2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)最新文献
Jihyun Mun, Sunhee Kim, Myeong-Ju Kim, J. Ryu, Sejoong Kim, Minhwa Chung
{"title":"A Speech Corpus For Chronic Kidney Disease","authors":"Jihyun Mun, Sunhee Kim, Myeong-Ju Kim, J. Ryu, Sejoong Kim, Minhwa Chung","doi":"10.1109/O-COCOSDA202257103.2022.9997994","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997994","url":null,"abstract":"In this study, we present a speech corpus of patients with chronic kidney disease (CKD) that will be used for research on pathological voice analysis, automatic illness identification, and severity prediction. This paper introduces the steps involved in creating this corpus, including the choice of speech-related parameters and speech lists as well as the recording technique. The speakers in this corpus, 289 CKD patients with varying degrees of severity who were categorized based on estimated glomerular filtration rate (eGFR), delivered sustained vowels, sentence, and paragraph stimuli. This study compared and analyzed the voice characteristics of CKD patients with those of the control group; the results revealed differences in voice quality, phoneme-level pronunciation, prosody, glottal source, and aerodynamic parameters.","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115095684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Babita Saxena, Sunita Arora, K. Arora, Hemant Keshwal
{"title":"Acoustical Analysis of Speech of ASD Children and Typically Developing Children","authors":"Babita Saxena, Sunita Arora, K. Arora, Hemant Keshwal","doi":"10.1109/O-COCOSDA202257103.2022.9997993","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997993","url":null,"abstract":"The aim of this paper is to analyze difference in speech patterns of Autism Spectrum Disorder (ASD) child and typically developing child. The speech of Hindi speaking children is recorded between age 3 to 12 years. The speech corpus includes nearly 50 sessions of speech recordings from 15 children. The data is collected for special education sessions from children as per availability. These recordings are carried out in special education training room which contains toys, flash cards and things required for different activities. The recordings are carried in the presence of surrounding background noise in order to capture the natural background noise. Further, the effects of developmental changes on the speech are analyzed using pitch, formant frequencies and intensity. This research is carried out to facilitate development of systems for automatic detection of autism and intervention.","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128151149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Speaking-Rate Effect On Prosodic Grammar Of Mandarin Read Speech","authors":"Yu Hong, Chen-Yu Chiang, Yih-Ru Wang, Sin-Horng Chen","doi":"10.1109/O-COCOSDA202257103.2022.9997893","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997893","url":null,"abstract":"The effect of speaking rate (SR) on the prosodic grammar of Mandarin read speech inferred previously is investigated. A speech corpus comprising four parallel subcorpora with different SR of fast, normal, medium and slow is used in the study. The changes of the break-type distributions at critical junctures of the syntactic patterns considered in the two sets of prosodic grammatical rules due to the SR change are explored. Based on the variations of break-type distribution, the SR influence for a juncture is characterized by three newly-defined matrices: prosodic boundary strength, occurrence of strong break, and non-paused break probability range. Experimental results showed that the SR influence varies wildly from juncture to juncture. For most junctures, the SR effect mainly lies in the occurrences of many BNP to BPW changes as SR decreases from fast to slow, while the two strong paused breaks of BPPh and BPG are affected slightly.","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123935461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Y. Liao, Jane S. Tsay, P. Kang, Hui-Lu Khoo, Le-Kun Tan, Li-Chen Chang, Un-Gian Iunn, Huang-Lan Su, Tsun-guan Thiann, Hak-Khiam Tiun, Su-Lian Liao
{"title":"Taiwanese Across Taiwan Corpus And Its Applications","authors":"Y. Liao, Jane S. Tsay, P. Kang, Hui-Lu Khoo, Le-Kun Tan, Li-Chen Chang, Un-Gian Iunn, Huang-Lan Su, Tsun-guan Thiann, Hak-Khiam Tiun, Su-Lian Liao","doi":"10.1109/O-COCOSDA202257103.2022.9997977","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997977","url":null,"abstract":"Taiwanese across Taiwan (TAT) corpus is the first large-scale and publicly released Taiwanese speech corpus which represents the modern Taiwanese around Taiwan. This paper briefly reviews the TAT corpus and a corresponding parallel Chinese, Hàn-Lô-Tâi-bûn, Tai-Luo and Péh-ōe-jī lexicon and demonstrate some of their potential applications including ASR, TTS and voice conversion. The corresponding pretrained ASR and TTS models, sample model usage codes and training scripts will also be released. More information could be found on the Formosa Speech in the Wild website: https: //sites. google. com/nycu.edu.tw/fsw.","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124254232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Convenor","authors":"","doi":"10.1109/o-cocosda202257103.2022.9998003","DOIUrl":"https://doi.org/10.1109/o-cocosda202257103.2022.9998003","url":null,"abstract":"","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129969191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Speech Labeling and Modeling Toolkit (SLMTK) Version 1.0","authors":"Chen-Yu Chiang, Wu-Hao Li, Yen-Ting Lin, Jia-Jyu Su, Wei-Cheng Chen, Cheng-Che Kao, Shu-Lei Lin, Pin-Han Lin, Shao-Wei Hong, Guan-Ting Liou, Wen-Yang Chang, Jen-Chieh Chiang, Yen-Ting Lin, Yih-Ru Wang, Sin-Horng Chen","doi":"10.1109/O-COCOSDA202257103.2022.9997860","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997860","url":null,"abstract":"This paper introduces the Speech Labeling and Modeling Toolkit version 1.0 (SLMTK 1.0), which facilitates automatic labeling of text and speech for constructing text-to-speech (TTS) systems and speech analysis. The SLMTK 1.0 supports mixed Mandarin-English speech and the associated texts. The following seven steps then process the inputs: 1) text analysis, 2) acoustic feature extraction, 3) linguistic-speech alignment, 4) integration of syllable-based linguistic and prosodic-acoustic features, 5) prosody labeling, 6) construction of prosody generation model, and 7) construction of acoustic models for speech synthesis. The outputs of the seven steps are, respectively, 1) linguistic labels, 2) acoustic features, 3) linguistic-speech alignment, 4) syllable-based linguistic and prosodic-acoustic features, 5) prosody tags, 6) prosody generation model, and 7) acoustic models for speech synthesis. The SLMTK 1.0 has been applied to constructing personalized TTS systems for augmentative and alternative communication. In addition, the toolkit has also been applied to phonetic and prosodic labeling of L2 Mandarin speech to facilitate prosody analysis studies. The SLMTK 1.0 is available at https://slmtk.ce.ntpu.edu.tw for non-commercial use and welcomes all parties to enrich the functions of the SLMTK.","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132166159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Designing a Speaking Assessment Task Using Elicited Imitation to Build a Korean Learner Corpus","authors":"Chang-kyung Song, Hye Yun Jeong, Ho-Jung Kim","doi":"10.1109/O-COCOSDA202257103.2022.9997881","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997881","url":null,"abstract":"In this study, we propose an L2 Korean-speaking assessment task that uses elicited imitation (EI) as a tool to build an L2 Korean learner corpus. The corpus in this study differs from other Korean learner corpora as it is meant for use as a language teaching tool. Consequently, several speaking assessment tasks linked to accredited L2 Korean proficiency tests were performed to collect a large amount of speech data from learners of various nationalities. EI is used to measure language proficiency and has the advantage of being able to explore the spoken interlanguage of learners. For this study, we designed and proposed a Korean EI task and showed how it can be used, including scoring it. We also explained how it can be validated in the future and used to build an L2 Korean learner corpus.","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128748020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nattapong Kurpukdee, K. Thangthai, Vataya Chunwijitra, P. Chootrakool, S. Kasuriya
{"title":"NASAM 2.0: Cleft-Palate Speech Assessment Application","authors":"Nattapong Kurpukdee, K. Thangthai, Vataya Chunwijitra, P. Chootrakool, S. Kasuriya","doi":"10.1109/O-COCOSDA202257103.2022.9997825","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997825","url":null,"abstract":"This paper describes the incremental development of Naso-ariticulometer (NASAM) equipment for assessing children with cleft lip and palate pronunciation. The NASAM collects patients’ words and sentences, predicts phoneme sequences, and delivers pronunciation and nasality scores. This program faces a number of issues, including identifying children’s speech, applying automatic phoneme recognition to exact speech evaluation, and developing the application’s UI/UX for both children and language and speech assessors. This study focuses on enhancing acoustic modeling for Thai children aged 6 to 13 years old in the phoneme recognition module. We address the issue of determining an acceptable acoustic characteristic for children’s speech and compare acoustic model training methods. The phone error rate (PER) using collected speech from 75 cleft children and 104 normal children is used to test the acoustic models. The experimental results show that the vocal tract length normalization method provides the best PER in normal children, resulting in a 19.17 percent relative error reduction from the baseline, while Mel-filter bank and pitch performs well in cleft children, resulting in a 4.61 percent relative error reduction from the baseline. Additionally, we conducted a satisfaction poll during the function test and discovered that the most pleasing response was 42 percent.","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116892673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"List of Papers","authors":"T. Valk","doi":"10.4282/sosj.18.52","DOIUrl":"https://doi.org/10.4282/sosj.18.52","url":null,"abstract":"van der Valk, T. 2019. Genomics of population decline. Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology 1822. 57 pp. Uppsala: Acta Universitatis Upsaliensis. ISBN 978-91-513-0684-1. With human populations forecasted to grow in the next decades, many mammals face increasing anthropogenic threats. The consequential population declines are a precursor to extinctions, as small populations are not only more sensitive to stochastic events, but reduction in population size is generally also followed by a decrease in genetic diversity, which in turn reduces adaptive potential and fitness of the population. By using molecular methods I aimed to estimate the magnitude of the genomic consequences as a result of rapid population declines with a focus on the endangered eastern gorillas. First, I genotyped Grauer’s gorilla (Gorilla beringei graueri) faecal samples, which revealed lower genetic diversity and high differentiation in the peripheral compared to the central populations, indicating a strong effect of genetic drift and limited gene flow among the small, isolated forest fragments (Chapter 1). Next, by using a target capture approach I obtained complete mitochondrial genomes from degraded Grauer’s and mountain (Gorilla beringei beringei) gorilla faecal and museum samples (Chapter 2) which showed a loss of mitochondrial diversity within the last century in Grauer’s gorillas, mainly driven by the extinction of peripheral populations (Chapter 3). Genome-wide sequence data from historical samples suggests that this loss has also affected the nuclear genome, as modern Grauer’s gorillas carry on average more genetic variants with putatively negative fitness consequences than historically. No significant temporal changes were observed in the closely related mountain gorillas, which might be due to their contrasting demographic history (Chapter 4). I then switched study species to the endangered Dryas monkey and find that, despite its possible small population size, the current Dryas monkey population is genetically diverse with low levels of inbreeding and as such likely viable in the long-term if appropriate conservation measures are taken (Chapter 5). Finally, I aimed to estimate the strength of genetic purging across a range of mammalian species. This revealed that although genetic purging might be common among endangered species, it mainly acts on long evolutionary time scales with limited strength during the rapid population declines as experienced by many species today (Chapter 6).","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117334963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bao Thang Ta, Xuan Vuong Dang, Quang Tien Duong, Nhat Minh Le, Van Hai Do
{"title":"Improving Vietnamese Accent Recognition Using ASR Transfer Learning","authors":"Bao Thang Ta, Xuan Vuong Dang, Quang Tien Duong, Nhat Minh Le, Van Hai Do","doi":"10.1109/O-COCOSDA202257103.2022.9997947","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997947","url":null,"abstract":"Accent Recognition (AR) is a critical task in voice-controlled systems. If accent information is known in advance, voice-controlled systems can switch to a suitable accent-specific mode to improve their performance and user experience. However, available accent datasets, especially Vietnamese, are relatively small, making AR very challenging. To deal with these drawbacks, this paper proposes a transfer learning method using pretrained ASR models for Vietnamese accent recognition. This helps the system utilize available speech recognition systems while capturing implicit linguistic and phonetic information learned in ASR to improve its performance. Several experiments were conducted on a Vietnamese 8kHz telephone call dataset, which showed a significant improvement of the proposed system over existing Vietnamese AR models.","PeriodicalId":220366,"journal":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114220022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}