Speech Analysis Research Articles

"Hawks & Doves: U.S.-DPRK Foreign Policy Speech Analysis and the Perception of the Other"

"Hawks & Doves: U.S.-DPRK Foreign Policy Speech Analysis and the Perception of the Other"

Comparison of TEVA vs. PRAAT in the Acoustic Characterization of the Tracheoesophageal Voice in Laryngectomized Patients.

Background: Previous studies have assessed the capability of PRAAT for acoustic voice analysis in total laryngectomized (TL) patients, although this software was designed for acoustic analysis of laryngeal voice. Recently, we have witnessed the development of specialized acoustic analysis software, Tracheoesophageal Voice Analysis (TEVA). This study aims to compare the analysis with both programs in TL patients. Methods: Observational analytical study of 34 TL patients where a quantitative acoustic analysis was performed for stable phonation with vowels [a] and [i] as well as spectrographic characterization using the TEVA and PRAAT software. Results: The Voice Handicap Index (VHI-10) showed a mean score of 11.29 ± 11.16 points, categorized as a moderate handicap. TEVA analysis found lower values in the fundamental frequency vs. PRAAT (p < 0.05). A significant increase in shimmer values was observed with TEVA (>20%). No significant differences were found between spectrographic analysis with TEVA and PRAAT. Conclusions: Tracheoesophageal speech is an alaryngeal voice, characterized by a higher degree of irregularity and noise compared to laryngeal speech. Consequently, it necessitates a more tailored approach using objective assessment tools adapted to these distinct features, like TEVA, that are designed specifically for TL patients. This study provides statistical evidence supporting its reliability and suitability for the evaluation and tracking of tracheoesophageal speakers.

Онтологічний підхід в системі забезпечення безпеки використання IP-телефонії

In today's information world, the use of VoIP has become an attractive option for user communication. With the downward trend in paying for basic broadband services and the rapid increase in internet speeds, the use of VoIP should only continue to grow in popularity. However, as the use of VoIP increases, so do the potential threats to ordinary users. This article examines the peculiarities of organizing corporate VoIP telephony systems, highlights the main problems in information protection systems in VoIP telephony, and outlines ways to solve them. The development of methods for speech analysis and corresponding processing of natural language, which allows for creating more accurate and effective systems for detecting anomalous traffic and potentially dangerous communications, is especially relevant. With the continuous development of artificial intelligence technologies, the direction of using intelligent means for content analysis in the VoIP system is becoming interesting. A method for detecting anomalies in IP-telephony traffic, based on grouping VoIP messages through context-frequency analysis, is proposed. Additionally, a method for automated filling of the ontology of thematic messages in corporate IP-telephony systems is proposed, based on the formalized presentation of messages using tree-like structures and the description of interaction operations through tuple algebra. Furthermore, a software implementation for converting voice messages into text representations using the SpeechRecognition library for voice-to-text conversion in the Python programming language was created. Experimental studies of the proposed approaches were conducted, and a software subsystem for detecting anomalous messages based on the ontological approach was implemented in the current corporate IP-telephony system.

Automated speech analytics in ALS: higher sensitivity of digital articulatory precision over the ALSFRS-R

Objective: Although studies have shown that digital measures of speech detected ALS speech impairment and correlated with the ALSFRS-R speech item, no study has yet compared their performance in detecting speech changes. In this study, we compared the performances of the ALSFRS-R speech item and an algorithmic speech measure in detecting clinically important changes in speech. Importantly, the study was part of a FDA submission which received the breakthrough device designation for monitoring ALS; we provide this paper as a roadmap for validating other speech measures for monitoring disease progression. Methods: We obtained ALSFRS-R speech subscores and speech samples from participants with ALS. We computed the minimum detectable change (MDC) of both measures; using clinician-reported listener effort and a perceptual ratings of severity, we calculated the minimal clinically important difference (MCID) of each measure with respect to both sets of clinical ratings. Results: For articulatory precision, the MDC (.85) was lower than both MCID measures (2.74 and 2.28), and for the ALSFRS-R speech item, MDC (.86) was greater than both MCID measures (.82 and .72), indicating that while the articulatory precision measure detected minimal clinically important differences in speech, the ALSFRS-R speech item did not. Conclusion: The results demonstrate that the digital measure of articulatory precision effectively detects clinically important differences in speech ratings, outperforming the ALSFRS-R speech item. Taken together, the results herein suggest that this speech outcome is a clinically meaningful measure of speech change.

A Speech Act Analysis of Language of Emotion in Governor Akeredolu's Post Owo Massacre Broadcast

The attack on the worshippers of St. Francis Xavier Catholic Church, Ogwaluwa, Owo, Ondo State, Nigeria has further revealed the state of insecurity in the Nigerian sociospace. The grisly act, referred to as Owo massacre, has attracted widespread condemnation from individuals and groups in and outside the shore of Nigeria. This paper attempts the analysis of the post Owo massacre speech of the Governor of Ondo State, Nigeria, Arakunrin Odunayo Oluwarotimi Akeredolu’s as presented in his state broadcast on Owo terror attack. The text of the Post Owo Massacre Speech of Governor Odunayo Oluwarotimi Akeredolu as contained in his state broadcast made on June 7, 2022, entitled Owo terror attack, was downloaded from the Facebook page of Oluwarotimi Akeredolu Aketi on https://fb.watch/mhM-xkaQUu/ and analysed using Speech Act Theory as propounded by J. L Austin (1962) and expatiated by John Searle (1971). The study identifies the illocutionary acts of assertive, directive, expressive and commissive; analyse the performative functions of the identified illocutionary acts and the communicative element that give effectiveness to the acts in the emotional speech and concludes that emotion dictates the choices of the communicating elements deployed in the post Owo massacre state broadcast of Arakunrin Odunayo Oluwarotimi Akeredolu.

Unilateral gamma knife thalamotomy for tremor safety and efficacy in multimodal assessment: a prospective case-control study with two-year follow-up.

Unilateral gamma knife thalamotomy (GKT) is a treatment option for pharmacoresistant tremor of various aetiologies. There have been to date no randomised controlled trials performed to assess its safety and efficacy. Our aim was to summarise a two-year multimodal observation of patients with tremor caused by Parkinson's Disease (PD) or essential tremor (ET). 23 patients with PD (n = 12) or ET (n = 11) were included. They underwent assessments before, V0 (n = 23), and 12 months, V12 (n = 23), and 24 months, V24 (n = 15), after unilateral GKT. Patients were assessed with psychological tests and acoustic voice analysis. Tremor assessment was performed with a digitising table using the Fahn-Tolosa-Marin rating scale (FTMRS). The Unified Parkinson's Disease rating scale part III (UPDRS-III) was also used in the PD group. Gait and balance was assessed using clinical tests, stabilometric platform, and treadmill. No side effects were observed in a two-year follow-up. There was no notable deterioration observed in the patients' psychological evaluation, speech, or assessment of gait and balance. The scores were significantly lower (p = 0.01) in parts A and B of FTMRS one year after GKT. In post hoc analysis, the scores did not differ significantly between V0 and V24. In FTMRS part C (activities of daily living), no significant change was observed. There was no significant difference in total UPDRS part III score or in score of UPDRS part III domains 3 and 4 ('tremor at rest' and 'action and postural tremor of hands') between measurements. UGKT may be a safe treatment modality if performed in an experienced centre. Tremor reduction may diminish over time, and UGKT did not lead to cognitive, gait or speech deterioration in a long-term observation.

A bibliometric analysis of speech and language impairments in Parkinson's disease based on Web of Science.

Many individuals with Parkinson's disease suffer from speech and language impairments that significantly impact their quality of life. Despite several studies on these disorders, there is a lack of relevant bibliometric analyses. This paper conducted a bibliometric analysis of 3,610 papers on speech and language impairments in Parkinson's disease patients from January 1961 to November 2023, based on the Web of Science Core Collection database. Using Citespace software, the analysis focused on annual publication volume, cooperation among countries and institutions, author collaborations, journals, co-citation references, and keywords, aiming to explore the current research status, hotspots, and frontiers in this field. The number of annual publications related to speech and language impairment in Parkinson's disease have been increasing over the years. The USA leads in the number of publications. Research hotspots include the mechanism underlying speech and language impairments, clinical symptoms, automated diagnosis and classification of patients with PD using linguistic makers, and rehabilitation interventions.

AI Detection of Human Understanding in a Gen-AI Tutor

Subjective understanding is a complex process that involves the interplay of feelings and cognition. This paper explores how computers can monitor a user’s sympathetic and parasympathetic nervous system activity in real-time to detect the nature of the understanding the user is experiencing as they engage with study materials. By leveraging advancements in facial expression analysis, transdermal optical imaging, and voice analysis, I demonstrate how one can identify the physiological feelings that indicate a user’s mental state and level of understanding. The mental state model, which views understandings as composed of assembled beliefs, values, emotions, and feelings, provides a framework for understanding the multifaceted nature of the emotion–cognition relationship. As learners progress through the phases of nascent understanding, misunderstanding, confusion, emergent understanding, and deep understanding, they experience a range of cognitive processes, emotions, and physiological responses that can be detected and analyzed by AI-driven assessments. Based on the above approach, I further propose the development of Abel Tutor. This AI-driven system uses real-time monitoring of physiological feelings to provide individualized, adaptive tutoring support designed to guide learners toward deep understanding. By identifying the feelings associated with each phase of understanding, Abel Tutor can offer targeted interventions, such as clarifying explanations, guiding questions, or additional resources, to help students navigate the challenges they encounter and promote engagement. The ability to detect and respond to a student’s emotional state in real-time can revolutionize the learning experience, creating emotionally resonant learning environments that adapt to individual needs and optimize educational outcomes. As we continue to explore the potential of AI-driven assessments of subjective understanding, it is crucial to ensure that these technologies are grounded in sound pedagogical principles and ethical considerations, ultimately empowering learners and facilitating the attainment of deep understanding and lifelong learning for advantaged and disadvantaged students.

A Critical Discourse Analysis of Active and Passive Voice in Three News Texts

This paper applies CDA (critical discourse analysis) to display the hidden relationship between language and power in the discourse of the media; it focuses on the issues which are related to the use of passive or active voice, and tries to investigate which forms of voice are used (passive or active). Data have been collected from three different news texts on the subject of Iraq War Logs. The data have been analysed by using the framework model of Fowler et al. [6] and the findings have been discussed within the framework which is provided by Fairclough, N. [4]. The results show that there is a hidden relationship between language and power in the discourse of the media. Access to the media discourse is limited to specific people only, while other people lack this access. Moreover, the types of voice (passive or active) that are used in different texts determine which sentences are more powerful.

The Problems of National Identity in Contemporary Germany in an International Context

The article analyzes the influence of the current international situation on the concept of German identity. The main elements that form the basis of contemporary German self-consciousness are identified. The author explores the relationship between the regional, national, and supranational components of German self-identification, examining the persistent mental “divide” between the new (former GDR) and the old lands (West Germany). Special attention is paid to the challenges posed for the Federal Republic of Germany in terms of historical discourse and memorial practices by the influx of migrants from the Middle East and North Africa. The role of the 2023 Palestine-Israel escalation in the transformation of the national narrative is separately examined. The article also evaluated the conflict around Ukraine as a factor in strengthening the European dimension of German identity.Among the key methods used by the author are content analysis of speeches by German officials, analysis of legislation and media. In addition, logical, chronological, and comparative-historical methods were applied. All this in aggregate led to the following conclusions. The Federal Republic of Germany is undergoing a systemic and multidimensional identity crisis. The main challenge is finding a balance between historical responsibility, transatlantic commitments, and national interests. The goal of the German establishment is to formulate a new national idea, which includes defining the role and place of Germany in the world, forming a value consensus regarding migrants, and overcoming the alienation between the east and west of the country. However, in the post-1990 world order, such a large-scale task remains rather impossible for the current elites.

COVID success? For whom? Examining the political representation of migrants in Taiwan

ABSTRACT Taiwan’s handling of COVID-19 has been seen as a success. Nevertheless, little is known about how the government has considered migrants in its COVID-19 policies. Using a corpus analysis of the legislative speeches of the Taiwanese policymakers between 2020 and 2022, we investigate how migrants are represented in Taiwan’s COVID-19 strategy. Our findings show that policymakers inadequately consider migrants when drawing up emergency measures and restrictions, despite making up of 6.3 per cent of the population. Our findings illustrate that policymakers focus more on migrant workers than migrant spouses and that policymakers demonize migrant workers and victimize migrant spouses. As COVID-19 does not differentiate based on nationality and constituents would want migrants to be represented for their own safety, the study demonstrates how policymakers may accommodate a diverse population beyond their constituents in crises and illuminates ways to create an inclusive society where non-citizens’ health and safety are considered.

Analisis Wacana Kohesi Pada Teks Debat Calon Presiden Prabowo Subianto Tahun 2024

The research on "Text Cohesion Analysis of Prabowo's Speeches in the Election of Presidential Candidates and Vice Presidential Candidates in 2024" examines the forms of lexical cohesion and grammatical cohesion in the context of the 2024 Prabowo Subianto presidential candidate debate text. The descriptive qualitative methodology was used to analyse the data. The data source for this research is the text recording of the 2024 presidential candidate debate sourced from National TV broadcasts and online news outlets on Narasi.tv. Data was collected for this research through the use of the observational method, accompanied by note-taking techniques. The discourse theory-based agih method was utilized for the data analysis. The findings of this research revealed the existence of lexical cohesion and grammatical cohesion in the texts under examination. The grammatical cohesion observed comprises personal referential elements, including singular and plural first person pronouns, demonstrative references in the past tense, substitutions and conjunctions. In contrast, lexical cohesion is observed in only a few instances, such as repetition and synonymy. This article aims to provide a deeper understanding of discourse, particularly with regard to lexical cohesion and grammatical cohesion.

The kitchen assessment: an interactional analysis of assessment and feedback between an occupational therapist and a patient with aphasia post stroke

Purpose After stroke, patients undergo frequent multidisciplinary assessments. Little is known about patients’ experiences of being assessed and the impact of assessment interactions and feedback for ongoing engagement in rehabilitation. This research aims to stimulate reflection on clinical interactions, even during routine clinical assessments, and the provision of assessment feedback. Materials and methods This study involved a detailed analysis of an authentic kitchen assessment interaction between an occupational therapist and a patient with aphasia following stroke. It used a speech function analysis based on systemic functional linguistics resulting in both dynamic and synoptic data, and a consideration of interactive framing, to explore assessment explanation and feedback. Results The analysis revealed the clinician’s interactive dominance in terms of number and type of moves, and misalignment of interactional framing at different points in the exchange. The session appeared to result in patient disengagement related both to the clinician’s misjudged response to the patient’s aphasia, and the context of assessment itself, characterised by reliance on question-and-answer exchanges, and a tendency to highlight deficit. Conclusions Assessment sessions may be emotionally challenging for patients after stroke and feedback may be interpreted as bad news. Sensitive communication is required to support psychological wellbeing and engagement in rehabilitation. IMPLICATIONS FOR REHABILITATION After stroke, patients are assessed by the multidisciplinary team to inform intervention and discharge planning. Little is known about the feedback patients receive or their views of this feedback, including when it is perceived as bad news. The presence of aphasia can complicate how assessments are conducted and how feedback is delivered and received. Greater awareness is needed of how feedback following assessment might impact patients’ psychological wellbeing and engagement in rehabilitation.

Two voices calling out as one: A split voice analysis of Javanese passives

Two voices calling out as one: A split voice analysis of Javanese passives

Automated free speech analysis reveals distinct markers of Alzheimer’s and frontotemporal dementia

Dementia can disrupt how people experience and describe events as well as their own role in them. Alzheimer’s disease (AD) compromises the processing of entities expressed by nouns, while behavioral variant frontotemporal dementia (bvFTD) entails a depersonalized perspective with increased third-person references. Yet, no study has examined whether these patterns can be captured in connected speech via natural language processing tools. To tackle such gaps, we asked 96 participants (32 AD patients, 32 bvFTD patients, 32 healthy controls) to narrate a typical day of their lives and calculated the proportion of nouns, verbs, and first- or third-person markers (via part-of-speech and morphological tagging). We also extracted objective properties (frequency, phonological neighborhood, length, semantic variability) from each content word. In our main study (with 21 AD patients, 21 bvFTD patients, and 21 healthy controls), we used inferential statistics and machine learning for group-level and subject-level discrimination. The above linguistic features were correlated with patients’ scores in tests of general cognitive status and executive functions. We found that, compared with HCs, (i) AD (but not bvFTD) patients produced significantly fewer nouns, (ii) bvFTD (but not AD) patients used significantly more third-person markers, and (iii) both patient groups produced more frequent words. Machine learning analyses showed that these features identified individuals with AD and bvFTD (AUC = 0.71). A generalizability test, with a model trained on the entire main study sample and tested on hold-out samples (11 AD patients, 11 bvFTD patients, 11 healthy controls), showed even better performance, with AUCs of 0.76 and 0.83 for AD and bvFTD, respectively. No linguistic feature was significantly correlated with cognitive test scores in either patient group. These results suggest that specific cognitive traits of each disorder can be captured automatically in connected speech, favoring interpretability for enhanced syndrome characterization, diagnosis, and monitoring.

Operationalizing Clinical Speech Analytics: Moving From Features to Measures for Real-World Clinical Impact.

This research note advocates for a methodological shift in clinical speech analytics, emphasizing the transition from high-dimensional speech feature representations to clinically validated speech measures designed to operationalize clinically relevant constructs of interest. The aim is to enhance model generalizability and clinical applicability in real-world settings. We outline the challenges of using conventional supervised machine learning models in clinical speech analytics, particularly their limited generalizability and interpretability. We propose a new framework focusing on speech measures that are closely tied to specific speech constructs and have undergone rigorous validation. This research note discusses a case study involving the development of a measure for articulatory precision in amyotrophic lateral sclerosis (ALS), detailing the process from ideation through Food and Drug Administration (FDA) breakthrough status designation. The case study demonstrates how the operationalization of the articulatory precision construct into a quantifiable measure yields robust, clinically meaningful results. The measure's validation followed the V3 framework (verification, analytical validation, and clinical validation), showing high correlation with clinical status and speech intelligibility. The practical application of these measures is exemplified in a clinical trial and designation by the FDA as a breakthrough status device, underscoring their real-world impact. Transitioning from speech features to speech measures offers a more targeted approach for developing speech analytics tools in clinical settings. This shift ensures that models are not only technically sound but also clinically relevant and interpretable, thereby bridging the gap between laboratory research and practical health care applications. We encourage further exploration and adoption of this approach for developing interpretable speech representations tailored to specific clinical needs.

An Analysis of Merry Riana’s Speech Acts in Alberthiene Endah’s Million Dollar Dream

This research is entitled analysis of Merry Riana's speech acts in the novel A Million Dollar Dream by Alberthiene Endah. This research is limited to several main ideas related to observations of the following two questions: what are the types of Riana's speech acts in the Million Dollar Dream Novel and the types of Riana's reference expressions in the Million Dollar Dream Novel. To explain this, the theory used comes from Austin's theory and Kroeger's theory which is used to dissect and get answers to the objectives of this research. For the data analysis method, the author uses a qualitative method by emphasizing the meaning and meaning of Merry Riana's speech acts. This research uses data collection techniques in the form of reading and taking notes. The conclusion in this research is the meaning contained in Merry Riana's speech acts. There are locutionary speech acts, namely speech acts to state something, illocutionary speech acts, namely speech acts that contain hidden meanings or other meanings that the speaker wants to convey to the interlocutor, perlocutionary speech acts are acts of increasing influence or impact on the interlocutor.

Voice as a Biomarker of Pediatric Health: A Scoping Review.

The human voice has the potential to serve as a valuable biomarker for the early detection, diagnosis, and monitoring of pediatric conditions. This scoping review synthesizes the current knowledge on the application of artificial intelligence (AI) in analyzing pediatric voice as a biomarker for health. The included studies featured voice recordings from pediatric populations aged 0-17 years, utilized feature extraction methods, and analyzed pathological biomarkers using AI models. Data from 62 studies were extracted, encompassing study and participant characteristics, recording sources, feature extraction methods, and AI models. Data from 39 models across 35 studies were evaluated for accuracy, sensitivity, and specificity. The review showed a global representation of pediatric voice studies, with a focus on developmental, respiratory, speech, and language conditions. The most frequently studied conditions were autism spectrum disorder, intellectual disabilities, asphyxia, and asthma. Mel-Frequency Cepstral Coefficients were the most utilized feature extraction method, while Support Vector Machines were the predominant AI model. The analysis of pediatric voice using AI demonstrates promise as a non-invasive, cost-effective biomarker for a broad spectrum of pediatric conditions. Further research is necessary to standardize the feature extraction methods and AI models utilized for the evaluation of pediatric voice as a biomarker for health. Standardization has significant potential to enhance the accuracy and applicability of these tools in clinical settings across a variety of conditions and voice recording types. Further development of this field has enormous potential for the creation of innovative diagnostic tools and interventions for pediatric populations globally.

Speech production and perception data collection in R: A tutorial for web-based methods using speechcollectr.

This tutorial is designed for speech scientists familiar with the R programming language who wish to construct experiment interfaces in R. We begin by discussing some of the benefits of building experiment interfaces in R-including R's existing tools for speech data analysis, platform independence, suitability for web-based testing, and the fact that R is open source. We explain basic concepts of reactive programming in R, and we apply these principles by detailing the development of two sample experiments. The first of these experiments comprises a speech production task in which participants are asked to read words with different emotions. The second sample experiment involves a speech perception task, in which participants listen to recorded speech and identify the emotion the talker expressed with forced-choice questions and confidence ratings. Throughout this tutorial, we introduce the new R package speechcollectr, which provides functions uniquely suited to web-based speech data collection. The package streamlines the code required for speech experiments by providing functions for common tasks like documenting participant consent, collecting participant demographic information, recording audio, checking the adequacy of a participant's microphone or headphones, and presenting audio stimuli. Finally, we describe some of the difficulties of remote speech data collection, along with the solutions we have incorporated into speechcollectr to meet these challenges.

Machine Learning Approaches for Dementia Detection Through Speech and Gait Analysis: A Systematic Literature Review.

Dementia is a general term for several progressive neurodegenerative disorders including Alzheimer's disease. Timely and accurate detection is crucial for early intervention. Advancements in artificial intelligence present significant potential for using machine learning to aid in early detection. Summarize the state-of-the-art machine learning-based approaches for dementia prediction, focusing on non-invasive methods, as the burden on the patients is lower. Specifically, the analysis of gait and speech performance can offer insights into cognitive health through clinically cost-effective screening methods. A systematic literature review was conducted following the PRISMA protocol (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). The search was performed on three electronic databases (Scopus, Web of Science, and PubMed) to identify the relevant studies published between 2017 to 2022. A total of 40 papers were selected for review. The most common machine learning methods employed were support vector machine followed by deep learning. Studies suggested the use of multimodal approaches as they can provide comprehensive and better prediction performance. Deep learning application in gait studies is still in the early stages as few studies have applied it. Moreover, including features of whole body movement contribute to better classification accuracy. Regarding speech studies, the combination of different parameters (acoustic, linguistic, cognitive testing) produced better results. The review highlights the potential of machine learning, particularly non-invasive approaches, in the early prediction of dementia. The comparable prediction accuracies of manual and automatic speech analysis indicate an imminent fully automated approach for dementia detection.