Comparing patterns of familiar language use across spontaneous speech contexts in individuals with nonfluent aphasia and healthy controls

Aphasiology ◽  
2021 ◽  
pp. 1-20
Author(s):  
Catherine Torrington Eaton ◽  
Lindsey Burrowes
Keyword(s):  
Language Use ◽  
Spontaneous Speech ◽  
Healthy Controls ◽  
Nonfluent Aphasia

scholarly journals Can Frequency Account for the Grammatical Choices of Children and Adults in Nominal Modification Contexts? Evidence from Elicited Production and Child-Directed Speech

Languages ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. 35
Author(s):  
Emanuela Sanfelici ◽  
Petra Schulz
Keyword(s):  
Language Acquisition ◽  
Production Rate ◽  
Relative Clauses ◽  
Language Use ◽  
Spontaneous Speech ◽  
Production Task ◽  
Specific Context ◽  
High Production Rate ◽  
High Production ◽  
Acquisition Order

There is consensus that languages possess several grammatical variants satisfying the same conversational function. Nevertheless, it is a matter of debate which principles guide the adult speaker’s choice and the child’s acquisition order of these variants. Various proposals have suggested that frequency shapes adult language use and language acquisition. Taking the domain of nominal modification as its testing ground, this paper explores in two studies the role that frequency of structures plays for adults’ and children’s structural choices in German. In Study 1, 133 three- to six-year-old children and 21 adults were tested with an elicited production task prompting participants to identify an agent or a patient referent among a set of alternatives. Study 2 analyzed a corpus of child-directed speech to examine the frequency of passive relative clauses, which children, similar to adults, produced very often in Study 1. Importantly, passive relatives were found to be infrequent in the child input. These two results show that the high production rate of rare structures, such as passive relatives, is difficult to account for with frequency. We claim that the relation between frequency in natural speech and use of a given variant in a specific context is indirect: speakers may opt for the less grammatically complex computation rather than for the variant most frequently used in spontaneous speech.

scholarly journals Linguistic Parameters of Spontaneous Speech for identifying Mild Cognitive Impairment and Alzheimer’s Disease

2021 ◽  
pp. 1-34
Author(s):  
Veronika Vincze ◽  
Martina Katalin Szabó ◽  
Ildikó Hoffmann ◽  
László Tóth ◽  
Magdolna Pákáski ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Spontaneous Speech ◽  
Healthy Controls ◽  
Demographic Information ◽  
Linguistic Features ◽  
Significance Level ◽  
Speech Transcripts

Abstract In this paper, we seek to automatically identify Hungarian patients suffering from mild cognitive impairment (MCI) or mild Alzheimer’s Disease (mAD) based on their speech transcripts, focusing only on linguistic features. In addition to the features examined in our earlier study, we introduce syntactic, semantic and pragmatic features of spontaneous speech that might affect the detection of dementia. In order to ascertain the most useful features for distinguishing healthy controls, MCI patients and mAD patients, we will carry out a statistical analysis of the data and investigate the significance level of the extracted features among various speaker group pairs and for various speaking tasks. In the second part of the paper, we use this rich feature set as a basis for an effective discrimination among the three speaker groups. In our machine learning experiments, we will analyze the efficacy of each feature group separately. Our model which uses all the features achieves competitive scores, either with or without demographic information (3-class accuracy values: 68–70%, 2-class accuracy values: 77.3–80%). We also analyze how different data recording scenarios affect linguistic features and how they can be productively used when distinguishing MCI patients from healthy controls.

Can bilingual two-year-olds code-switch?

1992 ◽  
Vol 19 (3) ◽  
pp. 633-658 ◽  
Author(s):  
Elizabeth Lanza
Keyword(s):  
Language Use ◽  
Child Language ◽  
Spontaneous Speech ◽  
Code Switching ◽  
Bilingual Children ◽  
Language Mixing ◽  
Language Differentiation ◽  
Language Literature

ABSTRACTSociolinguists have investigated language mixing as code-switching in the speech of bilingual children three years old and older. Language mixing by bilingual two-year-olds, however, has generally been interpreted in the child language literature as a sign of the child's lack of language differentiation. The present study applies perspectives from sociolinguistics to investigate the language mixing of a bilingual two-year-old acquiring Norwegian and English simultaneously in Norway. Monthly recordings of the child's spontaneous speech in interactions with her parents were made from the age of 2;0 to 2;7. An investigation into the formal aspects of the child's mixing and the context of the mixing reveals that she does differentiate her language use in con-textually sensitive ways, hence that she can code-switch. This investigation stresses the need to examine more carefully the roles of dominance and context in the language mixing of young bilingual children.

scholarly journals Linguistic and Sociolinguistic Aspects of Variation in the Eastern Cape: Complexities of Xhosa Language Use

2018 ◽  
Vol 6 ◽  
pp. 90-120
Author(s):  
Eva-Marie Bloom Ström
Keyword(s):  
South Africa ◽  
Regional Variation ◽  
Language Use ◽  
Linguistic Diversity ◽  
Spontaneous Speech ◽  
Eastern Cape ◽  
Linguistic Identity ◽  
Syntactic Variation ◽  
Personal Mobility ◽  
Bantu Languages

This paper presents the results of a micro-variation project in which linguistic diversity of the Eastern Cape of South Africa is examined. It shows that regional variation in the Xhosa dialect cluster is minimal and that many older forms and sounds that have previously been reported on are no longer in use. With a specific focus on morpho-syntactic variation, the paper gives examples from a corpus of recorded, transcribed and glossed speech collected across the Eastern Cape. It is argued that spontaneous speech is crucial in analysing morpho-syntactic variation when it is on a fine, intralinguistic level. The paper gives a detailed overview of previous publications on the dialects of the area and relates this to current findings based on the recordings. It is shown that the presumed decline in dialectal differences is not paired with a decrease in linguistic identity which is connected to separate clans and kingdoms. The dwindling use of regional variables is explained by a longstanding situation of personal mobility, standardization and schooling. This paper contributes to our understanding of the linguistic complexities of the Nguni subgroup of Bantu languages. It concludes that any experienced differences between standard Xhosa and the language spoken at home is not due to regional variation, and that their causes should be sought elsewhere.

Language use, role and context in a five-year-old

1978 ◽  
Vol 5 (1) ◽  
pp. 81-99 ◽  
Author(s):  
Margaret Martlew ◽  
Kevin Connolly ◽  
Christine McCleod
Keyword(s):  
Social Interactions ◽  
Language Use ◽  
Role Play ◽  
Spontaneous Speech ◽  
Speech Transcripts ◽  
Relationship Of ◽  
The Relationship

ABSTRACTTo explore the relationship of language use and speech adaptation to role and context the spontaneous speech of a boy aged 5; 6 was recorded in three different situations: playing alone, playing with a friend of the same age, and playing with his mother. Several analyses were made of the speech transcripts to examine the relationship between context and language use. The nature of play episodes was also investigated. The findings suggest that role play has an important function in the development of a child's ability to communicate effectively, and that a child's awareness of his own role and the expectations he has concerning social interactions lead to modification in language use.

scholarly journals Crossing the “Cookie Theft” Corpus Chasm: Applying What BERT Learns From Outside Data to the ADReSS Challenge Dementia Detection Task

2021 ◽  
Vol 3 ◽  
Author(s):  
Yue Guo ◽  
Changye Li ◽  
Carol Roan ◽  
Serguei Pakhomov ◽  
Trevor Cohen
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Spontaneous Speech ◽  
Cognitive Status ◽  
Detection Task ◽  
Training Data ◽  
Data Provenance ◽  
Healthy Controls ◽  
Learning Models ◽  
Machine Learning Models

Large amounts of labeled data are a prerequisite to training accurate and reliable machine learning models. However, in the medical domain in particular, this is also a stumbling block as accurately labeled data are hard to obtain. DementiaBank, a publicly available corpus of spontaneous speech samples from a picture description task widely used to study Alzheimer's disease (AD) patients' language characteristics and for training classification models to distinguish patients with AD from healthy controls, is relatively small—a limitation that is further exacerbated when restricting to the balanced subset used in the Alzheimer's Dementia Recognition through Spontaneous Speech (ADReSS) challenge. We build on previous work showing that the performance of traditional machine learning models on DementiaBank can be improved by the addition of normative data from other sources, evaluating the utility of such extrinsic data to further improve the performance of state-of-the-art deep learning based methods on the ADReSS challenge dementia detection task. To this end, we developed a new corpus of professionally transcribed recordings from the Wisconsin Longitudinal Study (WLS), resulting in 1366 additional Cookie Theft Task transcripts, increasing the available training data by an order of magnitude. Using these data in conjunction with DementiaBank is challenging because the WLS metadata corresponding to these transcripts do not contain dementia diagnoses. However, cognitive status of WLS participants can be inferred from results of several cognitive tests including semantic verbal fluency available in WLS data. In this work, we evaluate the utility of using the WLS ‘controls’ (participants without indications of abnormal cognitive status), and these data in conjunction with inferred ‘cases’ (participants with such indications) for training deep learning models to discriminate between language produced by patients with dementia and healthy controls. We find that incorporating WLS data during training a BERT model on ADReSS data improves its performance on the ADReSS dementia detection task, supporting the hypothesis that incorporating WLS data adds value in this context. We also demonstrate that weighted cost functions and additional prediction targets may be effective ways to address issues arising from class imbalance and confounding effects due to data provenance.

Evaluating Web-Based Automatic Transcription for Alzheimer’s Speech Data: Transcript Comparison and Machine Learning Analysis (Preprint)

2021 ◽  
Author(s):  
Thomas Soroski ◽  
Thiago da Cunha Vasco ◽  
Sally Newton-Mason ◽  
Saffrin Granby ◽  
Caitlin Lewis ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neurodegenerative Disease ◽  
Life Experience ◽  
Cost Savings ◽  
Spontaneous Speech ◽  
Error Rates ◽  
Healthy Controls ◽  
Machine Learning Classification ◽  
Speech Data ◽  
Automatic Transcription

BACKGROUND Speech data for medical research can be collected non-invasively and in large volumes. Speech analysis has shown promise in diagnosing neurodegenerative disease. To effectively leverage speech data, transcription is important as there is valuable information contained in lexical content. Manual transcription, while highly accurate, limits potential scalability and cost savings associated with language-based screening. OBJECTIVE To better understand the use of automatic transcription for classification of neurodegenerative disease (Alzheimer’s Disease [AD], mild cognitive impairment [MCI] or subjective memory complaints [SMC] versus healthy controls), we compared automatically generated transcripts against transcripts that went through manual correction. METHODS We recruited individuals from a memory clinic (“patients”) with a diagnosis of mild-moderate AD, (n=44), MCI (n=20), SMC (n=8) and healthy controls living in the community (n=77). Participants were asked to describe a standardized picture, read a paragraph, and recall a pleasant life experience. We compared transcripts generated using Google speech-to-text software to manually-verified transcripts by examining transcription confidence scores, transcription error rates, and machine learning classification accuracy. For the classification tasks, Logistic Regression, Gaussian Naive Bayes, and Random Forests were used. RESULTS The transcription software showed higher confidence scores (P<.001) and lower error rates (P>.05) for speech from healthy controls as compared with patients. Classification models using human-verified transcripts significantly (P<.001) outperformed automatically-generated transcript models for both spontaneous speech tasks. This comparison showed no difference in the reading task. Manually adding pauses to transcripts had no impact on classification performance. Manually correcting both spontaneous speech tasks led to significantly higher performances in the machine learning models. CONCLUSIONS We found that automatically-transcribed speech data could be used to distinguish patients with a diagnosis of AD, MCI or SMC from controls. We recommend a human verification step to improve the performance of automatic transcripts, especially for spontaneous tasks. Moreover, human verification can focus on correcting errors and adding punctuation to transcripts. Manual addition of pauses, however, is not needed, which can simplify the human verification step to more efficiently process large volumes of speech data.

Voice Use in Daily Life Studied With a Portable Voice Accumulator in Individuals With Parkinson's Disease and Matched Healthy Controls

2019 ◽  
Vol 62 (12) ◽  
pp. 4324-4334 ◽  
Author(s):  
Joakim Körner Gustafsson ◽  
Maria Södersten ◽  
Sten Ternström ◽  
Ellika Schalling
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Daily Life ◽  
Spontaneous Speech ◽  
Environmental Noise ◽  
Sound Level ◽  
Female Group ◽  
Healthy Controls ◽  
The Impact ◽  
Voice Use

Purpose The purpose of this work was to study how voice use in daily life is impacted by Parkinson's disease (PD), specifically if there is a difference in voice sound level and phonation ratio during everyday activities for individuals with PD and matched healthy controls. A further aim was to study how variations in environmental noise impact voice use. Method Long-term registration of voice use during 1 week in daily life was performed for 21 participants with PD (11 male, 10 female) and 21 matched healthy controls using the portable voice accumulator VoxLog. Voice use was assessed through registrations of spontaneous speech in different ranges of environmental noise in daily life and in a controlled studio recording setting. Results Individuals with PD use their voice 50%–60% less than their matched healthy controls in daily life. The difference increases in high levels of environmental noise. Individuals with PD used an average voice sound level in daily life that was 8.11 dB (female) and 6.7 dB (male) lower than their matched healthy controls. Difference in mean voice sound level for individuals with PD and controls during spontaneous speech during a controlled studio registration was 3.0 dB for the female group and 4.1 dB for the male group. Conclusions The observed difference in voice use in daily life between individuals with PD and matched healthy controls is a 1st step to objectively quantify the impact of PD on communicative participation. The variations in voice use in different levels of environmental noise and when comparing controlled and variable environments support the idea that the study of voice use should include methods to assess function in less controlled situations outside the clinical setting.

scholarly journals Puheessa esiintyvistä riittävyyden verbeistä norjansuomalaisilla nuorilla

Virittäjä ◽  
2019 ◽  
Vol 123 (1) ◽  
Author(s):  
Kristiina Lieri
Keyword(s):  
Individual Differences ◽  
Language Learning ◽  
Language Use ◽  
Native Speakers ◽  
Spontaneous Speech ◽  
Primary Data ◽  
Verb Constructions ◽  
Modal Verb ◽  
Language Context

Tässä artikkelissa tarkastellaan, millaisia riittävyyden verbejä Oslon seudulla asuvat kuusi 12–23-vuotiasta kaksi- ja monikielistä norjansuomalaista nuorta käyttävät spontaanissa puheessaan. Nuoret ovat oppineen suomen ensikielenään (L1) ja norjan toisena kielenä (L2). Artikkelissa pohditaan myös, miten informanttien kielenkäyttöaktiivisuus heijastuu riittävyyden verbien käyttöön kielikontaktitilanteessa. Tutkimusaineisto koostuu neljästä haastattelusta. Norjansuomalaisten informanttien verbikonstruktioiden käyttöä tarkastellaan suhteessa verrokkiryhmän vastaavaan käyttöön. Verrokkiryhmä koostuu samanikäisistä Suomessa asuvista informanteista. Teoreettisesti tutkimus pohjautuu kielenoppimista koskevaan käyttöpohjaiseen (usage-based) lähestymistapaan, jossa kielen rakenteet kehittyvät käytössä. Tutkimus on luonteeltaan kvalitatiivinen. Tulokset osoittavat, että norjansuomalaiset nuoret käyttävät puheessa vain muutamia riittävyyden verbejä. He käyttävät kuitenkin enimmäkseen samoja verbejä kuin suomensuomalainen verrokkiryhmä. Voida-verbin ohella useimmin esiintyvät verbit ovat päästä ja pystyä. Kaksikielisten informanttien välillä on yksilöllisiä eroja, jotka johtuvat erityisesti suomen kielen käyttöaktiivisuudesta. Melko tavallisten verbien pienten semanttisten erojen omaksuminen on vaikeaa kontekstissa, jossa kieltä käytetään vain muutamien ihmisten kanssa. Aineisto osoittaa, että informantit käyttävät kompleksisia suomen kielen verbikonstruktioita pääasiassa suomen yleiskielen mallin mukaisesti. Muutama esimerkki nostaa kuitenkin esiin toisen kielen vaikutuksen.   Verbs of sufficiency in spontaneous speech among Finnish-Norwegian adolescents The aim of the present study is to investigate what kind of verbs of sufficiency six young Finns aged 12–23 living in the greater Oslo area in Norway use in spontaneous speech. The six subjects have learned Finnish as their L1 and Norwegian as L2. The article also discusses how the speakers’ language use is reflected in their use of verbs of sufficiency in a language context situation. The primary data consists of four audio-recorded interviews with six bilingual and multilingual Finnish-Norwegian adolescents. Their use of verbs is compared with that of Finnish L1 speakers of the same age. The study is based on the usage-based approach to language learning, where constructions develop in language use. The analysis of the data is qualitative. The results show that Finnish-Norwegian subjects use only a few verbs of sufficiency. However, they mostly use the same verbs as native speakers. The most frequent verbs beside voida are päästä and pystyä. There are individual differences between the bilingual subjects, which is due in particular to how actively they use the Finnish language. Adopting rather small semantic differences of fairly common verbs is difficult in a context where the language is used by only a few people. The data indicates that complex Finnish modal verb constructions are used with only a few deviations from the spoken patterns of native Finnish speakers. However, some examples reveal the influence of the L2.  

Effects of Gender, Parental Role, and Time on Infant- and Adult-Directed Read and Spontaneous Speech

2019 ◽  
Vol 62 (11) ◽  
pp. 4001-4014
Author(s):  
Melanie Weirich ◽  
Adrian Simpson
Keyword(s):  
Parental Involvement ◽  
Gender Identity ◽  
Spontaneous Speech ◽  
First Year ◽  
Space Size ◽  
Vowel Space ◽  
Potential Impact ◽  
Phonetic Features ◽  
And Gender ◽  
Description Task

Purpose The study sets out to investigate inter- and intraspeaker variation in German infant-directed speech (IDS) and considers the potential impact that the factors gender, parental involvement, and speech material (read vs. spontaneous speech) may have. In addition, we analyze data from 3 time points prior to and after the birth of the child to examine potential changes in the features of IDS and, particularly also, of adult-directed speech (ADS). Here, the gender identity of a speaker is considered as an additional factor. Method IDS and ADS data from 34 participants (15 mothers, 19 fathers) is gathered by means of a reading and a picture description task. For IDS, 2 recordings were made when the baby was approximately 6 and 9 months old, respectively. For ADS, an additional recording was made before the baby was born. Phonetic analyses comprise mean fundamental frequency (f0), variation in f0, the 1st 2 formants measured in /i: ɛ a u:/, and the vowel space size. Moreover, social and behavioral data were gathered regarding parental involvement and gender identity. Results German IDS is characterized by an increase in mean f0, a larger variation in f0, vowel- and formant-specific differences, and a larger acoustic vowel space. No effect of gender or parental involvement was found. Also, the phonetic features of IDS were found in both spontaneous and read speech. Regarding ADS, changes in vowel space size in some of the fathers and in mean f0 in mothers were found. Conclusion Phonetic features of German IDS are robust with respect to the factors gender, parental involvement, speech material (read vs. spontaneous speech), and time. Some phonetic features of ADS changed within the child's first year depending on gender and parental involvement/gender identity. Thus, further research on IDS needs to address also potential changes in ADS.

Sign in / Sign up

Export Citation Format

Share Document