of these two dialects, who have not been exposed to English before, are asked to repeat the recording of English words, and through phonetic analysis of the material, we can find the difference in these candidates ability to acquire these sounds. The results show that the two branches of the Chinese language are found to both facilitate and obstacle native speakers SLA in different aspects.

Simulation of e-learning in vocal network teaching experience system based on intelligent Internet of things technology

With the rapid development of smart Internet of Things technology, education is also starting to use this technology to improve the learning experience. As an art subject, vocal music teaching has many limitations in the traditional face-to-face teaching methods, and e-learning provides new possibilities for vocal music network teaching. We analyze the problems and challenges existing in the traditional face-to-face mode of vocal music teaching, and then based on the intelligent Internet of Things technology, we design a vocal music network teaching experience system. The system combines sound acquisition equipment, intelligent audio processing algorithm, virtual classroom and other technologies to realize the simulation experience of online vocal music teaching. We have developed an intelligent audio processing algorithm for analyzing and processing students’ singing sounds. This algorithm can detect problems in tone, timbre, rhythm, and more, and provide real-time feedback and advice. In this way, students can understand the shortcomings of their own singing skills, and make timely adjustments and improvements. This study shows that e-learning based on intelligent Internet of Things technology has important application value in vocal music network teaching. By simulating the classroom environment and providing real-time feedback, students can obtain a better learning experience and improve their vocal skills.

Enhanced surrounding sound signal acquisition for arbitrary source location by the acoustic higher-order topological insulator

Enhanced surrounding sound signal acquisition for arbitrary source location by the acoustic higher-order topological insulator

A Preliminary Study of Model-Generated Speech

The goal of this study was to compare model-generated sounds with the process of sound acquisition in humans. The research utilized two dictionaries of the Chaoshan dialect spanning approximately one century. Identical Chinese characters were selected from each dictionary, and their contemporary pronunciations were documented. Subsequently, inconsistencies in pronunciation were manually rectified, following which three machine learning methods were employed to train the pronunciation of words from one dictionary to another. These methods comprised the attention-based sequence-to-sequence method, DirecTL+, and Sequitur. The accuracy of the model was evaluated using five-fold cross-validation, revealing a maximum accuracy of 68%. Additionally, the study investigated how the probability of a sound’s subsequent unit influences the accuracy of the machine learning methods. The attention-based sequence-to-sequence model is not solely influenced by the frequency of input but also by the probability of the subsequent unit.

Research on Fault Prediction Method of Elevator Door System Based on Transfer Learning.

The elevator door system plays a crucial role in ensuring elevator safety. Fault prediction is an invaluable tool for accident prevention. By analyzing the sound signals generated during operation, such as component wear and tear, the fault of the system can be accurately determined. This study proposes a GNN-LSTM-BDANN deep learning model to account for variations in elevator operating environments and sound signal acquisition methods. The proposed model utilizes the historical sound data from other elevators to predict the remaining useful life (RUL) of the target elevator door system. Firstly, the opening and closing sounds of other elevators is collected, followed by the extraction of relevant sound signal characteristics including A-weighted sound pressure level, loudness, sharpness, and roughness. These features are then transformed into graph data with geometric structure representation. Subsequently, the Graph Neural Networks (GNN) and long short-term memory networks (LSTM) are employed to extract deeper features from the data. Finally, transfer learning based on the improved Bhattacharyya Distance domain adversarial neural network (BDANN) is utilized to transfer knowledge learned from historical sound data of other elevators to predict RUL for the target elevator door system effectively. Experimental results demonstrate that the proposed method can successfully predict potential failure timeframes for different elevator door systems.

Arabic speech intelligibility: Perception of spoken Arabic by native and non-native speakers

Previous studies have shown that native language backgrounds of both talkers and listeners affect speech intelligibility. This study investigated the interlanguage speech intelligibility benefit (ISIB) that is also known as the advantage in understanding second language (L2) speech that non-native listeners have over native listeners when both groups listen to speakers with the same first language (L1). More specifically, it looked into the ISIB in relation to the Arabic language spoken by both native Arabic (NA) and English speakers. To this end, 15 NA and 15 native English (NE) subjects listened to Arabic produced by two groups of talkers (5 NA talkers and 5 NE talkers) and were asked to identify the words they heard. Results showed evidence for the interlanguage speech intelligibility for listeners (i.e. NE listeners were more accurate than NA listeners at identifying English-accented Arabic speech). However, no evidence for the ISIB for talkers was found. That is, NE listeners did not find English-accented speech more intelligible than NA speech. By examining L2 learners’ recognition of L2 consonant contrasts, the study contributes to the body of knowledge on L2 sound acquisition as well as the ISIB literature. It also provides some insight into the problem of adult L2 learners’ ability to learn novel L2 consonants.

An Acoustic System of Sound Acquisition and Image Generation for Frequent and Reliable Lung Function Assessment

An Acoustic System of Sound Acquisition and Image Generation for Frequent and Reliable Lung Function Assessment

Phonetic Interference Changes of Arabic to Indonesian in Arabic Learning

The integration of Indonesian with other languages causes Indonesian to easily absorb various elements of foreign languages, Arabic has a strong influence and integration with Indonesian. This has caused a lot of Arabic to be absorbed in Indonesian, which is commonly found in some Indonesian vocabulary listed in KBBI, officially recorded to be used in full form by the people of Indonesia. The purpose of this study is to describe the form and see the phonetic changes that occur in the absorption elements of Arabic Indonesian vocabulary listed in the officially recorded KBBI. The method used in research is library research, using a qualitative approach, namely research that attaches importance to collecting qualitative data. The result of the study is that the acquisition of sounds in this language can be studied scientifically, so how to produce these sounds can be explained in more detail phonetically or phonetically. The absorption element of Arabic has a positive effect on Arabic language learning. This effect occurs when the vocabulary inherited from Arabic is not changed entirely, changing the sound and use of the language's words.

Sound recognition method for white feather broilers based on spectrogram features and the fusion classification model

This paper presents a sound recognition method for white feather broilers using spectrogram features and a fusion classification model, with the goal of achieving accurate classification of white feather broilers sound signals and providing a reliable basis for monitoring their health. In the training part, after five steps of sound signal acquisition, pre-processing, feature extraction, feature optimization, and model training, a fusion classification model with strong reliability is constructed for practical application scenarios. In the testing part, the method is applied to a real farming scenario of white feather broilers, and the stability of the multi-classification models and the reliability of the fusion classification model are verified. The fusion classification model comprises Random Forest, K-nearest neighbor, and RBF-based SVM. Results from multiple tests showed that the highest classification accuracies achieved by the three multi-classification models were 100%, 86.67%, and 93.33%, respectively. The average prediction accuracy of the fusion classification model on multiple audio signals was 98.57%, the results effectively demonstrate the feasibility and practicality of the proposed method.

Research on Multi-Source Simultaneous Recognition Technology Based on Sagnac Fiber Optic Sound Sensing System

To solve the problem of multiple sound recognition in the application of Sagnac optical fiber acoustic sensing system, a multi-source synchronous recognition algorithm was proposed, which combined the VMD (variational modal decomposition) algorithm and MFCC (Mel-frequency cepstral coefficient algorithm) algorithm to pre-process the photoacoustic sensing signal, and uses BP neural network to recognize the photoacoustic sensing signal. The modal analysis and feature extraction theory of photoacoustic sensing signal based on the VMD and MFCC algorithms were presented. The signal recognition theory analysis and system recognition program design were completed based on the BP neural network. Signal acquisition of different sounds and verification experiments of the recognition system have been carried out in a laboratory environment based on the Sagnac fiber optic sound sensing system. The experimental results show that the proposed optical fiber acoustic sensing signal recognition algorithm has a simultaneous recognition rate better than 96.5% for six types of sounds, and the optical acoustic signal recognition takes less than 5.3 s, which has the capability of real-time sound detection and recognition, and provides the possibility of further application of the Sagnac-based optical fiber acoustic sensing system.

Orthographic influence in the distributional learning of non-native speech sounds

This study investigated the role of orthographic information in the acquisition of non-native speech sounds by monolingual English listeners. Two potentially important orthographic variables were explored: Orthographic compatibility (whether the orthographic information supports or contradicts the distributional information) and orthographic familiarity (whether the native and target languages share the same orthography). Ten groups of learners were trained on either a unimodal or bimodal distribution of two length continua. Out of the 10 groups, eight groups were also exposed to orthographic cues that varied in their compatibility with the distributional information (compatible vs. incompatible) and familiarity with the orthography of learners’ native language (Roman vs. Arabic). Following training, all participants performed an AX discrimination task to test their discrimination of the length contrast. The results revealed that, in general, the availability of either familiar or unfamiliar orthographic input which signaled the existence of a single length category significantly lowered learners’ discrimination of the length contrast regardless of the auditory distribution. Further, the exposure to orthographic input that supported a two-category length distinction enhanced the discrimination of the length contrast irrespective of the distribution. However, the most significant improvement occurred when both distributional information and familiar orthographic input were compatible. Overall, these findings indicate that orthographic input, regardless of its level of compatibility or familiarity, may influence the acquisition of non-native speech sounds.

Phonological development in first language Laki-speaking children aged 3 to 5 years: A pilot study

Purpose To date there are no studies of speech sound acquisition in Laki, a language spoken in western regions of Iran. Thus, we set out a pilot study to investigate the speech development of 56 first language Laki-speaking children (aged 3–5 years). Method Single words were elicited through a picture naming test specifically developed for this study. After recording and transcribing of speech samples, percentage of consonants correct (PCC), percentage of vowels correct (PVC), and proportion of whole word proximity (PWP) were documented in four age groups (36–41, 42–47, 48–53, and 54–59 months) and both genders. Children’s phonetic inventories and consonant and vowel accuracy were also described. Result All the sounds were considered as emerging by 53 months of age. For speech sound accuracy, all the speech sounds except /ɢ, z, ŋ, ʒ/ were mastered by 5 years. The effect of age on PCC values was significant. Also, age groups showed significant differences for PWP but were not significant for PVC. Boys and girls did not differ for PCC, PVC, and PWP values. Conclusion From a theoretical perspective, findings contribute to theories about phonological acquisition in general and will enable crosslinguistic comparisons. From an applied standpoint, language-specific characteristics are identified, which are much needed for clinical practice with Laki-speaking children.

Sound-Based Real-Time Scrap Falling State Monitoring in the Shearing Process of Wide Heavy Plate Mill

The scrap falling state in the shearing process of a Wide Heavy Plate Mill depends on manual monitoring and judgment. The steel plate can only move forward after the scrap falls, otherwise, the equipment will be damaged. An experienced operator can use the sound they hear to estimate the falling state. To automatically recognize sound events, a scheme of sound data acquisition processing and recognition for monitoring the scrap state of the shearing process is proposed in this paper. Firstly, a pickup is installed at the monitoring point of the crop shear to collect the sound. Afterward, the sound data is processed and finally fed into the model for recognition. Since many sound segments in the field are not related to key actions, an endpoint detection technique based on a short-term energy threshold and the variable window length strategy is applied in the data processing section to obtain the sound segments to be identified. The Log-Mel spectrogram feature of the sound segment is then extracted. After a data filling to ensure a uniform data shape, the feature map is fed into a lightweight deep convolution neural network called MobileNetV2 to quickly identify sound events. For the shearing process events, the model recognition accuracy can reach 95% of the F1 score in a realistic noise environment and we can identify the scrap falling 0.3s after the action starts. Finally, the model was applied to the UrbanSound8K dataset and achieved 95% recognition accuracy, validating the performance of the method.