Phonetic Features Research Articles

SELECTION OF DISCRIMINATIVE FEATURES FOR ARABIC PHONEME’S MISPRONUNCIATION DETECTION

Pronunciation training is an important part of Computer Assisted Pronunciation Training (CAPT) systems. Mispronunciation detection systems recognized pronunciation mistakes from user’s speech and provided them feedback about their pronunciation. Acoustic phonetic features plays a vital role in speech classification based applications. This research work investigated the suitability of various acoustic features: pitch, energy, spectrum flux, zero-crossing, Entropy and MelFrequency Cepstral Coefficients (MFCCs). Sequential Forward Selection (SFS) was used to find out most suitable acoustic features from the computed feature set. This study used K-Nearest Neighbors (K-NN) classifier was used to detect the pronunciation mistakes from Arabic phonemes. This research selected the set of most discriminative acoustic features for each phoneme. K-NN achieved accuracy of 92.15% for mispronunciation detection of Arabic Phonemes

Extracting Phonetic Posterior-Based Features for Detecting Multiple Sclerosis From Speech.

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system which, in addition to affecting motor and cognitive functions, may also lead to specific changes in the speech of patients. Speech production, comprehension, repetition and naming tasks, as well as structural and content changes in narratives, might indicate a limitation of executive functions. In this study we present a speech-based machine learning technique to distinguish speakers with relapsing-remitting subtype MS and healthy controls (HC). We exploit the fact that MS might cause a motor speech disorder similar to dysarthria, which, with our hypothesis, might affect the phonetic posterior estimates supplied by a Deep Neural Network acoustic model. From our experimental results, the proposed posterior posteriorgram-based feature extraction approach is useful for detecting MS: depending on the actual speech task, we obtained Equal Error Rate values as low as 13.3%, and AUC scores up to 0.891, indicating a competitive and more consistent classification performance compared to both the x-vector and the openSMILE 'ComParE functionals' attributes. Besides this discrimination performance, the interpretable nature of the phonetic posterior features might also make our method suitable for automatic MS screening or monitoring the progression of the disease. Furthermore, by examining which specific phonetic groups are the most useful for this feature extraction process, the potential utility of the proposed phonetic features could also be utilized in the speech therapy of MS patients.

A pattern-based approach to detect irony in twitter sentiment analysis

Twitter sentiment analysis poses challenges due to the informal language, limited character count, and prevalence of sarcasm, which can alter the polarity of messages. This paper presents a pattern-based approach to detect irony in Twitter sentiment analysis. By analyzing various types of irony and identifying their patterns, this paper proposes a methodology to improve the efficiency of sentiment analysis. Tweets are classified into different categories based on their sarcasm using a machine learning algorithm. The proposed approach involves feature extraction from tweets, including sentiment-related features, punctuation-related features, grammatical and phonetic features, and patternbased features. A hybrid pattern extraction with a classification model is employed to process tweet data and classify it as sarcastic or not. Experimental results demonstrate the effectiveness of the proposed approach in detecting sarcasm in tweets, with precision ranging from 84.6% to 98.1% across different classifier algorithms. This pattern-based approach offers promising results for enhancing sentiment analysis on Twitter and understanding the nuances of communication in social media discourse.

Interpreting Deep Representations of Phonetic Features via Neuro-Based Concept Detector: Application to Speech Disorders Due to Head and Neck Cancer

The popularity of Deep Neural Networks (DNNs) is growing significantly, and so is the interest in gaining a better understanding of their functioning. In this work, it is even more interesting to reveal the behavior of these black-boxes since we are involved in a clinical context. To this end, we propose a general analytic framework, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Neuro-based Concept Detector (NCD)</i> , for interpreting deep representations of a DNN. Based on the activation patterns of the hidden neurons, this framework highlights the capacity of neurons to detect a specific concept related to the final task. The key strength of our framework is that it provides an interpretability tool for any type of DNN performing a classification task regardless of the application field. In this paper, we evaluate this framework on a Convolutional Neural Network (CNN) trained for the task of French phone classification. This choice was guided by the final objective of a long-term research project, which aims to identify the linguistic units best contributing to the maintenance or loss of intelligibility in the context of speech disorders. Through <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">NCD</i> , we demonstrate the emergence of phonetic features in the classification layers of the CNN-based model, while applied on healthy speech, a concept with a great interest in the field of clinical phonetics. Indeed, we further show that these interesting findings shed light on the characteristics of speech disorders in terms of altered phonetic features and provide relevant information for clinical practice, notably, patients' rehabilitation and follow-up.

ОТКЛОНЕНИЯ ОТ ЛИТЕРАТУРНОЙ НОРМЫ ЯЗЫКА КАК ЛИНГВОКУЛЬТУРНАЯ ПРОБЛЕМА ПЕРЕВОДА

To create vivid speech portrayals of the characters, British and American authors often use deviations from the norms of literary language at different levels. The article compares Russian translations of such works of fiction made at the end of the 19th century and the very beginning of the 20th century with those produced a hundred years later. Analysis has shown that formerly translators did not use to pay attention to language norms and deviations from them, but with the development of national literary culture, translation theory and practice, the situation has changed. Nowadays most deviations are successfully reproduced in translation by analogous violations of the norms at the same level as in the original, a notable exception being territorial and socio-ethnic dialects that have no equivalents in other languages and translators have to resort to vertical compensation of their phonetic features, usually by making use of the lexical resources of the translating language. Thus, vocabulary proves to be the most comprehensive and universal resource for reproducing violations of literary norms not only on the lexical level itself, but also on other levels of language. The appropriate use of vocabulary, however, requires on the part of the translator a particularly high literary culture, language skill and linguistic flair.

East Slavic Contact Interaction in Primorsky Krai (According to the Linguistic Expedition of 2023)

The paper presents the first results of the field research carried out in June 2023 in the Khorol and Chernigov districts of Primorsky Krai of Russia among the descendants of immigrants from Ukrainian and Belarusian lands. The purpose of the expedition survey was to record the speech of dialect speakers of the Ukrainian and Belarusian languages, to study the functioning of dialects in contact with closely related Russian language, to identify the preservation of traditional folk culture. The main problem during field research was related to the difficulties of informants when trying to record spontaneous dialect speech. Relics of Belarusian dialects were not found in this expedition. The utterances in Ukrainian were recorded in cases of quoting speech of older relatives, in memories about childhood and in folklore. The paper presents some transcribed texts, reveals phonetic and morphological features, analyzes individual lexical units. Narratives on the following topics are presented: the linguistic situation among migrants at the micro and macro levels, metalanguage observations, stories about local place names and ethnic nicknames. In addition to audio recordings, a written source is analyzed, the history of the formation of the Khorol village, written in Russian with Ukrainian dialect items. This text reveals all the linguistic features noted in the oral speech of the informants. More-over, it contains valuable information about the daily activities of the first settlers, about their holidays, customs, contacts with neighbors of different ethnicity. In the future, it is planned to work on transcribing the entire corpus of recorded texts for their publication and analysis, as well as to publish a written history of the village of Khorol.

Зоонимы, обозначающие оленевых в алтайской лингвокультуре

The article is devoted to the linguistic and cultural specificity of zoonyms denoting reindeer family members (sygyn ‘deer, deer’ and bulan ‘elk’) in the Altai culture. A case study of artistic and folklore texts and field materials allowed the phonetic, dialect, lexical-semantic, folklore, and ethnographic features of zoonyms denoting deer animals in the Altai language and folklore to be identified for the first time. The cultural stereotypes of the Altai people about deer are closely related to hunting customs and traditions. In hunting folklore, reindeer family members have a sacred meaning: they are considered sacred animals of Altai, the personification of the master spirit of Altai. In this context, a complete system of prohibitions and taboos has been formulated within the realm of hunting ethics. In the fiction of the Altai people, the deer and elk became animal characters of hunting stories and are also used for comparisons and metaphorical allegories about humans. In folklore and artistic texts, the denotative features of zoonyms characterize the features of the body structure or color, the habitat of these wild animals. The connotations associated with these zoonyms serve as a reflection of a person’s moral and ethical character. In the linguistic consciousness of native speakers of the Altai language and culture, deer and elk are associated with male strength and courage. The participation of zoonyms-reindeer in the conceptualization of spatial and temporal concepts is presented in chrononyms (sygyn ai ‘month of deer’) and toponyms indicating the habitat of moose and deer (for example, Bulandu ‘with moose’).

Z badań nad językiem piśmiennictwa nowogródzkiego z okresu międzywojennego. 3. Elementy kresowe i inne osobliwości językowe w międzywojennym „Życiu Nowogródzkim”

In the inter‑war period, a number of press titles appeared in Nowogródek, but chief among them was “Życie Nowogródzkie”. Several dozen issues of this periodical/daily bear witness to the rare phonetic, inflectional, word‑making and syntactic features of Borderland Polish. Much more numerous are Borderland dialect words, words and phrases more frequently used in the Borderlands, and other peculiar words (archaisms, words now obsolete, words rarely used, “neologisms,” idiolectisms and phrasal idioms). 165 such language forms have been recorded. All volumes of “Życie Nowogródzkie” are deserving of detailed study.

Особливості гуцульської говірки села Розтоки Вижницького району Чернівецької області

The purpose of the research is to describe the main features of the Hutsul dialect in the village of Roztoky Vyzhnytcia district Chernivtci region. This ancient dialect of Northern Bukovyna not been the specific topic yet. The material of the study was the author's recordings of dialect speech in the village of Roztoky in 2017. There were characterized the most important phonetic, morphological and syntactic features of spoken language manifested in spontaneous dialectal speech. Special attention was paid to ancient local features of dialect. There were described the word change of nominal parts of speech, morphological features of nouns, adjectives, numerals, dialectal forms of pronouns, peculiarities of dialectal conjugation too. Moreover, there was noted about the functioning of prepositional-noun constructions, reinforcing particles and exclamations, the frequent use of subordinate clauses, their stringing in the dialectal text. This research also emphasizes the isoglosses of the phenomena that separate the dialect from the neighboring Bukovyna dialects.

РЕАЛІЗАЦІЯ ЛЮБОВНОЇ МАГІЇ В ТЕКСТАХ TABELLAE DEFIXIONUM

The main focuses of the study include the analysis of lexical items related to “love potions” in Latin, such as amātōrium, medicamentum amatorium, potio, venus, venenum. The author notes that these terms have a double meaning, covering both love and poison. The focus of this study is the analysis of lexical units related to “love potions” in Latin (amātōrium, medicamentum amatorium, potio, venus, venenum), which have a double meaning, covering both love and poison. A separate aspect of the article is devoted to tabellae defixionum, which are considered an important element of the sacred Latin text. The motives that prompted the creation of such tablets are considered, in particular in the context of the difficult position of women in ancient Rome. Love was especially important for women at that time, and the article points to a variety of motives: revenge for betrayal, the desire to “get your desired man”, strong love and healthy children. The analysis of phonetic and morphological features of tabellae defixionum is carried out in the works of V. Vaananen, R. Tomlin, G. Herman, A. Kropp, J. Blansdorf and others. However, the author focuses not on the systemic and structural features of the texts, but on the pragmalinguistic aspect, simultaneously solving the question of whether these texts belong to everyday speech and considering their lingual pragmatic function. The article also highlights different types of achieving the desired effect in the texts of love magic: a) aimed at arousing attachment and b) aimed at seduction. The connection between the magical text and its effect on the psyche and feelings of the target person is being tracked. A general conclusion is drawn regarding the high level of organization and careful use of verbal elements to achieve the desired effect in the context of love magic in ancient Rome.

MIKOŁAI KRUSZEWSKI IN THE LANGUAGE SPACE OF UKRAINE

The article examines the Ukrainian works in the scientific heritage of Mikołaj Kruszewski in three aspects: biographical, social and scientific. The linguist was born in Volyn in a Polish-German family, where the indigenous Ukrainian population was the majority. He formed his personality in the region, he considered Volyn his native land, and later, working in distant Kazan, he repeatedly came with his family in the summer to rest on his mother’s estate. In those days, Ukraine did not have the status of statehood. They called the country “Little Russia”. The disputable question was whether the Ukrainian language is independent or it is a dialect of the Russian language. The most common terms were “Little Russian dialect” and “Dialect of Rus’ Minor”. Kruszewski used these terms. The scientist applied knowledge of the Ukrainian language and culture for a scientific purpose. In his student essay “Spelis as a form of Russian folk poetry” he referred to Ukrainian works, used the toponyms “Little Russia” and “Volyn province”, included beliefs collected by him in the village of Solotvin. In Kazan Mikołaj Kruszewski studied the phonetic and morphological features of the Ukrainian language. For this purpose, he translated the Lithuanian fairy tale «Who knows better to lie» to the dialect of Solotvino. At the masters exam he received eight assignments on the text of a Ukrainian story from Jan Baudouin de Courtenay. In the works “On “analogy” and “folk etymology” (“Volksеtymologie”)”, “On the question of the guna. A study in the domain of Old Slavic vocalism”, “Üeber die Lautabwechslung”, “An Outline of Lingustic Science” Mikołaj Kruszewski drew on Ukrainian vocabulary to illustrate reflections and conclusions on word formation and phonetics. Ukrainian content in the research of Mikołaj Kruszewski testifies to the author᾽s linguistic erudition and desire, revealing the potential of a non-state language, to put it on a par with other Indo-European languages.

Spatial patterns of elevated magnetic susceptibility in progressive apraxia of speech

PurposeProgressive apraxia of speech (PAOS) is a neurodegenerative disorder affecting the planning or programming of speech. Little is known about its magnetic susceptibility profiles indicative of biological processes such as iron deposition and demyelination. This study aims to clarify (1) the pattern of susceptibility in PAOS patients, (2) the susceptibility differences between the phonetic (characterized by predominance of distorted sound substitutions and additions) and prosodic (characterized by predominance of slow speech rate and segmentation) subtypes of PAOS, and (3) the relationships between susceptibility and symptom severity. MethodsTwenty patients with PAOS (nine phonetic and eleven prosodic subtypes) were prospectively recruited and underwent a 3 Tesla MRI scan. They also underwent detailed speech, language, and neurological evaluations. Quantitative susceptibility maps (QSM) were reconstructed from multi-echo gradient echo MRI images. Region of interest analysis was conducted to estimate susceptibility coefficients in several subcortical and frontal regions. We compared susceptibility values between PAOS and an age-matched control group and performed a correlation analysis between susceptibilities and an apraxia of speech rating scale (ASRS) phonetic and prosodic feature ratings. ResultsThe magnetic susceptibility of PAOS was statistically greater than that of controls in subcortical regions (left putamen, left red nucleus, and right dentate nucleus) (p < 0.01, also survived FDR correction) and in the left white-matter precentral gyrus (p < 0.05, but not survived FDR correction). The prosodic patients showed greater susceptibilities than controls in these subcortical and precentral regions. The susceptibility in the left red nucleus and in the left precentral gyrus correlated with the prosodic sub-score of the ASRS. ConclusionMagnetic susceptibility in PAOS patients was greater than controls mainly in the subcortical regions. While larger samples are needed before QSM is considered ready for clinical differential diagnosis, the present study contributes to our understanding of magnetic susceptibility changes and the pathophysiology of PAOS.

Unified Parametrization of Phonetic Features and Numerical Calculation of Phonetic Distances between Speech Sounds

Unified Parametrization of Phonetic Features and Numerical Calculation of Phonetic Distances between Speech Sounds

ІСТОРИЧНИЙ І МОВНО-КУЛЬТУРНИЙ ВИМІРИ НОБЕЛЬСЬКОГО ЄВАНГЕЛІЯ 1520 РОКУ

A manuscript from the beginning of the 16th century from Noble (Pinsk County, which is now in Rivne oblast, Ukraine) was studied, representing the religious writing of the Grand Duchy of Lithuania in historical and language-cultural aspects. The afterword to the Nobel Gospel was analyzed, and the historical figures named in it were identified (Prince Fedor Ivanovich Yaroslavich, Bishop Jonah). Information about them was collected based on historical sources and scientific literature. The ‘Ruthenian’ edition of the Church Slavonic language, manifestations of the second South Slavic influence in the text, is characterized. The monument’s history information, now represented in the Library of the Vrublevsky Academy of Sciences of Lithuania (Lithuania), was systematized. The Nobel Gospel, which has not been the subject of scientific study until now, was analyzed during an interdisciplinary study. The historical context of the monument’s creation based on the afterword is analyzed. Its temporal and spatial localization, the possible sphere of operation, ancient storage of the rarity, scribes (Chivs), and historians were established. Prince Fedor Ivanovich Yaroslavich carried out charitable activities. He founded and supported churches and monasteries in the Pinsk District. The bishops of Pinsk and Turov, Vasian, and later Jonah, mentioned in the afterword, appealed to the king and received a “salary” letter stating that it should be their will and approval for the construction of churches and monasteries. The analyzed manuscript from Polissia was proved to reveal the book traditions of the 16th century and the eccentricity of the centers of rewriting texts of religious writing. The main manifestations of the second South Slavic influence in the orthography of the manuscript are characterized. Different orthographic and phonetic features of the ‘Ruthenian’ edition of the Church Slavonic language have been analyzed. Since the 60s of the 19th century, the manuscript from Polissia was transported to the Vilnius Public Library. The Manuscript Department was founded here, and the first descriptions of the monument were compiled.

Some of Azerbaijan anthroponyms of Arabic origin phonetic features

Some of Azerbaijan anthroponyms of Arabic origin phonetic features

Структурные типы и семантические особенности односложных корней в лексических единицах, представляющих концептосферы «Мхи», «Грибы», «Травы», «Цветы» (на материале лексики татарского, башкирского и чувашского языков)

The research is devoted to the study of the structural type of nominal and verbal word stems and the ideographic characteristics of monosyllabic roots in the Turkic languages of the Urals-Volga region. The paper presents the lexemes of the Tatar, Bashkir and Chuvash languages associated with the conceptual spheres “Mosses”, “Mushrooms”, “Grasses”, “Flowers”. The aim of the study is to identify the features of the sound composition of monosyllabic roots in the lexemes representing the concept of the cognitive sphere “Nature (Animate)” using the vocabulary of the Tatar, Bashkir and Chuvash languages. Scientific novelty of the work lies in taking a holistic approach to the issue of lexico-semantic and phonetic characteristics of monosyllabic roots in the Turkic languages of the Urals-Volga region within the framework of the cognitive sphere “Nature (Animate)”. The paper is the first to examine the interlanguage and intralanguage semantic fields of the Tatar, Bashkir and Chuvash languages. The research findings have shown that the analysed names of plants in the modern Turkic languages of the Urals-Volga region make it possible to trace the development of the meanings of the same word in different languages. This points to the fact that people comprehend the surrounding world through objects to which they give names.

Phonetic characteristics of the language of the national press in the period of ADR (1918-1920)

Phonetic characteristics of the language of the national press in the period of ADR (1918-1920)

"PHONETIC PECULIARITIES OF THE DEFENCE SPEECH OF A LAWYER "

"The article aims to uncover the phonetic peculiarities of an attorney’s defence speech in the English and Kazakh languages from the perspective of persuasive speech technique. The reason for analysing the phonetical peculiarities of an attorney’s defence speech is that the responsibilities of an attorney comprise the litigation of the client from the beginning to the end of the case; in particular, working with the client, revealing evidence and witnesses; identifying, selecting, and collecting paperwork; talking with the client to formulate the exhibits; clarifying the issue through questions and answers, and the last step is defending in court. These activities require an attorney to be well acquainted with legal literature and the language of the court, which precisely, takes place in the courtroom. Thus, we have collected the fragments of attorney defence speech that took place at the trial from the YouTube channel and analysed the phonetic features using the Praat computer program. The authors demonstrate how phonetic features are realised during cross-questioning moments using excerpts from an attorney’s persuasive speech. These findings shed light on how the persuasive speech of the attorney can create the discursive space and phonological features of the speech to effectively impact the process. "

АДАМДЫН КЕСИБИН, КЫЗМАТЫН АТООНУН ИЗИЛДӨӨ МЕТОДДОРУ ЖАНА АСПЕКТИЛЕРИ

The system of nominations is wide and varied. The graphic structure, phonetic features, morphological and syntactic structures of the profession nomination were not even a special object of study for linguists in the history of the language. However, the name of a person's profession is included in the vocabulary group of each nation and is analyzed. The nomination of a person's profession is associated with his activity abilities. The current situation on the labor market allows us to name many professions. For example, a manager, management, blogger, designer, programmer, flash programmer, florist, etc. The expansion of economic, political and cultural ties in society, the development of science and technology will stimulate quantitative and qualitative changes in the group of professional titles of a person.

Boosting Speech-to-Text software potential

The article focuses on finding ways of boosting efficiency and accuracy of Speech-to-Text (STT)-powered input. The effort is triggered by the growing popularity of the software among professional translators, which is in line with the general trend of abandoning typing in favor of speech-to-text applications. Insisting that better effectiveness of such programs is contingent on their accuracy, the researchers analyze major factors, both linguistic and technical in nature, affecting the computer-assisted speech transcribing quality. This leads to an experiment, putting the hypothesis to a test. Based on numerical and performance data, errors and their breakdown into categories in an attempt to figure out their origins, it dwells on various approaches to dictation in a combination with several hardware options and configurations. These pave the way for recommendations on the improvement of STT performance based on the Dragon software. The authors arrive at a conclusion that it is possible to boost the STT accuracy up to 99 percent by adjusting the program profile to accommodate phonetic features of the speaker with due consideration of his accent, adding to the dictionary the most complex and rare vocabulary beforehand, and fine-tuning input hardware. Other noteworthy results include ways to overcome the most complex transcribing challenges, i.e. proper names, placenames, abbreviations, etc.