Context Of Speech Research Articles

Reduplication; Noun Formation Pattern in Ternate Language a Morphophonemic Study

The Ternate language is one of the non-Austronesian languages which has several unique characteristics, including the form of prefixes and possessive verbs that can only be differentiated based on the context of speech and the absence of inflexion. It will produce or find a pattern of rules from the formation of nouns in the Ternate language. Data were analyzed morphophonemically using structural theory to find out the forms of nouns in Ternate and the process of their formation The main aim of this research is to find rules for noun formation, and patterns in the Ternate language. The method in this research is descriptive qualitative with observation and interview data collection techniques as well as literature study as data sources. Meanwhile, data analysis was carried out through the identification and classification stages as well as analysis of the formation process as nouns. In conclusion that nouns are formed from verb and adjective classes by repeating and adding phonemes; these nouns have the meanings of actor, tool, place/locative, possession, rather, and abstract.

Graph Neural Network-Based Speech Emotion Recognition: A Fusion of Skip Graph Convolutional Networks and Graph Attention Networks

In speech emotion recognition (SER), our research addresses the critical challenges of capturing and evaluating node information and their complex interrelationships within speech data. We introduce Skip Graph Convolutional and Graph Attention Network (SkipGCNGAT), an innovative model that combines the strengths of skip graph convolutional networks (SkipGCNs) and graph attention networks (GATs) to address these challenges. SkipGCN incorporates skip connections, enhancing the flow of information across the network and mitigating issues such as vanishing gradients, while also facilitating deeper representation learning. Meanwhile, the GAT in the model assigns dynamic attention weights to neighboring nodes, allowing SkipGCNGAT to focus on both the most relevant local and global interactions within the speech data. This enables the model to capture subtle and complex dependencies between speech segments, thus facilitating a more accurate interpretation of emotional content. It overcomes the limitations of previous single-layer graph models, which were unable to effectively represent these intricate relationships across time and in different speech contexts. Additionally, by introducing a pre-pooling SkipGCN combination technique, we further enhance the ability of the model to integrate multi-layer information before pooling, improving its capacity to capture both spatial and temporal features in speech. Furthermore, we rigorously evaluated SkipGCNGAT on the IEMOCAP and MSP-IMPROV datasets, two benchmark datasets in SER. The results demonstrated that SkipGCNGAT consistently achieved state-of-the-art performance. These findings highlight the effectiveness of the proposed model in accurately recognizing emotions in speech, offering valuable insights and a solid foundation for future research on capturing complex relationships within speech signals for emotion recognition.

Vertical larynx actions and intergestural timing stability in Hausa ejectives and implosives.

The current project undertakes a kinematic examination of vertical larynx actions and intergestural timing stability within multi-gesture complex segments such as ejectives and implosives that may possess specific temporal goals critical to their articulatory realization. Using real-time MRI (rtMRI) speech production data from Hausa non-pulmonic and pulmonic consonants, this study illuminates speech timing between oral constriction and vertical larynx actions within segments and the role this intergestural timing plays in realizing phonological contrasts and processes in varying prosodic contexts. Results suggest that vertical larynx actions have greater magnitude in the production of ejectives compared to their pulmonic counterparts, but implosives and pulmonic consonants are differentiated not by vertical larynx magnitude but by the intergestural timing patterns between their oral and vertical larynx gestures. Moreover, intergestural timing stability/variability between oral and non-oral (vertical larynx) actions differ among ejectives, implosives, and pulmonic consonants, with ejectives having the most stable temporal lags, followed by implosives and pulmonic consonants, respectively. Lastly, the findings show how contrastive linguistic 'molecules'- here, segment-sized phonological complexes with multiple gestures- interact with phrasal context in speech in such a way that it variably shapes temporal organization between participating gestures as well as respecting stability in relative timing between such gestures comprising a segment.

Contrastive Learning based Speech Spoofing Detection for Multimedia Security in Edge Intelligence

Artificial intelligence (AI) empowered edge computing has given rise to a new paradigm and effectively facilitated the promotion and development of multimedia applications. The speech assistant is one of the significant services provided by multimedia applications, which aims to offer intelligent interactive experiences between humans and machines. However, malicious attackers may exploit spoofed speeches to deceive speech assistants, posing great challenges to the security of multimedia applications. The limited resources of multimedia terminal devices hinder their ability to effectively load speech spoofing detection models. Furthermore, processing and analyzing speech in the cloud can result in poor real-time performance and potential privacy risks. Existing speech spoofing detection methods rely heavily on annotated data and exhibit poor generalization capabilities for unseen spoofed speeches. To address these challenges, this paper first proposes the Coordinate Attention Network (CA2Net) that consists of coordinate attention blocks and Res2Net blocks. CA2Net can simultaneously extract temporal and spectral speech feature information and represent multi-scale speech features at a granularity level. Besides, a contrastive learning-based speech spoofing detection framework named GEMINI is proposed. GEMINI can be effectively deployed on edge nodes and autonomously learn speech features with strong generalization capabilities. GEMINI first performs data augmentation on speech signals and extracts conventional acoustic features to enhance the feature robustness. Subsequently, GEMINI utilizes the proposed CA2Net to further explore the discriminative speech features. Then, a tensor-based multi-attention comparison model is employed to maximize the consistency between speech contexts. GEMINI continuously updates CA2Net with contrastive learning, which enables CA2Net to effectively represent speech signals and accurately detect spoofed speeches. Extensive experiments on the ASVspoof2019 dataset show that GEMINI reduces the Equal Error Rate and tandem Detection Cost Function by up to 96.75% and 96.35% in the physical access scenario, and by up to 86.62% and 87.71% in the logical access scenario compared to peer methods.

Sarcasm Detection Based on Sentiment Analysis of Audio Corpus Using Deep Learning

With the rapid progress in digitalization, hundreds of services and applications have begun to depend on human-machine communication, primarily voice-based. As technology advances, it has become increasingly imperative to develop systems that can discern sophisticated emotions from humans, like sarcasm. Despite research that has been conducted on the detection and analysis of speech signals to try and understand emotion, the detection of sarcasm, which is often not overtly expressed, is quite far from something that has received the attention it deserves in recent years. It plays a very important role in any utterance, searching to identify the psychology, mood, or even health behind it. Hence, it does give interactions with humans a more human-like flavor while raising the feeling of understanding human emotions. This article tries to identify sarcasm in speech using audio data derived from real-world, spontaneous, monolingual corpora. In this classification process, a deep learning classifier known as CNN-LSTM model is used. Results of the study showed that a robust combination between feature extraction through convolutional layers and sequential learning through LSTM layers can identify intricate speech patterns in sarcasm. Experimented and validated in terms of performance, this model shows the model to be very good at discriminating between sarcastic and no sarcastic speech, thus promoting it for more extensive use in various applications related to sentiment analysis and in human-computer interaction applications. The results show that this system provides far much closer approximations to human interaction styles, but its impact would extend into a wide area from customer services, monitoring mental health, and even AI-driven communication systems. It is a monolingual and spontaneous corpus that will open the gates for further work and development down the line and possibly extend to multilingual and more diversified speech contexts, thus fine-tuning accuracy in practical scenarios of sarcasm detection.

Characteristics of Nasal Coarticulation by Nasality Visualization System in Children with Speech Sound Disorders

Objectives: In this study, we analyzed the nasal coarticulation characteristics of children with and without speech sound disorders by comparing nasalance scores according to speech contexts. Methods: The subjects of this study were 30 children, 15 children with speech sound disorder (SSD) and 15 typically developing (TD) children, aged 4 to 6 years old. Subjects were asked to speak stimuli in different speech contexts-low vs. high vowels, nasal consonant+vowel (NV) vs. vowel+nasal consonant (VN) syllables, words vs. nonwords - and nasalance scores were measured using the Nasality Visualization System (NVS) on their speech samples. Results: First, both groups showed significantly higher naslance scores for high vowels compared to low vowels, with a significant between-group difference in high vowel. Second, both groups showed significantly higher nasalance scores for VN syllables than for NV syllables, with no between-group difference. Third, both groups showed significantly lower nasalance scores in nonwords compared to words. While there was no group difference in the words, the nasalance scores of the SSD group was lower in the nonwords, which was significantly different from that of the TD groups. Conclusion: These results suggest that the SSD group exhibits somewhat different nasal characteristics than the TD group, and furthermore, that SSD children articulate phoneme sequences more segmentally in unlearned nonword contexts.

A Corpus Pragmatics Approach to Active Listenership in Conversations in British English: Contextualised Function-To-Form

Active Listenership are the features that refer to the linguistic behaviour of the listener in casual conversations. The listener continuously utters Listener Response Tokens, Sentence-Completions and Which-Comment-Clauses to signal emotional and social involvement in the discourse. Particularly in the field of corpus pragmatics, Active Listenership has found attention over the past two decades. In this paper, I introduce a novel context-driven function-to-form corpus pragmatics annotation scheme. The scheme is applied to a down-sampled version of the spoken BNC2014, and subsequently evaluated in terms of inter-rater plausibility. Then, I present the qualitative findings on how frequent the features of Active Listenership are in the corpus in general. Subsequently, I analyse the contextual units (as per my annotation scheme) to show which feature of Active Listenership is most likely to occur in a specific speech context. I finish this paper with suggestions for future research and a call to include more features of conversational English into an elaboration of the annotation scheme. My findings can be applied to general pragmatics research and English Language Teaching.

THE ANALYSIS OF THE SPEECH “WHAT ISLAM REALLY SAYS ABOUT WOMEN” BY ALAA MURABIT BASED ON THE PERSPECTIVE OF LINGUISTICS BEHAVIORISM

This study aims to explain the analysis of the meaning of a speech context delivered by Alaa Murabit in the speech "What Islam Really says about Women" on the TED YouTube channel (July 21, 2015) in order to help the audience in interpreting the context of meaning so as not to cause misunderstandings. This study uses the theory of Linguistic Behaviorism pioneered by Bloomfield (2013). The method used in analyzing data is a qualitative descriptive method by selecting some data in a speech that contains a mismatch of context with stimulus. The result of this study, Alaa Murabit, used two main stimuli: family background and religion, so that it gave rise to a response in the form of a parable sentence that has many interpretations.

العلاقة بين استيعاب المفردات وتحصيل الطالبات التعليمي في مهارة الكلام للصف الأول من المتوسط بمعهد عبد الله بن مسعود أساهان

Speaking skill is a productive skill that involves the process of learning various aspects of the Arabic language. To acquire this skill, one needs to understand grammar, morphology, vocabulary, style, and meanings. Proficiency in speaking Arabic requires comprehension of the elements and rules of the language, including vocabulary acquisition, sentence structure, speech context, and the ability to understand the speaker's language. Vocabulary is a very important linguistic element that must be mastered, used in both spoken and written language. This issue leads to weaknesses in vocabulary comprehension and the presence of excuses for not speaking Arabic in certain situations. The methodology used in this research is a quantitative correlational method, and the data analysis technique employed is the statistical method using Pearson's product-moment correlation coefficient. The research results indicate that there is a moderate positive correlation between vocabulary comprehension and students' academic achievement in speaking skills for the first-grade students at the Abdullah bin Masoud Institute in Asahan, with a correlation coefficient value of 0.474.

A Pragmatic Study: Investigating The Meaning of Social Deixis in Spoken Discourse

This research aims to investigate the types of social deixis and analyze their social meaning in a speech context. This research used a qualitative method. The participant of this research is Retno Marsudi’s utterances, who the Ministry of Foreign Affairs of the Republic of Indonesia. The data was collected from YouTube and a transcript from the Ministry of Foreign Affairs of the Republic of Indonesia’s website. The data collected was analyzed using qualitative analysis, where the data was divided into five types of deixis and then narrowed down into two types of social deixis. After the data narrowed down, the researchers analyzed the meaning of the social deixis based on contextual and sociocultural theory. The results of the analysis conclude that there are two types of social deixis: 1) relational social deixis and 2) place social deixis with three data of relational and one data of place social deixis. The social meaning of social deixis imply profesionalism, social status, familiarity, and formality.

Strategy for developing a speech recognition model specialized for patients with depression or Parkinson's disease with small size speech database.

Most of speech recognition models currently in use have been dealt with speech of normal people. The speech recognition rate for patients with depression or Parkinson's disease (PD) who show differences in speech characteristics compared to normal subjects is lower than that of normal subjects. This study explores the model to enhance accuracy of speech recognition for individuals who have depression or PD, aiming to provide them more accurate service. In this study, considering the speech features of patients with depression or PD, we designed a model with the assumption that understanding the overall meaning and context of speech through the utilization of global information, rather than local information, is more effective in enhancing recognition accuracy. We propose the m-Globalformer, a model based on the Globalformer architecture that combines the squeeze-and-excitation (SE) module with the Transformer. The m-Globalformer enhances the utilization of global information by modifying the base SE module. The model employs pre-training and fine-tuning strategies, considering the limited speech data of the patients. In the initial training phase, a large-scale normal speech dataset was used, followed by fine-tuning the model with a small-scale dataset of depression or PD patients. The m-Globalformer demonstrated superior performance in our experiments, achieved character error rates (CER) of 11.28% for depression and 19.67% for PD.

An Ideational Metafunction Analysis of Indonesian Presidential Candidate Speeches

The problem in this research is what the discourse context and inferences are about the speeches of the Indonesian presidential candidates in 2024. The focus is on discussing Prabowo-Gibran's expressions in their orations. The aim of the research is to describe the context and inference of discourse Prabowo Subianto's speech on electronic media TEMPO.CO and CNBC Indonesia. The type of research is qualitative research using a descriptive approach. The data sources in this research were taken from electronic media Tempo.CO and CNBC Indonesia.The data analysis technique uses content analysis. The results of context research and discourse inference in Prabowo Subianto's speech are that Prabowo Subianto's speech as a whole contains the context and inference of campaigning, enthusiasm, readiness and optimism of the presidential candidate pair. and representatives, the winning team, supporters, and especially the entire Gerindra Party family, with persuasive speeches for get more support so you can achieve victory. Prabowo's expressions regarding his work program are still being monitored and are being questioned by the public.

Indirect reciprocity in Japanese

I shall discuss a special usage of the Japanese reciprocal expression otagai. In this usage, otagai does not occur as the object of a transitive verb and does not induce a reciprocal interpretation. Rather, it seems to modify the nominal in the subject position. I argue that otagai in such examples expresses reciprocity only indirectly in that the relation is not expressed overtly in the sentence in question. The relation is a psychological one in that the sentence as a whole says that each participant of the speech context knows that the other participant(s) have the property given by the overt predicate in the sentence. This, then, entails that each of them has this same property since know is a factive predicate. Since each participant has to be in a position to assess what the other member(s) are thinking of, the group of people in question must know each other well. This means that the nature of reciprocity is essentially the same in English and Japanese except that otagai could introduce a covert psychological relation to satisfy the reciprocity requirement. The article also discusses the similarity between the indirect use of otagai and the indirect passive in Japanese.

THE PHENOMENON OF SPEECH ACTS IN THE SUNDANESE NOVEL ISTRI-ISTRI NU DIPIHORMAT BY MEMEN DURACHMAN

This research is motivated by the importance of understanding the context of speech and speech acts to avoid misunderstanding in understanding speech. The source of the research data is the Sundanese novel Wife-wife nu Dipihormat by Memen Durachman because Sundanese novels have many messages about life and are one of the efforts to preserve the Sundanese language. The purpose of this research is to find out the speech acts in the dialogue of Memen Durachman's novel Wife-Wife nu Dipihormat through Austin's theory. The method used is the descriptive analytical method using data collection techniques in the form of literature review and data analysis. The results of the study show that of the 385 dialogues in the novel, the forms of speech acts found in this novel are locations with a total of 202 utterances, illocutionary acts with a total of 193 utterances, and perlocutions with a total of 228 utterances. The results of this study can be used as an alternative in paguneman learning that is by KIKD, so that it can be an effort to preserve Sundanese.

Vowel perception research from formant thresholds to sentence intelligibility

Historically, research on the contribution of vowels to speech understanding lagged that of consonants. Speech synthesis techniques were then developed that established that the primary acoustic features of vowels are formant frequency, fundamental frequency, speech dynamics and naturalness. For speech perception research, precise control of the features in vowel stimuli was required. Starting in the 1980s, the Klatt formant synthesizer was the first important tool, and by 2000 Kawahara’s STRAIGHT synthesizer generated nearly natural speech. As a baseline for vowel perception, my research sought to determine psychophysical thresholds for F1 and F2 under ideal conditions. This talk reports contributions from my vowel perception studies on three questions. First, how do formant thresholds change with speech context (isolated vowels up to sentences), across age and with hearing impairment? Second, do vowels or consonants contribute more to intelligibility in noise-interrupted sentences? Third, given formant dynamics, how is intelligibility affected as consonant-vowel boundary conditions are manipulated across age and hearing impairment? Significant results include: (1) Vowels carry more information about sentence intelligibility than consonants for both young and older listeners; (2) Even though older listeners’ performance is reduced compared to young, hearing impairment has a greater negative impact than age-related cognitive decline.

Influence of social and semantic context in processing speech in noise

Social interactions occupy a substantial part of our life, and listening to others’ interactions is critical in understanding our social world. Although the role of semantics in speech comprehension has been studied, the role of social context, and its interaction with semantics, remain unknown. We conducted a series of four perceptual experiments to better understand the processing of multiple-speaker conversations from a third-person viewpoint, manipulating the social and semantic context of a conversation. We used a stimulus set consisting of two-speaker dialogues or one-speaker monologues (factor: social context) arranged in intact or sentence-scrambled order (factor: semantic context). Each stimuli comprised five sentences, with the fifth sentence embedded in multi-talker babbling noise. This fifth sentence was subsequently repeated without noise, with a single word altered or unchanged. Stimuli were presented to healthy young adults, asked whether the repeated sentence was same as or different from previous in-noise sentence. We found significant effects for both social and semantic contexts when processing a conversation. Our findings highlight that both semantic and social aspects of a conversation can modulate the processing of conversations. These results raise new questions regarding predictive or other mechanisms that may be at play when perceiving speech in social contexts.

Citra Perempuan dalam Novel Perempuan Yang Menunggu Di Lorong Menuju Laut karya Dian Purnomo

This study aims to describe the image of the main character of women contained in the novel Perempuan yang Menunggu di Lorong Menuju Laut. The type of research used is literary research with descriptive method. The data source is the novel Perempuan yang Menunggu di Lorong Menuju Laut published in 2023 by Dian Purnomo. The data collection technique in this research is a literature study, namely (1) understanding the content of the story and the meaning of the novel under study, (2) conducting literature studies, namely reading and recording things related to research objectives (3) collecting related to the formulation of research problems into tables. The data analysis techniques in this research are: (1) classifying data regarding the form of women's image contained in the novel (2) describing and analyzing the context of speech that describes the image of women in the novel under study (3) interpreting data, (4) drawing conclusions and reporting the results of data analysis. The results of this study explain that the image of women contained in the novel Perempuan yang Menunggu di Lorong Menuju Laut includes women's self-image and women's social image. (a) Women's self-image consists of women's physical image and women's psychological image. (b) The social image of women includes: the role of women in the family and society. The image of women formed in the novel is progressive because it does not follow the conventions of the ideal image of women according to patriarchal ideology.

Short- and long-term influences of repeated speech examples on segmentation in an unfamiliar language analog.

Because segments in fluent speech (e.g., words and phrases) are not reliably separated by pauses, a key task when listening to an unfamiliar language is to parse the incoming speech into segments to be learned. We aim to understand how working memory contributes to that segmentation learning. One cue to segmentation occurs when a segment is repeated in varying contexts. Cowan (Acta Psychologica, 77(2), 121-135, 1991) explored a language analog to study how segmentation occurs during immediate memory of speech, and found effects of segment presentation frequency, stimulus length, and serial position. Here we ask whether those effects extend from working memory to long-term memory. Overlapping segments were presented (e.g., mah bar slo mi and slo mi geh), varying numbers of times (presentation frequencies) to determine how varying the schedule of repetition patterns would affect perception of a unified test pattern formed from the two of them (e.g., mah bar slo mi geh). These constructions provide an analogy to how segments occur in varying contexts in speech. Participants were to indicate where they heard the boundaries between syllables. In immediate memory, the perceived boundaries more often reflected the most frequently presented pattern, and often reflected both pattern boundaries (in this example, mah bar / slo mi / geh). In a long-term memory follow-up, however, the original presentation frequencies only mattered for certain short test pattern configurations. We suggest that working memory for speech, without a semantic component, may be an incomplete basis to learn longer segments in an unfamiliar language.

A stylistic analysis of the language of crisis (Covid-19): A transitivity and modality-based study

Speech, simply, is a kind of communication used to convey a speaker's intentions and ideas. The purpose of this study is to evaluate and interpret transitivity and modality as well as their use in Tedros Adhanom Ghebreyesus' Speeches on COVID-19. The data consists of transcripts of two speeches presented at the COVID-19 media briefings on March 11, 2020, and April 1, 2021, which are published on the (World Health Organization website) (www.who.int). The transcripts are reviewed and examined in terms of Halliday's (1994) 'Transitivity theory, as well as Lock's (1996) 'Modality theory'. The findings show that the speeches employed rational, material, mental, behavioral, and linguistic transitivity processes, as well as obligation, potentiality, ability, inclination, usuality, and probability modality. The usage of transitivity and modality, with reference to the context of speeches, reveals different interpretations of meaning. Furthermore, this study contributes and adds efficient methods and good practices to health socialization throughout the pandemic, which has a significant impact on the public's understanding of how to correctly handle COVID-19.

Socio-Pragmatic Functions of Greeting Expressions in Teaching Turkish as a Foreign Language Textbooks

Greetings serve as a fundamental aspect of human communication, playing a pivotal role in establishing and maintaining social relationships. This research investigates the socio-pragmatic functions of greetings reflected in teaching Turkish as a Foreign Language (TFL) textbooks, aiming to shed light on how the intricate interplay between language, culture, and social interaction is reflected in teaching materials. With this aim, greeting exchanges from five different series of TFL textbooks were collected and analyzed. In the quantitative analyses, the frequency of each form and strategy of greetings were determined in the data. In the qualitative analyses, the classification and pragmatic functions of the greetings were investigated by analyzing different variables such as the gender of the speakers, time relations, familiarity between the speakers, formality/speaker roles, the speech context, and the photographic details accompanying greetings. The data was also analyzed according to Ebsworth et al.’s (1995) categorization of American greetings. The Common European Framework of Reference for Languages (CEFR) levels of the textbooks under focus were considered in the analyses. The findings showed that greeting forms have mostly been reflected in the A1 level according to the CEFR criteria and the most frequently reflected form of greeting in Turkish is merhaba (Ar. marhaba/Eng. hello) in the current data. In terms of the socio-linguistic/pragmatic and non-verbal aspects regarding greetings and the classification and the socio-pragmatic functions of greetings in TFL textbooks, various reflections of the role of greetings in shaping social interaction in Turkish culture were also displayed.