Sentence Accuracy Research Articles

Frequency importance for sentence recognition in co-located noise, co-located speech, and spatially separated speech.

Frequency importance functions quantify the contribution of spectral frequencies to perception. Frequency importance has been well-characterized for speech recognition in quiet and steady-state noise. However, it is currently unknown whether frequency importance estimates generalize to more complex conditions such as listening in a multi-talker masker or when targets and maskers are spatially separated. Here, frequency importance was estimated by quantifying associations between local target-to-masker ratios at the output of an auditory filterbank and keyword recognition accuracy for sentences. Unlike traditional methods used to measure frequency importance, this technique estimates frequency importance without modifying the acoustic properties of the target or masker. Frequency importance was compared across sentences in noise and a two-talker masker, as well as sentences in a two-talker masker that was either co-located with or spatially separated from the target. Results indicate that frequency importance depends on masker type and spatial configuration. Frequencies above 5 kHz had lower importance and frequencies between 600 and 1900 Hz had higher importance in the presence of a two-talker masker relative to a noise masker. Spatial separation increased the importance of frequencies between 600 Hz and 5 kHz. Thus, frequency importance functions vary across listening conditions.

Hebrew Digits in Noise (DIN) Test in Cochlear Implant Users and Normal Hearing Listeners.

This study aimed to compare the Hebrew version of the digits-in-noise (DIN) thresholds among cochlear implant (CI) users and their normal-hearing (NH) counterparts, explore the influence of age on these thresholds, examine the effects of early auditory exposure versus its absence on DIN threshold, and assess the correlation between DIN thresholds and other speech perception tests. A total of 13 children with CI (aged 5.5-11 years), 15 pre-lingual CI users (aged 14-30 years), and 15 post-lingual CI users (aged 22-77 years), and their age-matched NH controls (n = 45) participated in the study. Speech perception tasks, including the DIN test, one-syllable word test, and sentence identification tasks in various auditory conditions, served as the main outcome measures. The results indicated that CI users exhibited higher speech reception thresholds in noise across all age groups compared to NH peers, with no significant difference between pre-lingual and post-lingual CI users. Significant differences were also observed in monosyllabic word and sentence accuracy in both quiet and noise conditions between CI and NH groups. Furthermore, correlations were observed between the DIN and other speech perception tests. The study concludes that CI users require a notably higher signal-to-noise ratio to discern digits in noise, underscoring the DIN test's utility in assessing speech recognition capabilities in CI users while emphasizing the need for a comprehensive test battery to fully gauge their speech perception abilities.

행정기관 보도자료의 공공언어 사용 실태 분석

This study examined the actual use of public language in administrative agency press releases from the perspective of sentence accuracy. The actual use of public language in terms of sentences, which was dealt with as an item of comprehensive discussion in previous studies, was classified into more detailed types and exam ined, and high-frequency error types were identified by analyzing the frequency of errors by detailed type. To this end, among the public language diagnostic criteria of Min Hyunsik(2010), the items that can be classified into sentence aspects in the ‘accuracy’ area were used as the subject of discussion to establish the <Public Language ‘Sentence Ac curacy’ Analysis Criteria>. It was largely divided into ‘grammatically correct sen tence’ and ‘Korean-style sentence’ and again set sub-items to analyze press releases posted on the Gyeongsangbuk-do Office of Education and the Korea Housing Finance Corporation’s website. The results of this study can be used as the basis for deriving improvement measures that can be of practical help in writing press releases for administrative agencies.

Handwriting Accuracy of Beginning Writers and Its Impact on the Readability of Their Sentences

Occupational therapists require an understanding of the range of factors which contribute to handwriting proficiency in beginning writers to best assist children experiencing handwriting difficulty. However, there is limited research which has focused on children’s ability to handwrite sentences. The purpose of this study was to evaluate the accuracy and readability of sentences written by mainstream Year 1 and Year 2 children. A total of 408 children were asked to write a self-generated, dictated, and copied sentence. The Perceive, Recall, Plan, and Perform (PRPP) System of Task Analysis (Stage One) was employed to determine the sentence mastery score and proficiency of the subskills required to correctly handwrite a sentence. The readability of each sentence was assessed using a three-point Likert scale. The results of the study showed that the sentence mastery score for Year 1 children ranged between 53-56% across the three sentence writing tasks, while Year 2 children scored between 63-65%. The overall score was impacted by errors in alphabet-letter-writing, letter-spacing, word-spacing, and spelling. 20% of Year 1 and 40% of Year 2 children generated a sentence which was easily readable when writing from memory. Readability scores improved when sentences were copied. The study identified proficiency levels for different subskills required for handwritten sentences to be readable. The need for further research to determine developmental and ability milestones for handwriting sentences in the early years are discussed. Considerations for occupational therapy handwriting assessment and intervention at the sentence level are provided.

Feasibility Study of Parkinson's Speech Disorder Evaluation With Pre-Trained Deep Learning Model for Speech-to-Text Analysis.

This study investigates the feasibility of employing a pre-trained deep learning wave-to-vec model for speech-to-text analysis in individuals with speech disorders arising from Parkinson's disease (PD). A publicly available dataset containing speech recordings including the Hoehn and Yahr (H&Y) staging, Movement Disorder Society Unified Parkinson's Disease Rating Scale (UPDRS) Part I, UPDRS Part II scores, and gender information from both healthy controls (HC) and those diagnosed with PD was utilized. Employing the Wav2Vec model, a speech-to-text analysis method was implemented on PD patient data. Tasks conducted included word letter classification, word match probability assessment, and analysis of speech waveform characteristics as provided by the model's output. For the dataset comprising 20 cases, among individuals with PD, the H&Y score averaged 2.50±0.67, the UPDRS II-part 5 score averaged 0.70±1.00, and the UPDRS III-part 18 score averaged 0.80±0.98. Additionally, the number of words derived from decoded text subsequent to speech recognition was evaluated, resulting in mean values of 299.10±16.79 and 259.80±93.39 for the HC and PD groups, respectively. Furthermore, the calculated degree of agreement for all syllables was based on the speech process. The accuracy for the reading sentences was observed to be 0.31 and 0.10, respectively. This study aimed to demonstrate the effectiveness of wave-to-vec in enhancing speech-to-text analysis for patients with speech disorders. The findings could pave the way for the development of clinical tools for improved diagnosis, evaluation, and communication support for this population.

Integration and Innovation of Artificial Intelligence and Traditional English Translation Methods

Abstract In this study, we employ autoregressive and neural machine translation models to process natural language. Our exploration of AI translation workflows encompasses three key aspects: the encoder-decoder framework, text feature representation, and translation derivation methodologies. Subsequently, we identify the core evaluation indices essential for assessing intelligent translation systems. An innovative translation model is constructed by amalgamating AI-driven and traditional English translation techniques. This model is scrutinized for its effectiveness through various lenses, including the quality of English-to-Chinese poetry translations and manual evaluations. Comparative analysis of the proposed translation method with other extant methods across diverse datasets reveals superior performance metrics: the BLEU score consistently exceeds 4.5 across all three test sets, and the METEOR score ranges between 4.3 and 4.6, surpassing competing methods. Additionally, translation accuracy for sentences of varying lengths in the source language is maintained between 85% and 96%. The objective of this research is to conduct a comprehensive examination of the integration of AI English translation with conventional methodologies, aiming to foster innovative theoretical contributions and practical advancements in the field.

AN ANALYSIS OF REDUCTION TECHNIQUE APPLIED ON THE INTERROGATIVE SENTENCES AND ITS IMPACT ON THE TRANSLATION QUALITY IN THE MOVIE SUBTITLE OF NATIONAL TREASURE 2: BOOK OF SECRET

<p align="center"> </p><p>This research is conducted to analyze the use of reduction technique on interrogative sentences in the movie subtitle of <em>National Treasure 2: Book of Secret</em>. The objectives of this research are (1) to find out the types of reduction technique in translating interrogative sentences in the movie subtitle of <em>National Treasure 2: Book of Secret</em>: (2) to find out the accuracy and acceptability of the interrogative sentences that are translated using reduction technique in the movie subtitle of <em>National Treasure 2: Book of Secret</em> as a result of the reduction technique application.</p><p>This research is a descriptive qualitative research. The data consist of interrogative sentences with reduction technique that are found in the movie subtitle <em>National Treasure 2: Book of </em>Secret and the statement from the informants about the quality of the translation. The sampling techniques are total sampling and a purposive sampling technique.</p><p>The result of this study shows that there are 62 data (52.54%) accurate, 51 data (43.22%) less accurate, and five data (4.23%) inaccurate. The current study also shows that there are 111 data (94.06%) classified into acceptable translations and seven (5.93%) classified into less acceptable translations.</p><p> </p><p><strong><em>Keywords:</em></strong> reduction, reduction techniques, translation quality.</p><p> </p>

Pengaruh Language Games Terhadap Kemampuan Berbicara Bahasa Inggris Mahasiswa Administrasi Bisnis Internasional Politeknik Kampar

In the process of language learning, particularly English, there are various methods and strategies that can be applied. One interesting approach is through language games. This study aims to examine the impact of using language games on students' English-speaking skills. The subjects of the study involved 19 students from classes 1 to 4 of the International Business Administration Program at Kampar Polytechnic. The results revealed that the use of language games significantly improved students' speaking abilities, including pronunciation, fluency, and sentence accuracy. Additionally, student participation, discipline, and responsiveness also showed improvement. Based on the questionnaire results, all students agreed that language games were not only enjoyable but also highly motivating, encouraging them to engage more actively in class activities.

A Feasibility Study in Virtual Assessment Procedures of a Sentence-Writing Probe for Use With Intermediate-Grade Students

This article reports on the development and initial feasibility of virtual assessment procedures for a sentence-writing probe for remote instructional purposes with intermediate-grade students. The study included a sample of 15 intermediate-grade children. The sentence-writing probe was administered through video conferencing software, an innovation of the times, across three sessions separated by 2 weeks. Scores derived from sentence probes included total number of words, a sentence accuracy score, and a word accuracy score, which were compared across time points. Results indicated no statistically significant differences across time points for the entire sample for all measures except the total number of words at Time 2. Measures obtained from the sentence-writing probe were significantly correlated with standardized measures of oral language. Findings from this study support the proof of concept that virtual assessment procedures can be used to assess sentence-level writing in intermediate-grade students. Future directions are provided regarding the utility of remote instruction for assessment purposes, the types of scores derived from measures, and future plans to scale up the assessment for use in research studies and as a curriculum-based evaluation tool.

Pengaruh Media Pembelajaran Flashcard Terhadap Kemampuan Menulis Surat Dinas Siswa Kelas VII SMP Muhammadiyah 1 Medan

This study aims to, (1) To describe the ability to write official letters of VII grade students of SMP Muhammadiyah 1 Medan in the academic year 2022/2023 before using flashcards learning media. (2) To describe the ability to write official letters of VII grade students of SMP Muhammadiyah 1 Medan in the academic year 2022/2023 after using flashcard learning media. (3) To describe the impact of using flashcard learning media in improving the ability to write official letters of VII grade students of SMP Muhammadiyah 1 Medan in the academic year 2022/2023. The population in this study were all VII grade students of SMP Muhammadiyah 1 Medan with a research sample of 37 students of VII-T2 grade students of SMP Muhammadiyah 1 Medan. The instruments used in this study are the accuracy of letter content, completeness of letter content, appropriateness of letter format, word accuracy, sentence accuracy, and spelling and writing. The method used in this research was one group pretest-posttest. The data analysis technique used the analysis requirement test, normality test, and hypothesis testing. The results of pretest research obtained an average of 57.75, and fell into the category of less. However, the posttest research results obtained an average of 79.29 and included in the good category. Through hypothesis testing, namely 6.20057 > 2.02809, it can be concluded that there is a significant effect of flashcard learning media on the ability to write official letters of VII grade students of SMP Muhammadiyah 1 Medan.

Application of Q-learning virtual network and embedded processor in Chinese English translation sentence accuracy analysis

Application of Q-learning virtual network and embedded processor in Chinese English translation sentence accuracy analysis

Improving distinctiveness in video captioning with text-video similarity

Video captioning is a task of automatically describing visual content of a video with a sentence. Recent works in video captioning focus on improving the performance of sentence accuracy. However, the distinctiveness of sentence, i.e., highlighting unique and accurate details of video, in video captioning is still underexplored. This paper aims to improve sentence distinctiveness by incorporating video retrieval into the training process of the video captioning model. Specifically, the video retrieval will calculate similarity scores between the input text generated by the video captioning and videos. These similarity scores are then incorporated into the training loss of video captioning, which serves as distinctiveness constraint where the generated sentence and its corresponding video should have the highest similarity scores. To further improve the sentence distinctiveness, we additionally use reference scores, i.e., similarity scores between ground truth sentences and videos, as weights to scale the training loss of video captioning. This reference score serves as a target score for the model, indicating the desired level of distinctiveness for the generated sentence on how similar the generated sentence should be to the ground truth sentence for the corresponding video. Our qualitative and quantitative results show that our method improves sentence distinctiveness while simultaneously increasing its accuracy on MSVD and MSR-VTT datasets.

Assessment of verb and sentence processing deficits in stroke-induced aphasia: the Italian version of the Northwestern Assessment of Verbs and Sentences (NAVS-I)

ABSTRACT Background The Northwestern Assessment of Verbs and Sentences (NAVS) assesses verb and sentence production and comprehension in aphasia. Results from the original English version and from its adaptation to German have shown that the NAVS is able to capture effects of verb-argument structure (VAS) complexity (i.e., lower accuracy for two- and three-argument vs. one-argument verbs) and syntactic complexity (i.e., lower accuracy for non-canonical vs. canonical sentences) in both agrammatic participants and individuals with fluent forms of aphasia. The NAVS has been recently adapted to Italian (NAVS-I) and tested on a group of healthy participants, with results showing longer reaction times to complex vs. simple verbs and sentences. Aims The present study aimed to test the ability of NAVS-I to i) capture verb/sentence production and comprehension deficits in Italian-speaking individuals with agrammatism or with fluent aphasia, and ii) differentiate individuals with aphasia from healthy age-matched participants, with the overall goal to validate its use in clinical practice. Methods & Procedures Forty-four healthy participants and 28 individuals with aphasia (10 with agrammatic speech production) were administered the NAVS-I, which includes tasks assessing production and comprehension of verbs requiring one, two or three arguments, as well as production and comprehension of canonical and non-canonical sentences. Outcomes & Results On the Verb Naming Task (VNT), better production of one- (vs. two- and three-) argument verbs was found in the agrammatic group, whereas, verb production in the fluent group was solely predicted by word length and imageability. No effects of argument optionality (i.e., greater difficulty for optionally transitive verbs than for 1-argument verbs) were found. Sentence-level tasks found no differences between the agrammatic and the fluent group in production or comprehension of both canonical and non-canonical sentences; rather, sentence comprehension accuracy was predicted by demographic variables and by aphasia severity. At the individual level, performance on the NAVS-I was significantly different from that of healthy speakers in 26/28 patients. Conclusions Data show that the NAVS-I is able to capture effects of argument structure complexity in verb production, and effects of syntactic complexity in sentence production and comprehension. In addition, our results point to verb production as the task with greater capability to differentiate agrammatism from other (fluent) forms of aphasia. The study provides support for the use of the NAVS-I in the diagnosis of aphasia, as it is able to detect language deficits at the individual level, even in participants with mild (residual) forms of aphasia.

Language impairment in Parkinson's disease: fMRI study of sentence reading comprehension.

Parkinson's disease (PD) affects the language processes, with a significant impact on the patients' daily communication. We aimed to describe specific alterations in the comprehension of syntactically complex sentences in patients with PD (PwPD) as compared to healthy controls (HC) and to identify the neural underpinnings of these deficits using a functional connectivity analysis of the striatum. A total of 20 patients PwPD and 15 HC participated in the fMRI study. We analyzed their performance of a Test of sentence comprehension (ToSC) adjusted for fMRI. A task-dependent functional connectivity analysis of the striatum was conducted using the psychophysiological interaction method (PPI). On the behavioral level, the PwPD scored significantly lower (mean ± sd: 77.3 ± 12.6) in the total ToSC score than the HC did (mean ± sd: 86.6 ± 8.0), p = 0.02, and the difference was also significant specifically for sentences with a non-canonical word order (PD-mean ± sd: 69.9 ± 14.1, HC-mean ± sd: 80.2 ± 11.5, p = 0.04). Using PPI, we found a statistically significant difference between the PwPD and the HC in connectivity from the right striatum to the supplementary motor area [SMA, (4 8 53)] for non-canonical sentences. This PPI connectivity was negatively correlated with the ToSC accuracy of non-canonical sentences in the PwPD. Our results showed disturbed sentence reading comprehension in the PwPD with altered task-dependent functional connectivity from the right striatum to the SMA, which supports the synchronization of the temporal and sequential aspects of language processing. The study revealed that subcortical-cortical networks (striatal-frontal loop) in PwPD are compromised, leading to impaired comprehension of syntactically complex sentences.

Pre-Trained Joint Model for Intent Classification and Slot Filling with Semantic Feature Fusion

The comprehension of spoken language is a crucial aspect of dialogue systems, encompassing two fundamental tasks: intent classification and slot filling. Currently, the joint modeling approach for these two tasks has emerged as the dominant method in spoken language understanding modeling. However, the existing joint models have limitations in terms of their relevancy and utilization of contextual semantic features between the multiple tasks. To address these limitations, a joint model based on BERT and semantic fusion (JMBSF) is proposed. The model employs pre-trained BERT to extract semantic features and utilizes semantic fusion to associate and integrate this information. The results of experiments on two benchmark datasets, ATIS and Snips, in spoken language comprehension demonstrate that the proposed JMBSF model attains 98.80% and 99.71% intent classification accuracy, 98.25% and 97.24% slot-filling F1-score, and 93.40% and 93.57% sentence accuracy, respectively. These results reveal a significant improvement compared to other joint models. Furthermore, comprehensive ablation studies affirm the effectiveness of each component in the design of JMBSF.

Joint modeling method of question intent detection and slot filling for domain-oriented question answering system

PurposeIntent detection and slot filling are two important tasks in question comprehension of a question answering system. This study aims to build a joint task model with some generalization ability and benchmark its performance over other neural network models mentioned in this paper.Design/methodology/approachThis study used a deep-learning-based approach for the joint modeling of question intent detection and slot filling. Meanwhile, the internal cell structure of the long short-term memory (LSTM) network was improved. Furthermore, the dataset Computer Science Literature Question (CSLQ) was constructed based on the Science and Technology Knowledge Graph. The datasets Airline Travel Information Systems, Snips (a natural language processing dataset of the consumer intent engine collected by Snips) and CSLQ were used for the empirical analysis. The accuracy of intent detection and F1 score of slot filling, as well as the semantic accuracy of sentences, were compared for several models.FindingsThe results showed that the proposed model outperformed all other benchmark methods, especially for the CSLQ dataset. This proves that the design of this study improved the comprehensive performance and generalization ability of the model to some extent.Originality/valueThis study contributes to the understanding of question sentences in a specific domain. LSTM was improved, and a computer literature domain dataset was constructed herein. This will lay the data and model foundation for the future construction of a computer literature question answering system.

Curriculum Compositional Continual Learning for Neural Machine Translation

Current trends in language modelling leverage large language models pre-trained on a huge corpus of data to achieve state of the art results on several NLP tasks. On the other hand, humans acquire language from small amount of data using cognitive principles. Recently, a continual learning approach using compositionality to disentangle the syntax and semantics of an input sentence for downstream sequence to sequence tasks was proposed. In this work, we show how curriculum learning can be incorporated with this framework to improve performance. More specifically, first, we show that using the model of interest with reduced hidden size as the auxiliary model to generate curriculum is not necessarily optimal and second, we propose a novel variant of the one best score approach for curriculum learning where, a sequence to sequence model is used as the auxiliary model to generate the conditional probabilities of word predictions (proxy for difficulty) and consequently used this to generate a curriculum. Results on a variety of translation tasks, demonstrate the superiority of the proposed approach compared to several baselines, enabling the improvement of sentence accuracy with respect to knowledge transfer and catastrophic-forgetting both by at least a significant margin of 35% with respect to the best performing baseline on the English-French translation task.

언어장애인의 스마트스피커 접근성 향상을 위한 개인화된 음성 분류 기법

With the spread of smart speakers based on voice recognition technology and deep learning technology, not only non-disabled people, but also the blind or physically handicapped can easily control home appliances such as lights and TVs through voice by linking home network services. This has greatly improved the quality of life. However, in the case of speech-impaired people, it is impossible to use the useful services of the smart speaker because they have inaccurate pronunciation due to articulation or speech disorders. In this paper, we propose a personalized voice classification technique for the speech-impaired to use for some of the functions provided by the smart speaker. The goal of this paper is to increase the recognition rate and accuracy of sentences spoken by speech-impaired people even with a small amount of data and a short learning time so that the service provided by the smart speaker can be actually used. In this paper, data augmentation and one cycle learning rate optimization technique were applied while fine-tuning ResNet18 model. Through an experiment, after recording 10 times for each 30 smart speaker commands, and learning within 3 minutes, the speech classification recognition rate was about 95.2%.

Translating SIBI (Sign System for Indonesian Gesture) Gesture-to-Text in Real-Time using a Mobile Device

The SIBI gesture translation framework by Rakun was built using a series of machine learning technologies: MobileNetV2 for feature extraction, Conditional Random Field for finding the epenthesis movement frame, and Long Short-Term Memory for word classification. This high computational translation system was previously implemented on a personal computer system, which lacks portability and accessibility. This study implemented the system on a smartphone using an on-device inference method: the translation process is embedded into the smartphone to provide lower latency and zero data usage. The system was then improved using a parallel multi-inference method, which reduced the average translation time by 25%. The final mobile SIBI gesture-to-text translation system achieved a word accuracy of 90.560%, a sentence accuracy of 64%, and an average translation time of 20 seconds.

Effects of markedness in gender processing in Italian as a heritage language: A speed accuracy tradeoff.

This study examined potential sources of grammatical gender variability in heritage speakers (HSs) of Italian with a focus on morphological markedness. Fifty-four adult Italian HSs living in Germany and 40 homeland Italian speakers completed an online Self-Paced Reading Task and an offline Grammaticality Judgment Task. Both tasks involved sentences with grammatical and ungrammatical noun-adjective agreement, manipulating markedness. In grammatical sentences, both groups showed a markedness effect: shorter reading times (RTs) and higher accuracy for sentences containing masculine nouns as compared to sentences with feminine nouns. In ungrammatical sentences, although both groups were sensitive to ungrammaticality, only HSs showed a markedness effect, that is, they had significantly longer RTs and higher accuracy when violations were realized on feminine adjectives. Proficiency in the HL was a significant predictor of accuracy and RTs at the individual level. Taken together, results indicate that HSs acquire and process gender in a qualitatively similar way to homeland native speakers. However, RT evidence seems to suggest that at least under particular experimental methods, markedness considerations are more prevalent for HSs resulting in a speed-accuracy tradeoff.