Speech Impairment Research Articles

Ensemble-based feature engineering mechanism to decode imagined speech from brain signals

Speech impairments, resulting from brain injuries, mental disorders, or vocal abuse, substantially affect an individual’s quality of life and can lead to social isolation. Brain–Computer Interfaces (BCIs), particularly those based on EEG, offer a promising support mechanism by harnessing brain signals. Owing to their clinical efficacy, cost-effective EEG devices, and expanding applications in the medical and social spheres, their usage has surged. This study introduces an ensemble-based feature engineering mechanism to pinpoint the optimal brain rhythm, channel subset, and feature set for accurately predicting imagined words from EEG signals via machine learning models. Leveraging the 2020 International BCI competition dataset, we employed bandpass filtering, channel wrapping, and ranking methods were applied to discern suitable brain rhythms and features associated with imagined speech. Subsequent application of kernel-based principal component analysis enabled us to compress the feature space dimensionality. We then trained various machine learning models, among which the kNN model excelled, achieving an average accuracy of 73% in a 10-fold cross-validation scheme ,surpassing 18% higher than the existing literature. The Gamma rhythm was identified as the most predictive of imagined speech from EEG brain signals. These advancements herald a new era of more precise and effective BCIs, poised to significantly improve the lives of those with speech impairments.

A Comprehensive Review on Hypoglossal Nerve Palsy Presenting with Cervical Pain

Hypoglossal nerve palsy HNP is an uncommon neurological condition that can manifest with symptoms such as tongue deviation swallowing difficulties and speech impairments. While the classic presentation of HNP involves deficits in tongue movement and function it is essential to recognize that cervical pain can also be an associated symptom. This manuscript comprehensively reviews the literature examining the relationship between HNP and cervical pain. A thorough search of Pubmed and Google Scholar was conducted to identify relevant articles published between 2012 and 2023. Four case studies were selected for analysis illustrating various etiologies of HNP in the context of cervical pain. These cases underscore the importance of a thorough neurological assessment in patients presenting with neck pain as it may lead to the timely diagnosis and management of HNP. Clinicians should maintain a high index of suspicion for HNP in individuals complaining of cervical pain especially when accompanied by other neurological symptoms. Further research is warranted to elucidate the underlying mechanisms and optimal treatment strategies for HNP presenting with cervical pain.

Gesture-to-Text: A Real-Time Indian Sign Language Translator with Pose Estimation and LSTMs

In recent years, there have been notable advancements in technology, deep learning, and pose detection. One significant application of these advancements pertains to the real-time detection of sign language from video sources. The motivation behind this research stems from the pressing societal need to enhance the quality of life for individuals with speech impairments. Given the current prominence of online meetings, exacerbated by the COVID-19 pandemic, there is a growing need for systems that can provide individuals with speech impairments greater independence in communication, eliminating the requirement for a human translator. This research proposal advocates for a solution that leverages PoseNet algorithms for the extraction of key pose points, which are subsequently employed within LSTM models for the predictive modeling of sign language gestures. This research paper aims to make several notable contributions to the field of assistive technology and human-computer interaction. The achieved accuracy stands at an impressive 98%, underscoring the robustness and precision of our proposed system.

A novel communication system based on sign language recognition and voice conversion for differently abled person

Sign language is a form of communication that helps deaf and mute people interact with those who can hear. In the country, around 2.78% of people are unable to speak, i.e., are mute or deaf. Their primary means of communication is through hand motions and gestures. The paper proposes a new technique called the "artificial speaking mouth" for individuals with speech impairments. Humans connect with each other through thoughts and ideas, but some people lack the ability to speak. For them, sign language is the only means of communication. Nowadays, technology has reduced this communication gap with systems that translate sign language into speech. Sign Language Recognition (SLR) and gesture-based control are two major applications used for hand gesture recognition technologies. On the other hand, the controller converts sign language into text and speech, using text-to-speech conversion and analog-to-digital conversion.

Maternal Uniparental Isodisomy of Chromosome 2 Leading to Homozygous Variants in SPR and ZNF142 : A Case Report and Review of the UPD2 Literature.

We report a 4-year-old girl with neurodevelopmental abnormalities who has maternal uniparental isodisomy of chromosome 2 leading to homozygosity for a likely pathogenic variant in SPR , and a variant of uncertain significance in ZNF142 . Biallelic pathogenic variants in SPR lead to sepiapterin reductase deficiency (SRD), a dopa-responsive dystonia. Pathogenic variants in ZNF142 are associated with an autosomal recessive neurodevelopmental disorder characterized by impaired speech and hyperkinetic movements, which has significant clinical overlap with SRD. Our patient showed dramatic improvement in motor skills after treatment with levodopa. We also reviewed 67 published reports of uniparental disomy of chromosome 2 (UPD2) associated with various clinical outcomes. These include autosomal recessive disorders associated with loci on chromosome 2, infants with UPD2 whose gestations were associated with confined placental mosaicism for trisomy 2 leading to intrauterine growth restriction with good postnatal catchup growth, and normal phenotypes in children and adults with an incidental finding of either maternal or paternal UPD2. These latter reports provide support for the conclusion that genes located on chromosome 2 are not subject to imprinting. We also explore the mechanisms giving rise to UPD2.

Improving Dysarthric Speech Segmentation With Emulated and Synthetic Augmentation.

Acoustic features extracted from speech can help with the diagnosis of neurological diseases and monitoring of symptoms over time. Temporal segmentation of audio signals into individual words is an important pre-processing step needed prior to extracting acoustic features. Machine learning techniques could be used to automate speech segmentation via automatic speech recognition (ASR) and sequence to sequence alignment. While state-of-the-art ASR models achieve good performance on healthy speech, their performance significantly drops when evaluated on dysarthric speech. Fine-tuning ASR models on impaired speech can improve performance in dysarthric individuals, but it requires representative clinical data, which is difficult to collect and may raise privacy concerns. This study explores the feasibility of using two augmentation methods to increase ASR performance on dysarthric speech: 1) healthy individuals varying their speaking rate and loudness (as is often used in assessments of pathological speech); 2) synthetic speech with variations in speaking rate and accent (to ensure more diverse vocal representations and fairness). Experimental evaluations showed that fine-tuning a pre-trained ASR model with data from these two sources outperformed a model fine-tuned only on real clinical data and matched the performance of a model fine-tuned on the combination of real clinical data and synthetic speech. When evaluated on held-out acoustic data from 24 individuals with various neurological diseases, the best performing model achieved an average word error rate of 5.7% and a mean correct count accuracy of 94.4%. In segmenting the data into individual words, a mean intersection-over-union of 89.2% was obtained against manual parsing (ground truth). It can be concluded that emulated and synthetic augmentations can significantly reduce the need for real clinical data of dysarthric speech when fine-tuning ASR models and, in turn, for speech segmentation.

Regional and cellular organization of the autism-associated protein UBE3A/E6AP and its antisense transcript in the brain of the developing rhesus monkey.

Angelman syndrome (AS) is a neurogenetic disorder caused by mutations or deletions in the maternally-inherited UBE3A allele, leading to a loss of UBE3A protein expression in neurons. The paternally-inherited UBE3A allele is epigenetically silenced in neurons during development by a noncoding transcript (UBE3A-ATS). The absence of neuronal UBE3A results in severe neurological symptoms, including speech and language impairments, intellectual disability, and seizures. While no cure exists, therapies aiming to restore UBE3A function-either by gene addition or by targeting UBE3A-ATS-are under development. Progress in developing these treatments relies heavily on inferences drawn from mouse studies about the function of UBE3A in the human brain. To aid translational efforts and to gain an understanding of UBE3A and UBE3A-ATS biology with greater relevance to human neurodevelopmental contexts, we investigated UBE3A and UBE3A-ATS expression in the developing brain of the rhesus macaque, a species that exhibits complex social behaviors, resembling aspects of human behavior to a greater degree than mice. Combining immunohistochemistry and in situ hybridization, we mapped UBE3A and UBE3A-ATS regional and cellular expression in normal prenatal, neonatal, and adolescent rhesus macaque brains. We show that key hallmarks of UBE3A biology, well-known in rodents, are also present in macaques, and suggest paternal UBE3A silencing in neurons-but not glial cells-in the macaque brain, with onset between gestational day 48 and 100. These findings support proposals that early-life, perhaps even prenatal, intervention is optimal for overcoming the maternal allele loss of UBE3A linked to AS.

But was it Trustworthy? Methodological Experiences From a Study of a Hard-to-Reach Group of Students in Need of a Flexible Research Approach

Pedagogical research on experiences of learning among students with severe speech and physical impairment (SSPI) is sparse. This may be due to a lack of research-on-research methodology literature about students with SSPI, as they are difficult to find and there are barriers to their participation in mainstream research. Hence, method development is especially important regarding these students, who cannot participate when traditional inquiry methods are used. This article’s objective is therefore to advance method development by means of a retrospective investigation. The empirical findings consist of documented experiences from a previous study of students with SSPI (henceforth, “literacy study”). A computer-assisted email dialogue technique was developed in the literacy study’s pilot study and eventually used in the main study, to investigate the students’ experiences of their literacy development. The aim of this study is to retrospectively and critically examine the scientific trustworthiness of a methodological research approach based on an email dialogue technique used exploratively in the literacy study, to investigate the literacy development among the students grounded in their own experiences, and to contribute methodological experiences gained from that study regarding the relationship between the use of verification strategies and checking techniques. The computer-assisted email dialogue approach was necessary because the few participants were spread over great geographical distances. The approach was developed as an explorative and flexible inclusive research design and was used within the tradition of participatory research. The students in both the pilot and main studies (8–16 years of age) were treated as collaborators rather than research subjects. Both the verification strategies and techniques regarding trustworthiness criteria were found to be important for trustworthiness. The main conclusion, based on our experiences in this retrospective investigation, is that it is necessary to continuously and thoroughly focus on trustworthiness issues throughout the research process to obtain trustworthy findings.

Sign language recognition with hand gestures using deep learning

There are several obstacles when communicating with individuals who are deaf or hard of hearing, but sign language has become an essential tool. It is an excellent tool that helps individuals with speech and hearing impairments convey their ideas and feelings. This encourages less complicated integration with the outside environment. However because sign language has its own set of difficulties, its simple construction is insufficient. It might be difficult to interpret gestures for people who are not familiar with sign language or who speak a different sign language. Thankfully, new technological developments have introduced several methods for automating the recognition of sign movements, providing encouraging alternatives. This invention has the potential to close the long- standing communication gap considerably. This work presents the usage of an exclusive dataset to identify hand motions. The research project uses a webcam to allow users to take pictures of their hand gestures. The system's goal is to anticipate and show the name that corresponds to the image that was taken. Convolutional Neural Networks (CNNs) are used for image training and classification, with computer vision aiding in the image collection and capture process.

Psychological and pedagogical approaches prevention and correction of social health deviations preschoolers with disabilities in the preschool education system

The article reveals approaches to the prevention and correction of deviations in the social health of preschool children with severe speech impairments in a preschool educational organization

Parkinson’s disease Detection and Classification: Leveraging Voice Features and Ensemble Methods with Feature Selection and ERT Classifier

Parkinson’s disease, a debilitating neurological disorder affecting mobility, stands as one of the most prevalent and life-altering conditions within the realm of neurological disorders. Tragically, it currently lacks a definitive cure, significantly impacting life expectancy and resulting in substantial disabilities. Recognizing and diagnosing the condition early is paramount to mitigating its effects. Notably, more than 90% of individuals afflicted by Parkinson’s experience speech impairments. This underscores the significance of speech features in the diagnostic process. To streamline and improve the accuracy of Parkinson’s diagnosis, this study employs an automated diagnostic process. It leverages ensemble methods, integrating feature selection techniques, and implements the Extremely Randomized Trees (ERT) classifier based on voice characteristics. Through rigorous experimentation, the effectiveness of the ERT classifier is assessed using various feature selection methods. Notably, when combined with embedded LASSO, the ERT classifier achieves an impressive accuracy of 87%. This substantial improvement in diagnostic accuracy has far-reaching implications for early detection and management of Parkinson’s disease. By providing clinicians and healthcare professionals with a reliable, non-invasive, and cost-effective screening tool, this approach promises to significantly enhance the quality of life for patients battling this debilitating condition.

Estimating Speech Impairment Profiles of Children with Cerebral Palsy Using a Novel Assessment Protocol Mapped with Updated Reviews

<b>Purpose: </b>Cerebral palsy (CP), being a neurological condition, is characterized by abnormalities in either the muscle tone, coordination, and/or motor functions caused by damage to the developing brain. Dysarthria commonly exists as an independent entity in approximately half of the patients with CP, or sometimes with a combination of both impairments. Due to the high variability (type and motor distribution) in the severity of the impairment in CP, a comprehensive speech impairment profile is warranted for deriving a highly customized interventional plan for them. <b>Objectives:</b> Therefore, the current study aims to develop one such assessment protocol and utilize the same to estimate the speech impairments in children with CP. The objectives of the study were to develop a speech assessment protocol, to administer the same on the patients with CP, and to estimate their speech impairments. <b>Method:</b> The study followed a cross-sectional design with a non-random convenience sampling method. A total of 51 patients between 3 and 12 years of age diagnosed with CP (any type, severity, motor tone, or motor distribution) were included in the study. The study was conducted in two phases. Phase 1 included the development of the speech assessment protocol, while phase 2 included the administration and profiling of the retrieved data. Descriptive statistics were used to profile the data based on the frequency and percentage of occurrences. <b>Results:</b> The results have been organized based on the general and oral profile, and subsystems of speech (respiration, phonation, resonance, prosody, articulation, and overall intelligibility) of patients with spastic, flaccid, and ataxic CP. <b>Conclusion: </b>The developed protocol is comprised of multiple crucial domains that requires to be assessed during a formal speech assessment. The protocol helps tap upon the relevant family, natal, and other medical histories which becomes crucial during the counselling process.

Evaluation of the results of tongue reconstruction using local flaps following partial glossectomy.

Tongue reconstruction results following partial glossectomy using primary closure and local tissue rearrangement were evaluated in this study. 7 patients diagnosed with tongue carcinoma were included. Tongue defects were reconstructed using local transposition, advancement and rotation of the remaining tongue tissue and closure of the defect. The patients were evaluated 6 months and 1 year following the surgery. None of the patients had permanent speech impairments or major swallowing problems following the surgery despite 33% to 50% reduction in tongue length. Unnecessary utilization of microvascular flaps for partial tongue reconstruction should be avoided in partial glossectomy patients in which reduction in tongue length is below 50%.

Legal Strength of Speech-Impaired Marriages in Makassar City from the Syafi'i School and KHI Perspectives

This article discusses the legal strength of speech-impaired marriages in Makassar City from the perspective of the Syafi'i schools and KHI. This article is a Field research using qualitative and descriptive research methods. The source of data in this research is field data in the form of interviews with instructors, those in charge of administration, the celebrant, the speech-impaired bride and the speech-impaired bride's family. The data collection methods used were observation, interviews and documentation. Then, data processing and analysis techniques are carried out through three stages, namely: data reduction, data presentation, and drawing conclusions. The research results show that the legal force for speech-impaired marriages in Makassar City is based on Law Number 1 of 1974 concerning Marriage which regulates marriage provisions. As for marriages with speech impairments, it has been determined in KHI Book I concerning Marriage in Article 17 paragraph (3) and this has compatible with Shafi'i madhhab. Implementation of marriage requirements in Makassar City based on PMA Number 20 of 2019 Article 10 paragraph (2) explains that marriage pillars that have been approved for implementation include the prospective husband, prospective wife, guardian, two witnesses and the consent. This requirement is also stated in KHI book I concerning Marriage Law, Chapter IV concerning the pillars and conditions of marriage, article 14, and then explained in the following articles regarding the requirements and detailed legal explanations. Based on this research, it was found that the terms and conditions were in line with The pillars and conditions that put forward by the Syafi'i school of thought. The practice of marriage contracts taking place in Makassar City refers to the Compilation of Islamic Law article 27 as well as the Regulation of the Minister of Religion of the Republic of Indonesia Number 20 of 2019 article 15. These regulations implemented are in line with several requirements for marriage contracts explained in the Shafi'i school of thought.

Metode Pembelajaran Al-Qur’an dalam Metode Iqro’ bagi Penyandang Tunarungu

Learning methods for deaf students who have hearing, and speech impairments require special methods that suit the condition of the deaf person. This article aims to analyze the Al-Qur'an learning method implemented for deaf students at SMPLB-B YPTB Malang through iqra' method. The research was conducted using a descriptive qualitative approach with the type of field study research. The results showed that iqra' method has advantages and disadvantages. The advantages are 1) students learn based on students' language ability through oral and finger spelling of SIBI signs, 2) applying CBSA strategies, 3) Learning is done privately, 4) teaching modules in the form of iqra' books are in accordance with the development of intelligence of students with visual impairments, 5)assistance is available for students, 6)practical, 7)systematic, 8)varied, 9)communicative, 10) flexible, making it easier for users learn. The disadvantages are it requires a long time to complete the whole learning module, students cannot read Qur'an perfectly as the ability of general students and requires more competent assistant teachers to facilitate students' movement in learning Qur'an. The advantages and disadvantages of the application of iqra' method still provide opportunities to apply other methods of learning Qur'an in order to achieve maximum results for students.

Clinical and molecular heterogeneity of VPS13D-related neurodevelopmental and movement disorders

BackgroundThe VPS13 family of proteins has been implicated in lipid transport and trafficking between endoplasmic reticulum and organelles, to maintain homeostasis of subcellular membranes. Recently, pathogenic variants in each human VPS13S gene, have been linked to distinct human neurodevelopmental or neurodegenerative disorders. Within the VPS13 family of genes, VPS13D is known to be implicated in mitochondria homeostasis and function. MethodsWe investigated a Pakistani sibship affected with neurodevelopmental impairment and severe hyperkinetic (choreoathetoid) movements. Whole exome sequencing (WES) and Sanger sequencing were performed to identify potential candidate variants segregating in the family. We described clinical phenotypes and natural history of the disease during a 3-year clinical follow-up and summarized literature data related to previously identified patients with VPS13D-related neurological disorders. ResultsWe identified by WES an homozygous non-synonymous variant in VPS13D (c.5723 T > C; p.Ile1908Thr) as the potential underlying cause of the disease in our family. Two young siblings developed an early-onset neurological impairment characterized by global developmental delay, with impaired speech and motor milestones, associated to hyperkinetic movement disorders as well as progressive and non-progressive neurological abnormalities. ConclusionIn this study we delineated the heterogeneity of VPS13D-related clinical phenotypes and described a novel VPS13D homozygous variant associated with severe neurological impairment. Further studies will be pivotal to understand the exact VPS13D function and its impact on mitochondria homeostasis, brain development and regulation of movements, to further clarify genotype-phenotype correlations and provide crucial prognostic information and potential therapeutic implications.

Design a Sign Language Translator Using Flexible Sensors

In terms of communication skills, many of us have limitations and shortcomings or what we are more familiar with is speech impairment Speaking is the ability to pronounce articulated sounds or words to express, express and convey thoughts, ideas and feelings. Communication skills can include many ways, including using verbal skills, namely verbally and non-verbally. In Indonesia, there are two sign languages used, namely Indonesian sign language (BISINDO) and Indonesian sign system (SIBI). BISINDO is a sign language that appears naturally in Indonesian culture and is practical for use in everyday life so that BISINDO has several variations in each region. The flex sensor has a thin and densely curved shape so that the flex sensor can be used as a motion detection and finger curve. Flex sensor application for human movement detection, patient monitoring. Therefore, hand-to-letter/text sign language translators using flexible sensors is a very important problem today. The method carried out is system design using tools and components used in research. This tool using the working principle in this system is to translate the sign language of alphabetic letters using flexible sensors. Design sign language translation of alphabetic letters using flexible sensors. The test to display the letters of the alphabet A-Z has a total minimum and maximum resistance at a flexible session of 1000 ohms with a voltage of 5V each. The result of this data is that there is no error in the play because the range value does not violate each other with other range values

Speaker identification using Ultra‐Wideband measurement of voice

AbstractVoice identification is being increasingly adopted in various domains, including security infrastructures, intelligent home systems, and personalised digital assistants. Notably, it harbours significant promise in transforming healthcare, especially in electronic health record detecting and speech impairment monitoring such as aphasia. Current strategies such as acoustic models based on deep learning, voice bio‐metrics, and spectrogram analysis, have been identified with several drawbacks including vulnerability to altered voices, susceptibility to ambient noise, and the necessity for significant computational power. In response to these issues, the authors introduce a ground‐breaking method of voice identification using Ultra‐Wideband (UWB) technology. This method capitalises on the micro‐Doppler shifts associated with movements of the laryngeal prominence. The distinctive nature of these bio‐metric traits related to speech production provides superior resistance against common pitfalls of voice identification. The proposed model leverages the high‐resolution characteristics of UWB to register tiny variations in laryngeal movements produced during speech, thus forming a distinct voice profile for each speaker. Through rigorous testing, the proposed system demonstrated significant progress in voice identification, achieving close to 90% accuracy in controlled experimental settings. This breakthrough indicates that UWB‐enabled voice identification could have a profound effect on medical applications, providing potential improvements in diagnosing, monitoring, possibly treating speech disorders, and thereby shaping a future of enhanced and secured healthcare services.

The Role of Computer-Aided Diagnosis in Speech Restoration in Patients with Cancer of the Oral Cavity and Oropharynx after Hemiglosectomy: a Prospective Comparative Study

INTRODUCTION. Oral cavity and oropharyngeal cancers usually require extensive surgeries accompanied by damages to anatomical structures and impaired speech function.
 AIM. To compare the effectiveness and terms of speech rehabilitation in patients with cancer of the oral cavity and oropharynx using various speech restoration techniques.
 MATERIALS AND METHODS. We studied the effectiveness and length of speech rehabilitation in 140 patients with stages II–IV oral cavity and oropharyngeal cancer. The age of the patients ranged from 24 to 70 years. All the patients underwent hemiglosectomy. Combined modality treatment and postoperative speech rehabilitation were performed according to the technique developed in the Department of Head and Neck Tumors of the Oncology Research Institute. Speech rehabilitation effectiveness was studied on the basis of subjective and objective evaluation of speech using the computer-software complex (OnkoSpeech v 1.0).
 RESULTS AND DISCUSSION. Impaired speech function of patients was observed before starting combined modality treatment and manifested as a change in the prosodic system of speech and subjective communication difficulties associated with the presence of a tumor. After surgery, all the patients demonstrated impaired speech function, ranging from distorted pronunciation to the complete absence of verbal communication. Speech rehabilitation started 8 to 29 days after surgery: in the study group I, Me = 9.6, in the study group II, Me = 9.8, values did not have statistically significant differences (p 0.05). At the beginning of speech rehabilitation, to restore activity and coordinate the work of articulatory apparatus muscles and speech expiration, special complexes of articulation and breathing exercises followed by sound pronunciation correction were performed. Postoperative speech rehabilitation resulted in the improvement of speech function in 100 % of cases. In group II, where the correction of sound pronunciation was performed on the basis of speech diagnosis data using the OnkoSpeech v 1.0 computer-software complex, it was possible to achieve a better result of sound pronunciation correction of all the studied sounds, except for hissing (lingual-frontal) [sh], [zh], [shch], [ch].
 CONCLUSION. The use of the OnkoSpeech v1. ± software package for speech computer-aided diagnosis made it possible to objectively evaluate and quantify the effectiveness of the correction of the sound pronunciation of six phonemes of the Russian language, improve the results of the correction of sound pronunciation and reduce the time of speech therapy.

Design and Development of Indian Sign Language Character Recognition System

The purpose of this study is to look into the challenges involved in categorizing Indian Sign Language (ISL) characters. While a lot of research has been done in the related field of American Sign Language (ASL), not as much has been done with ISL. Lack of standard datasets, obscured traits, and variance in language with geography are the key barriers that have hindered much ISL research. Our study aims to progress this field by collecting a dataset from a deaf school and applying various feature extraction techniques to extract useful information, which is then input into a range of supervised learning algorithms. Our current results for each approach include four fold cross-validation. What sets our work apart from earlier research is that the validation set in our four-fold cross-validation contains photographs of people who are not the same people as those in the training set. Hand gestures and signs are used by those with speech impairments to communicate. Understanding what they're trying to say is challenging for the average person. Though extremely uncommon, there are many systems that convert data to Hindi. Therefore, it is imperative to implement a system that enables the general public to understand and interpret all signals, gestures, and communications. It will close the communication gap that exists between normal people and those who have speech difficulty. The two primary research approaches centered on human-computer interaction are sign language recognition and learning. Multiple sensors are required in order for data flow to be understood in sign language. This research paper focuses on the development of a Hindi-language training tool that can detect images and interpret what someone else is trying to say to persons who have speech impairments. Keywords: Indian Sign Language (ISL), American Sign Language (ASL), Feature Extraction, Supervised learning, Sign Language, etc.