Prosody Features Research Articles

A Systematic Review and Bayesian Meta-Analysis of Acoustic Measures of Prosody in Parkinson's Disease.

Linguistic prosody is affected in Parkinson's disease (PD), which implicates the basal ganglia's role in the production of prosody. However, there is no recent systematic synthesis of the available acoustic evidence of prosodic impairment in PD. This study aimed to identify the acoustic features of linguistic prosody that are consistently affected in PD. The authors systematically reviewed articles that reported acoustic features of prosodic production in PD. Articles focused on fundamental frequency (F0) and its variability, intensity and its variability, speech and articulation rate, and pause duration and ratio. From a total of 648 records identified, 36 met criteria for inclusion and exclusion. For each acoustic measurement and task, data from people with PD (PwPD) were compared with those from controls to extract effect sizes. Pooled effect sizes were estimated using robust Bayesian hierarchical regression models. PD was associated with decreased F0 variability and increased pause duration. There was limited evidence of reduced intensity variability and speech rate in PwPD. No evidence was found to suggest that PD affects articulation rate or pause ratio. The primary acoustic parameters of prosody affected by PD are F0 variability and pause duration. The identification of these acoustic parameters has important clinical implications for the selection of PD management strategies. The association of F0 variability and pause duration with PD suggests that the neural circuits controlling these parameters are at least partly shared and might include the basal ganglia. While the current study focused on the phonetic realization of prosodic cues, future studies should examine whether and how PD affects prosody at higher levels of processing. https://doi.org/10.23641/asha.25892923.

L1–L2 Influence in Intonation: A Case of Russophone Immigrants in Brazil

This paper is devoted to the features of sentence prosody (intonation) in Brazilian Portuguese spoken by immigrants whose first language is Russian, and explores the consequences that L1–L2 influence in intonation may have for communication. The study addressed four research questions: (1) Do Brazilian Portuguese L2 speakers with Russian L1 always succeed in producing the correct utterance type? (2) Can L1–L2 influence lead to misunderstanding of connotations? (3) Is it possible that sometimes L1–L2 influence leads to being perceived as too emotional or not emotional enough? (4) Can L1–L2 influence in intonation be a significant factor in the perception of accent? In a perceptual experiment, productions of four target utterances in Brazilian Portuguese by Russian L1 and Brazilian Portuguese L1 speakers were evaluated by 124 Brazilian listeners in terms of sentence type, possible connotations, accent and arousal. The target utterances included three questions of different types and an exclamation. The findings revealed that the speaker’s L1 influenced the perception of prosodic meanings by Brazilian listeners. In some cases, interference from Russian melodic contours caused the incorrect identification of the sentence type in Brazilian Portuguese. However, even when sentence type was perceived correctly, differences could be found regarding the perception of arousal or accent.

Emotional Intelligence in Text-To-Speech Synthesis in Pali Language Using Fuzzy Logic

The field of emotional text-to-speech (TTS) synthesis is making swift progress within the realm of artificial intelligence, holding immense promise to transform our interaction with technology. By using advanced algorithms to analyze and understand the emotional content of text, these systems are able to produce spoken language that accurately conveys the intended emotional tone of the message. Despite the existence of several Text-To-Speech systems across various languages, Pali language is yet to have its own. As a result, we have taken the initiative to create a Text-To-Speech synthesizer exclusively for Pali. Our system offers an end-to-end solution for emotional speech synthesis via Text-To-Speech. We address the problem by incorporating disentangled, well-grained prosody features with global, sentence-level emotion implanting. These well-grained features learn to denote local prosodic differences disentangled from the speaker, tone, and worldwide emotion label. Prosody is usually modeled by rules, so we have implemented the fuzzy logic system to develop a controller for the prosody of Pali speech. The fuzzy controller handles different linguistic parameters in three types of sentences: interrogative, exclamatory, and declarative. The final system produces comprehensible speech that mimics the appropriate intonation for every type of sentence. In this paper, we introduce and outline the application of a fuzzy paradigm to incorporate a Text-To-Speech system for the Pali language while preserving a rule-based Concatenative synthesizer. In the outline of classic Concatenative TTS systems, we recommend a new method in order to increase Concatenative unit selection computation, directed at increasing synthetic speech perceptual superiority. In order to tackle the problem of phonemes that are prone to multiple descriptions in rule-based speech synthesis, the proposed solution involves a fuzzy system. In the introductory section, we offer a concise description of the current context surrounding the challenge of emotional speech synthesis. The second section of this paper outlines the notable advancements made in emotional speech synthesis, acknowledging the contributions of various researchers in this field. The third section delves into the technical details of implementing a fuzzy system The last section of the paper presents the main conclusions and future research scope.

Machine Learning Based Speech Emotion Recognition System

In the last decade, there has been significant research into Automatic Speech Emotion Recognition (SER). The primary goal of SER is to improve human-machine interfaces. It can also monitor someone's psychological state for lie detection applications. Recently, speech emotion recognition has found uses in medicine and forensics. This paper recognizes 7 emotions using pitch and prosody features. The majority of speech features used here are in the time domain. A Support Vector Machine (SVM) classifier categorizes the emotions. The Berlin emotional database was used for this task. A good recognition rate of 81% was achieved. The reference paper for this work recognized 4 emotions and obtained a 94.2% recognition rate. However, the reference paper used a more complex hybrid classifier, while this work focuses on recognizing more emotions with a simpler model. . KeyWords: Blindness, Smart Stick, BlinDar, GPS, ESP8266, Internet of Things, RF Tx/Rx, MQ2.

A Linguocognitive approach to the analysis of the interpreter’s language personality in an interpreting situation

The present article is devoted to the problem of applying a linguocognitive approach to the analysis of the linguistic personality of an interpreter/conference interpreter. The use of the linguocognitive approach seems to the author to be the most promising direction in view of the possibility of applying a comprehensive analysis of the interpreter’s verbal and non-verbal behavior. The conducted analysis − the study of the functional side of the linguistic personality at the moment of interpretation − contributes to the progress in the field of the national cognitive translation studies.The research aims to analyze the audiovisual series of simultaneous interpretations, which leads to the use of modern research methods in the analysis of verbal markers and the “unnoticed background”, including, on the one hand, the discursive features of linguistic personality in various sections of the language, and on the other hand, − intertextuality and creation of new meanings. The relevance of the linguocognitive approach in linguopersonology is due to the insufficiently studied mechanisms of comprehensive analysis of linguistic personality in general, as well as a rather limited number of studies of this kind.The author presents her view on the possibilities of applying linguocognitive analysis for a reliable and verifiable results of the interview genre research. The article describes the complexity and multi-dimensionality of the genre under study, reveals the destabilizing factors in the performance of interpretation that affect the manifestation of a linguistic personality, provides criteria for evaluating sounding speech, and the extent of its influence on the representation of linguistic personality, and, consequently, the success of the interpretation.The proposed approach to the study of the representation of the linguistic personality of an interpreter allows for linguistic and extralinguistic analysis, to study the verbal and nonverbal behavior of speakers, to assess the quality of translation, typologize translation errors, identify the features of prosody and non-verbal behaviour. In addition, the author introduces the term “an interpreting situation” in relation to the context of the study, describes the stages and the parameters of the source text analysis (translation degree) and destabilizing factors that affect the results of the study. The experimental study confirmed the prospects for the application of the linguocognitive approach; the representation of the interpreter/conference interpreter in the genre of television interview is marked by a special typical variety of text: a combination of journalistic and colloquial styles, the use of elliptical constructions, modality, syntactic and lexical repetitions.

Analysis of Speech Prosody Characteristics of Teachers

During the teaching process, the prosodic features of a teachers speech can influence students auditory perception of the teachers speech and, subsequently, affect students enthusiasm, concentration, and comprehension of the lesson content. This study aims to analyze the differences in prosodic features, including pitch, intensity, pauses, and speech rate, among speech samples from different categories of teacher instructional videos. The research algorithm is implemented in Python to calculate prosodic feature values for speech segments. Comparative data analysis revealed that, in comparison to negative teacher instructional video speech samples, positive teacher instructional video speech samples exhibit significantly higher average fundamental frequencies (pitch) and more noticeable variations in speech rate rhythm.

The diagnostic utility of picture description task in english, chinese and italian speaking individuals with primary progressive aphasia

AbstractBackgroundPrimary progressive aphasia (PPA) is a language‐predominant dementia syndrome (Mesulam et al.., 201) that impacts speakers of all languages. Despite there are more than 7,000 living languages, the diagnostic model is mainly tailored for English‐language speakers. Cross‐linguistic comparisons are called for, especially considering the heterogeneities of linguistic features in the different languages (Blasi et al., 2022). We intend to study the speech and language markers of English‐, Mandarin‐, Cantonese‐ and Italian‐speaking individuals with PPA when completing verbal picture description test. The goal is to (1) characterize the speech profiles of semantic(sv), logopenic(lv), nonfluent/agrammatic(nfv) PPA for each specific language, identifying key linguistic markers for the diagnosis; (2) identify similarities/differences in terms of markers across languages.MethodWe collected the oral picture description, based on the PicNic Scene from WAB battery (Schewan & Kertesz, 1980), of 30 English‐, 30 Chinese‐ (Mandarin and Cantonese), and 30 Italian‐ speaking PPA patients (equally distributed across the three variants) with 45 matched healthy controls (HC). Collected speech samples underwent CLAN and Whisper software analysis to characterize informativeness, lexico‐semantic, morpho‐syntactic, phonological and prosody features. We standardized PPA data relatively to their respective. Differences between PPA variants and with HC for the different features were only carried out for the Italian group, using non parametric tests. Performances across different language groups will be investigated as well.ResultAnalysis on Italian sample revealed that mean length of utterances, number of empty, filled pauses, abandoned words, and words repetition significantly distinguished PPA from HC. svPPA produced more irrelevant words and adverbs than other PPA groups. nfvPPA produced more sentences without verbs compared to HC and PPA. lvPPA produced more abandoned words than other PPA. svPPA and lvPPA produced less nouns and noun‐verbs ratio compared to HC and nfvPPA, meanwhile lvPPA and nfvPPA produced less words, open class words and more determiners‐noun ratio compared to HC. svPPA and nfvPPA showed reduced idea density compared to HC.ConclusionThose results are consistent with previous literature on PPA oral production. However, future comparisons across languages are extremely important and needed to ensure equitable assessment and minimize disparities globally.

A Review of Research on the Chinese EFL Learners’ Production of Linguistic Prosody in Turn Organization

Prosody features play crucial roles in the management and organization of conversations, among which turn-taking plays crucial roles in conversation organization. The appropriate use of prosodic features is an indispensable part of conversation strategies or skills, but the interaction between linguistic prosody and turn-taking is difficult to be acquired for EFL learners. This paper reviews the theoretical and empirical studies of interrelation between prosody and turn-taking, and the EFL learners’ acquisition of prosody in conversation organization in order to supply references for future studies in the similar fields.

Cross Corpus Speech Emotion Recognition using transfer learning and attention-based fusion of Wav2Vec2 and prosody features

Speech Emotion Recognition (SER) performance degrades when their training and test conditions or corpora differ. Cross-corpus SER (CCSER) is a research branch that discusses adapting an SER system to identify speech emotions on a corpus that has different recording conditions or language from the training corpus. For CCSER, adaption can be performed in the feature extraction module or emotion classifier, which are the two main components of the SER system. In this paper, we propose AFTL method (attention-based feature fusion along with transfer learning), including methods in both feature extraction and classification for CCSER. In the feature extraction part, we use Wav2Vec 2.0 transformer blocks and prosody features, and we propose an attention method for fusing them. In the classifier part, we use transfer learning for transferring the knowledge of a model trained on source emotional speech corpus to recognize emotions on a target corpus. We performed experiments on numerous speech emotional datasets as target corpora, where we used IEMOCAP as the source corpus. For instance, we achieve 92.45% accuracy on the EmoDB dataset, where we only use 20% of speakers for adapting the source model. In addition, for other target corpora, we obtained admissible results.

Automatic speaker verification system for dysarthric speakers using prosodic features and out-of-domain data augmentation

A communication disorder is an impairment of a person’s ability to talk or communicate appropriately. Dysarthria is a common neuro-motor speech communication disorder that can be caused by neurological damage. Dysarthria may affect the articulation, phonation, and prosody of a speaker. Dysarthria patients have poor neuromotor coordination and other physical impairments, making it difficult to utilize an interactive keyboard or other user interfaces. The ASV system can make biometric applications more accessible to dysarthric speakers by eliminating the need for them to remember cumbersome and unique authentication numbers and passwords. In this paper, we presented a study on developing an automatic speaker verification (ASV) system for dysarthria patients with varying speech intelligibility to assist them in remote access control and voice-based biometric applications. In the initial part of our proposed approach, we included a duration modification-based data augmentation module in the front end of the ASV system. Since prosody deficits are one of the early indicators of dysarthria, we investigated the role of prosodic variables in combination with the traditional Mel-frequency cepstral coefficients (MFCC). The prosodic variables explored in this study include pitch, loudness, and voicing probability. Separate i-vector and x-vector models are trained and compared using individual MFCC, prosodic variables, and their combinations. The experimental results showed that the proposed approach based on combining MFCC and prosody features along with duration-modification-based data augmentation produced promising results.

CNN-Based Identification of Parkinson's Disease from Continuous Speech in Noisy Environments.

Parkinson's disease is a progressive neurodegenerative disorder caused by dopaminergic neuron degeneration. Parkinsonian speech impairment is one of the earliest presentations of the disease and, along with tremor, is suitable for pre-diagnosis. It is defined by hypokinetic dysarthria and accounts for respiratory, phonatory, articulatory, and prosodic manifestations. The topic of this article targets artificial-intelligence-based identification of Parkinson's disease from continuous speech recorded in a noisy environment. The novelty of this work is twofold. First, the proposed assessment workflow performed speech analysis on samples of continuous speech. Second, we analyzed and quantified Wiener filter applicability for speech denoising in the context of Parkinsonian speech identification. We argue that the Parkinsonian features of loudness, intonation, phonation, prosody, and articulation are contained in the speech, speech energy, and Mel spectrograms. Thus, the proposed workflow follows a feature-based speech assessment to determine the feature variation ranges, followed by speech classification using convolutional neural networks. We report the best classification accuracies of 96% on speech energy, 93% on speech, and 92% on Mel spectrograms. We conclude that the Wiener filter improves both feature-based analysis and convolutional-neural-network-based classification performances.

Exploring Prosodic Features Modelling for Secondary Emotions Needed for Empathetic Speech Synthesis

A low-resource emotional speech synthesis system for empathetic speech synthesis based on modelling prosody features is presented here. Secondary emotions, identified to be needed for empathetic speech, are modelled and synthesised in this investigation. As secondary emotions are subtle in nature, they are difficult to model compared to primary emotions. This study is one of the few to model secondary emotions in speech as they have not been extensively studied so far. Current speech synthesis research uses large databases and deep learning techniques to develop emotion models. There are many secondary emotions, and hence, developing large databases for each of the secondary emotions is expensive. Hence, this research presents a proof of concept using handcrafted feature extraction and modelling of these features using a low-resource-intensive machine learning approach, thus creating synthetic speech with secondary emotions. Here, a quantitative-model-based transformation is used to shape the emotional speech's fundamental frequency contour. Speech rate and mean intensity are modelled via rule-based approaches. Using these models, an emotional text-to-speech synthesis system to synthesise five secondary emotions-anxious, apologetic, confident, enthusiastic and worried-is developed. A perception test to evaluate the synthesised emotional speech is also conducted. The participants could identify the correct emotion in a forced response test with a hit rate greater than 65%.

Perception of Prosody in Hearing-Impaired Individuals and Users of Hearing Assistive Devices: An Overview of Recent Advances.

Prosody perception is an essential component of speech communication and social interaction through which both linguistic and emotional information are conveyed. Considering the importance of the auditory system in processing prosody-related acoustic features, the aim of this review article is to review the effects of hearing impairment on prosody perception in children and adults. It also assesses the performance of hearing assistive devices in restoring prosodic perception. Following a comprehensive online database search, two lines of inquiry were targeted. The first summarizes recent attempts toward determining the effects of hearing loss and interacting factors such as age and cognitive resources on prosody perception. The second analyzes studies reporting beneficial or detrimental impacts of hearing aids, cochlear implants, and bimodal stimulation on prosodic abilities in people with hearing loss. The reviewed studies indicate that hearing-impaired individuals vary widely in perceiving affective and linguistic prosody, depending on factors such as hearing loss severity, chronological age, and cognitive status. In addition, most of the emerging information points to limitations of hearing assistive devices in processing and transmitting the acoustic features of prosody. The existing literature is incomplete in several respects, including the lack of a consensus on how and to what extent hearing prostheses affect prosody perception, especially the linguistic function of prosody, and a gap in assessing prosody under challenging listening situations such as noise. This review article proposes directions that future research could follow to provide a better understanding of prosody processing in those with hearing impairment, which may help health care professionals and designers of assistive technology to develop innovative diagnostic and rehabilitation tools. https://doi.org/10.23641/asha.21809772.

Adult Cochlear Implant Users Versus Typical Hearing Persons: An Automatic Analysis of Acoustic-Prosodic Parameters.

The aim of this study was to investigate the speech prosody of postlingually deaf cochlear implant (CI) users compared with control speakers without hearing or speech impairment. Speech recordings of 74 CI users (37 males and 37 females) and 72 age-balanced control speakers (36 males and 36 females) are considered. All participants are German native speakers and read Der Nordwind und die Sonne (The North Wind and the Sun), a standard text in pathological speech analysis and phonetic transcriptions. Automatic acoustic analysis is performed considering pitch, loudness, and duration features, including speech rate and rhythm. In general, duration and rhythm features differ between CI users and control speakers. CI users read slower and have a lower voiced segment ratio compared with control speakers. A lower voiced ratio goes along with a prolongation of the voiced segments' duration in male and with a prolongation of pauses in female CI users. Rhythm features in CI users have higher variability in the duration of vowels and consonants than in control speakers. The use of bilateral CIs showed no advantages concerning speech prosody features in comparison to unilateral use of CI. Even after cochlear implantation and rehabilitation, the speech of postlingually deaf adults deviates from the speech of control speakers, which might be due to changed auditory feedback. We suggest considering changes in temporal aspects of speech in future rehabilitation strategies. https://doi.org/10.23641/asha.21579171.

Prosody features based low resource Punjabi children ASR and T-NT classifier using data augmentation

Prosody features based low resource Punjabi children ASR and T-NT classifier using data augmentation

Spoken Language Identification Using Prosody, Phonotactics, and Acoustics: A Review

Spoken language identification (LID) is the identification of language present in a speech segment despite its size (duration and speed), ambiance (topic and emotion), and moderator (gender, age, demographic region). Information Technology has touched new vistas for a couple of decades mostly to simplify the day-to-day life of humans. One of the key contributions of Information Technology is the application of Artificial Intelligence to achieve better results. The advent of artificial intelligence has given rise to a new branch of Natural Language Processing (NLP) called Computational Linguistics, which generates frameworks for intelligently manipulating spoken language knowledge and has brought human–machine into a new stage. In this context, speech has arisen to be one of the imperative forms of interfaces, which is the basic mode of communication for us, and generally the most preferred one. Recognition of the spoken language is a frontend for several technologies, like multiple languages conversation systems, expressed translation software, multilingual speech recognition, spoken word extraction, speech production systems. This paper reviews and summarises the different levels of information that can be used for language identification. A broad study of acoustic, phonetic, and prosody features has been provided and various classifiers have been used for spoken language identification specifically for Indian languages. This paper has investigated various existing spoken language identification models implemented using prosodic, phonotactic, acoustic, and deep learning approaches, the datasets used, and performance measures utilized for their analysis. It also highlights the main features and challenges faced by these models. Moreover, this review analyses the efficiency of the spoken language models that can help the researchers to propose new language identification models for speech signals.

Discourses about independence: A corpus-based analysis of discourse prosodies in Spanish and Catalan newspapers

The present study is a corpus-assisted analysis of discourses on the Catalan movement of independence in the Catalan and Spanish press. A referendum for Catalan independence was held on 1 October 2017 but was not approved by the central Spanish government and was declared illegal. Spanish and Catalan newspapers differed considerably in their treatment and representation of the conflict, which also drew the attention of the international press to Catalonia. My analysis interconnects theoretical perspectives from linguistic critical discourse studies, cognitive linguistics, and media studies. The methodology is based on the analysis of two comparable corpora of journalistic texts (in Catalan, Spanish). My aim is to identify and compare different features of the semantic prosody of words describing the event of geopolitical separation and the different narratives on this sociopolitical conflict that these prosodies contribute to producing. More specifically, I focus on a selection of keywords, like independence, secession, and sovereignty, that seem to be indicative of different discursive strategies consciously, and possibly unconsciously, chosen by a selection of national Catalan and Spanish newspapers. By carrying out a contrastive analysis of the two corpora, I am able to describe certain similarities, like the similar frequent use of the word independence, and differences, like the more frequent use of the word secession in the Spanish corpus, that indicate different framings of the same event and can be related to different ideological positionings against or in favor of Catalonia’s independence from Spain.

Kalimat Interogatif Dialek Gyeongsang dalam Reply 1997

<p>The Gyeongsang dialect is phonologically and morphologically unique, yet current research generally focuses only on its prosody characteristics. Research related to language style and sentence-final ending in the Gyeongsang dialect has received less attention. Therefore, this study focuses on sentence-final ending or jeongyeol eomi in Korean interrogative sentences to fill the research gap. This research is qualitative research with a descriptive analysis method. Data is collected from the Korean drama Reply 1997 from the first three episodes. The result shows that a closed-ended interrogative sentence is the type of interrogative sentence most commonly used in the data, while the most widely used language style is plain style (haerache). The use of question words in an interrogative sentence in the Gyeongsang dialect also determines the variation of sentence-final ending used. The sentence-final ending ended in [o] sound, such as -go, -no, must be used for an open-ended interrogative sentence with question words. Sentence final ending ended in [a] sound, such as -ga, -na, must be used for a close-ended interrogative sentence with no question words.</p>

The Prosodic Aspects of Politeness in Instructional Interactions of Elementary School Teachers in Surabaya


 
 
 This study aimed to describe the prosodic aspects of politeness in the instructional interactions of elementary school teachers in Surabaya. These prosodic aspects describe the sound intensity, duration, speed and tone. The data were collected using observations at four elementary schools in Surabaya. Data analysis was performed by using Praat acoustic analysis devices and a computer software package for the scientific analysis of speech in phonetics. Based on the results, it can be concluded that the intensity, the speed of sound, and the tone of the prosodic aspects of politeness in the declarative mode of speech had lower averages than the prosodic aspects of politeness in the interrogative and imperative modes of speech. This may be because the declarative mode does not contain the illocutionary directive, while the interrogative and imperative modes do, which affects their use in response to threatening acts.
 Keywords: prosody characteristics, politeness, teacher instructional interactions
 
 

Text-to-Speech Synthesis: Literature Review with an Emphasis on Malayalam Language

Text-to-Speech Synthesis (TTS) is an active area of research to generate synthetic speech from underlying text. The identified syllables are uttered with proper duration and prosody characteristics to emulate natural speech. It falls under the category of Natural Language Processing (NLP), which aims to bridge the gap in communication between human and machine. So far as Western languages like English are concerned, the research to produce intelligent and natural synthetic speech has advanced considerably. But in a multilingual state like India, many regional languages viz. Malayalam is underexplored when it comes to NLP. In this article, we try to amalgamate the major research works performed in the area of TTS in English and the prominent Indian languages, with a special emphasis on the South Indian language, Malayalam. This review intends to provide right direction to the research activities in the language, in the area of TTS.