Speech Classification Research Articles

Machine learning in healthcare strategic management: a systematic literature review

PurposeThis study specifically seeks to investigate the strategic implementation of machine learning (ML) algorithms and techniques in healthcare institutions to enhance innovation management in healthcare settings.Design/methodology/approach The papers from 2011 to 2021 were considered following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. First, relevant keywords were identified, and screening was performed. Bibliometric analysis was performed. One hundred twenty-three relevant documents that passed the eligibility criteria were finalized.Findings Overall, the annual scientific production section results reveal that ML in the healthcare sector is growing significantly. Performing bibliometric analysis has helped find unexplored areas; understand the trend of scientific publication; and categorize topics based on emerging, trending and essential. The paper discovers the influential authors, sources, countries and ML and healthcare management keywords.Research limitations/implications The study helps understand various applications of ML in healthcare institutions, such as the use of Internet of Things in healthcare, the prediction of disease, finding the seriousness of a case, natural language processing, speech and language-based classification, etc. This analysis would help future researchers and developers target the healthcare sector areas that are likely to grow in the coming future.Practical implications The study highlights the potential for ML to enhance medical support within healthcare institutions. It suggests that regression algorithms are particularly promising for this purpose. Hospital management can leverage time series ML algorithms to estimate the number of incoming patients, thus increasing hospital availability and optimizing resource allocation. ML has been instrumental in the development of these systems. By embracing telemedicine and remote monitoring, healthcare management can facilitate the creation of online patient surveillance and monitoring systems, allowing for early medical intervention and ultimately improving the efficiency and effectiveness of medical services.Originality/value By offering a comprehensive panorama of ML's integration within healthcare institutions, this study underscores the pivotal role of innovation management in healthcare. The findings contribute to a holistic understanding of ML's applications in healthcare and emphasize their potential to transform and optimize healthcare delivery.

Examining Speech Acts in Jordanian Advertising: Pragmatic Functions, Linguistic Features, and Rhetorical Devices

This qualitative study aims to investigate the persuasive speech acts used by Jordanian advertisers in fashion, food, and technology print advertisements. The selected advertisements were transcribed and analyzed using NVivo. Commercial speech acts were classified using Searle’s (1979) taxonomy of assertives, directives, commissives, expressives, and declaratives. The researcher took care to obtain the participants' informed consent and kept subject data confidential and anonymous. The evaluation of Jordanian advertising speech activities and the linguistic and cultural influences exerted upon them was conducted using tables and narratives. The findings of this research emphasize the diverse advertising strategies employed by Jordanian organizations. It was determined that directives, statements, and demands were the three most prevalent categories of speech acts in Jordanian advertising. These methods of communication were utilized to advocate for particular client actions, to make claims about the quality of the product being sold, and to guarantee certain outcomes for buyers. The study also revealed that Jordanian businesses frequently employ hyperbole, metaphor, and rhetorical queries in their marketing communications in order to make their products or services appear more desirable to potential consumers.

The Role of Consumer Speech Acts in Brand Activism: A Transformative Advertising Perspective

Transformative advertising research (TAR) suggests examining advertising’s transformational possibilities via the interactions between institutional actors at each marketing level to gauge its effect on society. We employ rhetorical institutionalism as a lens to examine the online speech acts of consumers as they respond to a brand activism campaign focusing on an environmental problem. Our data take the form of written comments by YouTube users and employ a research design using automated text analysis and qualitative thematic data analysis. Our contributions to TAR are threefold. First, we offer a preliminary conceptualization of the role of consumer language as rhetorical institutional work to advance TAR scholars and practitioners’ insight. Second, we highlight the role of linguistic tone and clout in giving speakers agency through which consumers as institutional actors create, maintain, and disrupt institutional logics and practices. Finally, we develop a tripartite classification of consumer speech acts used to support brand activism. We label these activist warriors, brand champions, and conscious consumers as typologies that deepen understanding of how consumers’ online speech may amplify brand activism, thereby contributing to advertising’s transformative outcomes. We conclude by outlining important managerial implications including how practitioners can adopt the tripartite classification to enhance brand activism campaigns.

Ecologically valid speech collection in behavioral research: The Ghent Semi-spontaneous Speech Paradigm (GSSP)

This paper introduces the Ghent Semi-spontaneous Speech Paradigm (GSSP), a new method for collecting unscripted speech data for affective-behavioral research in both experimental and real-world settings through the description of peer-rated pictures with a consistent affective load. The GSSP was designed to meet five criteria: (1) allow flexible speech recording durations, (2) provide a straightforward and non-interfering task, (3) allow for experimental control, (4) favor spontaneous speech for its prosodic richness, and (5) require minimal human interference to enable scalability. The validity of the GSSP was evaluated through an online task, in which this paradigm was implemented alongside a fixed-text read-aloud task. The results indicate that participants were able to describe images with an adequate duration, and acoustic analysis demonstrated a trend for most features in line with the targeted speech styles (i.e., unscripted spontaneous speech versus scripted read-aloud speech). A speech style classification model using acoustic features achieved a balanced accuracy of 83% on within-dataset validation, indicating separability between the GSSP and read-aloud speech task. Furthermore, when validating this model on an external dataset that contains interview and read-aloud speech, a balanced accuracy score of 70% is obtained, indicating an acoustic correspondence between the GSSP speech and spontaneous interviewee speech. The GSSP is of special interest for behavioral and speech researchers looking to capture spontaneous speech, both in longitudinal ambulatory behavioral studies and laboratory studies. To facilitate future research on speech styles, acoustics, and affective states, the task implementation code, the collected dataset, and analysis notebooks are available.

A survey of machine learning based techniques for hate speech detection on Twitter

The use of the Internet and social networks for communication has significantly increased in recent years. Twitter is the third most popular worldwide Online Social Network (OSN), only after Facebook and Instagram. Compared to other OSNs, Twitter presents a simpler data model and more straightforward data access API, making it a valuable tool for studying and analyzing online behavior, including abusive patterns. This survey attempts to create a machine learning-based guide for automatic hate speech classification, including a description of Twitter's technology and terminology, social graphs, sentiment analysis concepts, and hate speech identification. This study also adopted a systematic literature review on the most advanced computing techniques involved with the subject, focusing on state-of-the-art machine learning and research directions.

The Cake Application: A Mobile-Assisted Language Learning (MALL) to Improve English Speaking Skill

Speaking is typically a crucial component of the English unit since it allows students to express and communicate their thoughts and opinions. Possessing strong communication skills allows students to discover who they are during the teaching-learning process. As a result, in order to encourage and assist the students, the teacher must determine the best way to spark their interest and enhance their proficiency in learning English. The excellent and contemporary Cake application can be utilized as supplementary material for speech classes. It encourages engaged and joyful learning among the pupils in the classroom. With the Cake application, they can concentrate more on honing their speaking skills and don't have to worry about making mistakes when they practice speaking because the app provides immediate feedback. Cake application also supports students in learning vocabulary. They can gain more vocabulary by learning dialogues from Cake application.

Hate speech detection on Indonesian text using word embedding method-global vector

<p>Hate speech is defined as communication directed toward a specific individual or group that involves hatred or anger and a language with solid arguments leading to someone's opinion can cause social conflict. It has a lot of potential for individuals to communicate their thoughts on an online platform because the number of Internet users globally, including in Indonesia, is continually rising. This study aims to observe the impact of pre-trained global vector (GloVe) word embedding on accuracy in the classification of hate speech and non-hate speech. The use of pre-trained GloVe (Indonesian text) and single and multi-layer long short-term memory (LSTM) classifiers has performance that is resistant to overfitting compared to pre-trainable embedding for hatespeech detection. The accuracy value is 81.5% on a single layer and 80.9% on a double-layer LSTM. The following job is to provide pre-trained with formal and non-formal language corpus; pre-processing to overcome non-formal words is very challenging.</p>

Extensive residence in a second language environment modifies perceptual strategies for suprasegmental categorization.

Languages differ in the importance of acoustic dimensions for speech categorization. This poses a potential challenge for second language (L2) learners, and the extent to which adult L2 learners can acquire new perceptual strategies for speech categorization remains unclear. This study investigated the effects of extensive English L2 immersion on speech perception strategies and dimension-selective-attention ability in native Mandarin speakers. Experienced first language (L1) Mandarin speakers (length of U.K. residence > 3 years) demonstrated more native-like weighting of cues to L2 suprasegmental categorization relative to inexperienced Mandarin speakers (length of residence < 1 year), weighting duration more highly. However, both the experienced and the inexperienced Mandarin speakers continued to weight duration less highly and pitch more highly during musical beat categorization and struggled to ignore pitch and selectively attend to amplitude in speech, relative to native English speakers. These results suggest that adult L2 experience can lead to retuning of perceptual strategies in specific contexts, but global acoustic salience is more resistant to change. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Interpreting Convolutional Layers in DNN Model Based on Time–Frequency Representation of Emotional Speech

Abstract The paper describes the relations of speech signal representation in the layers of the convolutional neural network. Using activation maps determined by the Grad-CAM algorithm, energy distribution in the time–frequency space and their relationship with prosodic properties of the considered emotional utterances have been analysed. After preliminary experiments with the expressive speech classification task, we have selected the CQT-96 time–frequency representation. Also, we have used a custom CNN architecture with three convolutional layers in the main experimental phase of the study. Based on the performed analysis, we show the relationship between activation levels and changes in the voiced parts of the fundamental frequency trajectories. As a result, the relationships between the individual activation maps, energy distribution, and fundamental frequency trajectories for six emotional states were described. The results show that the convolutional neural network in the learning process uses similar fragments from time–frequency representation, which are also related to the prosodic properties of emotional speech utterances. We also analysed the relations of the obtained activation maps with time-domain envelopes. It allowed observing the importance of the speech signals energy in classifying individual emotional states. Finally, we compared the energy distribution of the CQT representation in relation to the regions’ energy overlapping with masks of individual emotional states. In the result, we obtained information on the variability of energy distributions in the selected signal representation speech for particular emotions.

On the Pragmatic Properties of Statements with an Offensive Nomination of a Person (Linguistic Expertise and Invective Functioning of Language).

The article is devoted to the description of the pragmatic properties of statements with an offensive nomination of a person. This problem is relevant in both applied and theoretical aspects. To date, the question of the nature of the described speech acts in semantic and pragmatic terms has not been resolved; in particular, the question of whether offensive speech acts are specific speech acts and, if they are, to which class or classes they should belong within the framework of speech act theory is still open. These questions are solved within the framework of the classification of speech acts by J. Searle and J. Austin. The article focuses on the illocutionary purpose and the nature of the perlocutionary effect of the analyzed statements. The explanatory possibilities of classification of illocutionary acts for describing the properties of these statements are considered. It has been established that the description of such statements is more in line with J. Austin's theory of speech acts, according to which the type of statements under study should be recognized as verdicts. The results obtained in the article are relevant for the production of forensic linguistic examinations within those categories of cases that are related to invective functioning of language.

Experimental Analysis on Performance of Speech Utterance recognition using AI Models

In Automated speech recognition of the system performance is crucial and important to satisfy multiple requirements of HMI and, more recently, even in IoT-related applications as well. Concurrently, there has been an increase in demand for detecting strong critical features derived from speech utterances. This paper presents a performance of the developed machine learning algorithms with respect to audio digit speech recognition and classification. The prepared dataset contains a free range of words (from 1 to 10) from speakers of different age groups. The Audacity software used for preprocessing the audio files that includes removal of noise included in the signal and trimming the silence on either side of the word utterance. audio signal sampled at fs = 48kHz.We have developed four AI Models to recognise the word utterances. Audio signals are processed separately and derived two unique feature sets that includes statistical features set and singular values by performing SVD related to word utterances. The cepstral values for each utterance are obtained from state-of-the-art MFCC. Variance-covariance matrix is calculated from the generated MFCC matrix. The diagonal values which form the variance are recorded and denoted as feature set-1 for the word utterance and inputted to the machine learning algorithms. Performance matrices of the developed models are recorded. To keep the computational bottleneck associated with the use of feature sets to minimum, dimensionality reduction is carried out by applying singular value decomposition to the extracted MFCC matrix. The derived set of singular values ​​considered as feature set-2 is used to train and test the developed AI models with a ratio of 70:30. We presented and discussed the performance and results produced by MLP, KNN, SVM, Random Forest algorithms. In comparison, MLP and Random Forest were found to show excellent performance on both feature sets with 100% training accuracy and 99% test accuracy.

Deep Random Forest and AraBert for Hate Speech Detection from Arabic Tweets

Nowadays, hate speech detection from Arabic tweets attracts the attention of many researchers. Numerous systems and techniques have been proposed to address this classification challenge. Nonetheless, three major limits persist: the use of deep learning models with an excess of hyperparameters, the reliance on hand-crafted features, and the requirement for a huge amount of training data to achieve satisfactory performance. In this study, we propose Contextual Deep Random Forest (CDRF), a hate speech detection approach that combines contextual embedding and Deep Random Forest. From the experimental findings, the Arabic contextual embedding model proves to be highly effective in hate speech detection, outperforming the static embedding models. Additionally, we prove that the proposed CDRF significantly enhances the performance of Arabic hate speech classification.

Speech Emotion Recognition using Extreme Machine Learning

Detecting Emotion from Spoken Words (SER) is the task of detecting the underlying emotion in spoken language. It is a challenging task, as emotions are subjective and highly contextual. Machine learning algorithms have been widely used for SER, and one such algorithm is the Gaussian Mixture Model (GMM) algorithm. The GMM algorithm is a statistical model that represents the probability distribution of a random variable as a sum of Gaussian distributions. It has been widely used for speech recognition and classification tasks. In this article, we offer a method for SER using Extreme Machine Learning (EML) with the GMM algorithm. EML is a type of machine learning that uses randomization to achieve high accuracy at a low computational cost. It has been effectively utilised in various classification tasks. For the planned approach includes two steps: feature extraction and emotion classification. Cepstral Coefficients of Melody Frequency (MFCCs) are used in order to extract features. MFCCs are commonly used for speech processing and represent the spectral envelope of the speech signal. The GMM algorithm is used for emotion classification. The input features are modelled as a mixture of Gaussians, and the emotion is classified based on the likelihood of the input features belonging to each Gaussian. Measurements were taken of the suggested method on the The Berlin Database of Emotional Speech (EMO-DB) and achieved an accuracy of 74.33%. In conclusion, the proposed approach to SER using EML and the GMM algorithm shows promising results. It is a computationally efficient and effective approach to SER and can be used in various applications, such as speech-based emotion detection for virtual assistants, call centre analytics, and emotional analysis in psychotherapy.

Категория прямоты в лексике и прагматике

The article deals with the linguistic and speech category of directness, which is dialectically connected with its opposite – the category of indirectness. Realizations of the category of directness are considered: firstly, in language vocabulary and idiomatics; secondly, in speech communication; thirdly, in a more general sense of understanding the features of the system of language and speech. Two aspects of using the concept of directness to characterize linguistic and communicative-speech phenomena are considered. On the one hand, the use of the concept of directness for this purpose is due to the semantic structure of lexemes directly / direct / directness, their direct and figurative (metaphor, metonymy) meanings, relations with opposite concepts (various depending on the meaning of “directness”). On the other hand, this is due to the character of natural human language, which also dialectically combines “directness” (of communication, communicative meanings) and “indirectness” (inaccuracy, asymmetry, etc.). In theoretical linguistics, for several centuries, these features of the nature of language have repeatedly become the object of reflection – from different points of view, in different concepts, under different names, while so far much more attention has been paid to indirectness than directness, which is shown by a review of modern linguistic literature, dedicated to the relevant features and units of linguistic and communicative speech phenomena. The article analyzes the contexts representing the semantic and pragmatic polysemy of directness in speech communication: situations that are comprehended as such in artistic dialogues (author’s speeches) (“He / she said directly” / “Say directly”); the main speech intentions of the speakers in these situations are revealed – recognition, request, consent and refusal, prediction, statement, promise.

Evaluating the Performance of wav2vec Embedding for Parkinson's Disease Detection

Abstract Speech is one of the most serious manifestations of Parkinson's disease (PD). Sophisticated language/speech models have already demonstrated impressive performance on a variety of tasks, including classification. By analysing large amounts of data from a given setting, these models can identify patterns that would be difficult for clinicians to detect. We focus on evaluating the performance of a large self-supervised speech representation model, wav2vec, for PD classification. Based on the computed wav2vec embedding for each available speech signal, we calculated two sets of 512 derived features, wav2vec-sum and wav2vec-mean. Unlike traditional signal processing methods, this approach can learn a suitable representation of the signal directly from the data without requiring manual or hand-crafted feature extraction. Using an ensemble random forest classifier, we evaluated the embedding-based features on three different healthy vs. PD datasets (participants rhythmically repeat syllables /pa/, Italian dataset and English dataset). The obtained results showed that the wav2vec signal representation was accurate, with a minimum area under the receiver operating characteristic curve (AUROC) of 0.77 for the /pa/ task and the best AUROC of 0.98 for the Italian speech classification. The findings highlight the potential of the generalisability of the wav2vec features and the performance of these features in the cross-database scenarios.

Emotion Detection via Voice and Speech Recognition

Emotion detection from voice signals is needed for human-computer interaction (HCI), which is a difficult challenge. In the literature on speech emotion recognition, various well known speech analysis and classification methods have been used to extract emotions from signals. Deep learning strategies have recently been proposed as a workable alternative to conventional methods and discussed. Several recent studies have employed these methods to identify speech-based emotions. The review examines the databases used, the emotions collected, and the contributions to speech emotion recognition. The Speech Emotion Recognition Project was created by the research team. It recognizes human speech emotions. The research team developed the project using Python 3.6. RAVDEESS dataset was also used since it contained eight distinct emotions expressed by all speakers. The RAVDESS dataset, Python programming languages, and Pycharm as an IDE were all used by the author team.

Real objects as a reason for mathematical reasoning – A comparison of different task settings

In this article, the goal is to describe students’ mathematical reasoning in the context of different settings of problem-solving tasks. The core of the tasks are real objects, which are presented to the students with the help of photos, a 3D model or in the environment itself. With reference to the experiential learning theory and relations to problem-solving and modelling, theoretical potentials for mathematical reasoning emerge. In a qualitative study with 19 secondary school students these are empirically tested. The evaluation of the video recordings of the students’ solution processes are coded with the help of qualitative content analysis, among others with references to problem-solving and linguistic categories of conclusive speech acts. The results show that mathematical reasoning can be observed especially in the work with photos and that the work with real objects generally evokes reasoning activities in the area of planning and exploration of strategies.

Analyzing Deixis of English Speech by Kim Namjoon (BTS) at the United Nations

Humans, as social beings, naturally interact to fulfill various life needs. This study aimed to analyze different deixis types in Kim Namjoon's speech and understand their meanings. The research employed Stephen C. Levinson's Theory and utilized a descriptive qualitative method with a content analysis approach. The findings revealed five deixis categories in Kim Namjoon's speech: personal, spatial, temporal, discourse, and social. These were distributed as follows: 129 (65.8%) personal deixis, 15 (7.7%) spatial deixis, 10 (5.1%) temporal deixis, 31 (15.8%) discourse deixis, and 11 (5.6%) social deixis. In total, 196 deixis instances were identified in Kim Namjoon's speech. His speech, titled "Speak Yourself," aimed to inspire young people to embrace self-love, discover their inner voices, and confidently express themselves to the world. The significance of this research lies in enhancing our understanding of deixis and its role as a linguistic resource, particularly in terms of usage and significance within utterances.

Exploring digital speech biomarkers of hypokinetic dysarthria in a multilingual cohort

Hypokinetic dysarthria, a motor speech disorder characterized by reduced movement and control in the speech-related muscles, is mostly associated with Parkinson’s disease. Acoustic speech features thus offer the potential for early digital biomarkers to diagnose and monitor the progression of this disease. However, the influence of language on the successful classification of healthy and dysarthric speech remains crucial. This paper explores the analysis of acoustic speech features, both established and newly proposed, in a multilingual context to support the diagnosis of PD. The study aims to identify language-independent and highly discriminative digital speech biomarkers using statistical analysis and machine learning techniques. The study analyzes thirty-three acoustic features extracted from Czech, American, Israeli, Columbian, and Italian PD patients, as well as healthy controls. The analysis employs correlation and statistical tests, descriptive statistics, and the XGBoost classifier. Feature importances and Shapley values are used to provide explanations for the classification results. The study reveals that the most discriminative features, with reduced language dependence, are those measuring the prominence of the second formant, monopitch, and the frequency of pauses during text reading. Classification accuracies range from 67% to 85%, depending on the language. This paper introduces the concept of language robustness as a desirable quality in digital speech biomarkers, ensuring consistent behaviour across languages. By leveraging this concept and employing additional metrics, the study proposes several language-independent digital speech biomarkers with high discrimination power for diagnosing PD.

Integration of MFCC Extraction and LSTM Algorithm on PYNQ-Z2 for Enhanced Audio Analysis

The need for Speech Emotion Recognition (SER) is growing since researchers have found it difficult to interpret human emotions from speech data. SER is very interesting yet very challenging task of human-computer interaction (HCI). The SER application can be benefitted depending on the type of feature extraction technique and model used for classification. Deep Learning has made a great impact in the field of audio, image, video, EEG and ECG classification. The speech signal characteristics and classification model affect how well the SER application performs. The paper briefs about deploying Deep Learning Algorithm on FPGA based board i.e., PYNQ-Z2. MFCC feature extraction technique and LSTM model used for classification of human emotion is implemented on the board. Emotion can be predicted using led buttons on the board.