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

筛选
英文 中文
Nict-Tib1: A Public Speech Corpus Of Lhasa Dialect For Benchmarking Tibetan Language Speech Recognition Systems Nict-Tib1:用于对标藏语语音识别系统的拉萨方言公共语料库
Kak Soky, Zhuo Gong, Sheng Li
{"title":"Nict-Tib1: A Public Speech Corpus Of Lhasa Dialect For Benchmarking Tibetan Language Speech Recognition Systems","authors":"Kak Soky, Zhuo Gong, Sheng Li","doi":"10.1109/O-COCOSDA202257103.2022.9997917","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997917","url":null,"abstract":"The Lhasa dialect is the primary Tibetan dialect, with the most speakers in Tibet and the most extensive written scripts over its lengthy history. Studying speech recognition methods in the Lhasa dialect significantly conserves Tibet’s distinctive linguistic variety. Previous research on Tibetan speech recognition focused on academic research on non-public datasets, e.g., selecting phone-level acoustic modeling units and incorporating tonal information, but had less contribution to limited data for the community. To solve the low-resource data problem, we introduce the NICT-Tib1 (phase1) database, a new open-sourced database for the Lhasa dialect. We further update benchmark systems under the monolingual and multilingual settings, respectively. Experimental results show that the performances of these models are consistent with previous work. We believe our work will promote the existing speech recognition research on the Tibetan language, and other low-resource languages.","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":"44 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":"116399108","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}
引用次数: 1
MNASR: A Free Speech Corpus For Mongolian Speech Recognition And Accompanied Baselines 一个用于蒙古语语音识别的自由语料库
Yihao Wu, Yonghe Wang, Hui Zhang, F. Bao, Guanglai Gao
{"title":"MNASR: A Free Speech Corpus For Mongolian Speech Recognition And Accompanied Baselines","authors":"Yihao Wu, Yonghe Wang, Hui Zhang, F. Bao, Guanglai Gao","doi":"10.1109/O-COCOSDA202257103.2022.9997919","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997919","url":null,"abstract":"Thanks to the development of deep learning and the emergence of open source data sets, automatic speech recognition (ASR) has made great strides in mainstream languages such as Chinese and English. However, the research of ASR in Mongolian and other minority languages lags far behind the mainstream, due to low attention and limited open source data sets. To promote the development of new models and new methods for Mongolian ASR, this paper releases the MnASR database which contains 345 hours of Mongolian speech signal and the corresponding transcription. MnASR is the largest publicly available and free Mongolian speech database so far. Speech recognition baselines are made public at the same time. Both the database and the accompanied baselines are free for research purpose.","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":"23 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":"128110925","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}
引用次数: 0
Nasality in Zhangzhou: Distribution and Constraint 漳州鼻音的分布与制约
Yishan Huang
{"title":"Nasality in Zhangzhou: Distribution and Constraint","authors":"Yishan Huang","doi":"10.1109/O-COCOSDA202257103.2022.9997828","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997828","url":null,"abstract":"This study explores the distribution and constraint of nasality in Zhangzhou Southern Min spoken in Southern China. This dialect is observed employing the nasality in an ultimately dynamic, diverse but also severely constrained fashion. Vowels can be nasalised phonemically; nasals can be nuclei; the nasality can change the airstream mechanism and phonation of syllable onsets; a three-way nasal coda contrast can be identified but they appear to be complementary with obstruent codas conditioned by tones, while as many as 71% of theoretically possible nasality-featured syllables are prohibited from occurring in utterances. This exploration broadens our understanding of nasality as an important phenomenon in Southern China while contributing important empirical data to the typology of nasality in world languages.","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":"42 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":"121031662","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}
引用次数: 0
an automated speech recognition system for phonological awareness of kindergarten students in filipino 用于幼儿园学生菲律宾语语音意识的自动语音识别系统
Jazzmin R. Maranan
{"title":"an automated speech recognition system for phonological awareness of kindergarten students in filipino","authors":"Jazzmin R. Maranan","doi":"10.1109/O-COCOSDA202257103.2022.9997854","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997854","url":null,"abstract":"Phonological awareness is the ability to hear and attend to different units (e.g. syllables, onset and rime, and phonemes) of language. It is an essential aspect of a child’s learning development as it is a predictor of a child’s success in reading and spelling. The implemented phonological awareness system includes a Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) based automated speech recognizer with pitch prosody-based data augmentation and vocal tract length normalization for children’s phonological awareness skill training and assessment. This study found that the use of pitch prosody-based augmentation is efficient in addressing the pitch and formant mismatch between the trained adult utterances and tested children’s utterances which entailed a WER of 15.08% or an increase in accuracy by 5.16% in comparison to the baseline system. The vocal tract length normalization (VTLN) adaptation did not show much significant improvement to the augmented system as the accuracy only increased by 0.12% or a WER of 14.96%.","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":"37 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":"123083871","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}
引用次数: 1
Building A Speech Corpus Of Children With Cochlear Implants Via An Enhanced Metadata Structure 基于增强元数据结构构建人工耳蜗儿童语音语料库
Seonwoo Lee, Sunhee Kim, Minhwa Chung
{"title":"Building A Speech Corpus Of Children With Cochlear Implants Via An Enhanced Metadata Structure","authors":"Seonwoo Lee, Sunhee Kim, Minhwa Chung","doi":"10.1109/O-COCOSDA202257103.2022.9997935","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997935","url":null,"abstract":"This paper introduces a pilot speech corpus of 8 children with cochlear implant (CI) and proposes an enhanced metadata structure. The corpus is annotated with transcriptions and speech error patterns. A metadata structure for the corpus is proposed based on a meta-analysis of patient-related information included in studies on children with CI and a survey administered to speech and language pathologists asking clinical importance of given information. Then the results of the meta-analysis and the survey are combined to prioritize the patient-related information. The results show that the following elements are highly recommended: chronological age, implantation age, gender, duration of CI use, post-operational hearing threshold, onset time of hearing loss, information about assisting devices, pre-operational hearing threshold, speech perception performance, information about multiple disorders, and information about hearing aid. Particularly, the first four are the elements expected to be included in the speech corpus of children with CI.","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":"59 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":"124548377","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}
引用次数: 1
Experimentation Of Various Preprocessing Pipelines For Sentiment Analysis On Twitter Data About New Indonesia’s Capital City Using SVM And CNN 使用SVM和CNN对印尼新首都Twitter数据进行情感分析的各种预处理管道实验
Siska Pebiana, N. Hidayati, Dian Isnaeni Nurul Afra, Elvira Nurfadhilah, Harnum A. Prafitia, Junanto Prihantoro, Radhiyatul Fajri, M. T. Uliniansyah, Agung Santosa, Lyla Ruslana Aini, Yosi Sahreza, Aulia Haritsuddin Karisma Muhammad Subekti, Josua Geovani Pinem, Muhammad Reza Alfin, Agung Septadi, Siti Shaleha, G. Wibowanto, Asril Jarin, Gunarso, Andi Djalal Latief, Hammam Riza
{"title":"Experimentation Of Various Preprocessing Pipelines For Sentiment Analysis On Twitter Data About New Indonesia’s Capital City Using SVM And CNN","authors":"Siska Pebiana, N. Hidayati, Dian Isnaeni Nurul Afra, Elvira Nurfadhilah, Harnum A. Prafitia, Junanto Prihantoro, Radhiyatul Fajri, M. T. Uliniansyah, Agung Santosa, Lyla Ruslana Aini, Yosi Sahreza, Aulia Haritsuddin Karisma Muhammad Subekti, Josua Geovani Pinem, Muhammad Reza Alfin, Agung Septadi, Siti Shaleha, G. Wibowanto, Asril Jarin, Gunarso, Andi Djalal Latief, Hammam Riza","doi":"10.1109/O-COCOSDA202257103.2022.9997982","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997982","url":null,"abstract":"Selecting the sequence of pre-processing stages to obtain the best data for subsequent processes is still challenging. We have conducted a series of experiments with various sequences of pre-processing methods to acquire the best data. For the experiments, we used 12. 5K Indonesian Twitter on the new capital city of Indonesia (IKN) and 16. 2M monolingual text. We compared the manual labeling results with the outputs of SVM and CNN, which use the word-embedding feature generated by Word2Vec. The proposed pre-processing pipeline can be used as a reference for sentiment analysis research using Indonesian social media data. The best experimental results show a better F-1 value in SVM with B.2 pipeline (normalized word, stop word) is 69.32% and CNN with B.3 pipeline (normalized word, stop word, stemming) is 73.03%.","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":"26 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":"116083033","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}
引用次数: 4
A Corpus-Based Analysis Of Age-Related Changes In The Acoustic Features Of Elderly To Super Elderly Speech 基于语料库的老年至超老年语音声学特征年龄变化分析
Meiko Fukuda, Masakazu Sugiyama, Ryota Nishimura, Y. Iribe, Kazumasa Yamamoto, N. Kitaoka
{"title":"A Corpus-Based Analysis Of Age-Related Changes In The Acoustic Features Of Elderly To Super Elderly Speech","authors":"Meiko Fukuda, Masakazu Sugiyama, Ryota Nishimura, Y. Iribe, Kazumasa Yamamoto, N. Kitaoka","doi":"10.1109/O-COCOSDA202257103.2022.9997946","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997946","url":null,"abstract":"Speech recognition technology is a convenient modality for elderly people with limited dexterity and eyesight since it allows them to operate smartphones and other devices, but speech recognition accuracy declines as people get older. Our corpus of elderly Japanese speech, called EARS (Elderly Adults Read Speech), includes many speakers over 80 years old, and we have used it to create acoustic models which improve recognition accuracy for elderly speech [1]. Although the acoustic features of elderly people’s speech differs from those adults [2, 3], the studies compared the acoustic features of the speech of elderly and super elderly Japanese people are not so many. In this paper, we investigated age-related changes in fundamental frequency (Fo), formant frequencies, laryngeal noise, MFCCs and vowel centralization in elderly to super elderly speakers (60-98 years old), using speech data from the EARS corpus and the S-JNAS corpus of elderly Japanese speech. We found that the speech of both genders exhibited an increase in F1 and decrease in F2 of the vowel/i, some similarities in mean and standard deviation in MFCCs, and a decrease in the mean and standard deviation of shimmer with increasing age. In contrast, different aging-related dynamics were observed for male and female speakers in fundamental frequency, formant frequencies other than those listed above, vowel centralization, most other MFCCs.","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":"48 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":"121759121","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}
引用次数: 0
Production and Perception of Intonation Features by Cantonese EFL Learners 粤语学习者语调特征的产生与感知
Chenyang Zhao, Ziyu Xiong, Ai-jun Li
{"title":"Production and Perception of Intonation Features by Cantonese EFL Learners","authors":"Chenyang Zhao, Ziyu Xiong, Ai-jun Li","doi":"10.1109/O-COCOSDA202257103.2022.9997874","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997874","url":null,"abstract":"This paper, on the basis of AM intonation theory, aims to investigate Cantonese EFL English learners’ production and perception of intonation features, including the phonological features of nuclear accent and boundary tone, as well as the placement of nuclear accent. Altogether 252 sentences, including 136 statements and 116 yes-no questions were collected, from which it was found that learners tended to use H* and L* in statements and yes-no questions respectively, and these two tone types were also the ones that are easiest to be perceived. Interactive relationship between learners’ production and perception were discussed. The results will give guidance to the EFL intonation teaching for Cantonese learners.","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":"3 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":"126452294","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}
引用次数: 0
Sponssors Sponssors
{"title":"Sponssors","authors":"","doi":"10.1109/o-cocosda202257103.2022.9998006","DOIUrl":"https://doi.org/10.1109/o-cocosda202257103.2022.9998006","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":"48 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":"132049366","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}
引用次数: 0
Patterns of Vowel Production in the Speakers of Sanskrit Language 梵语使用者元音产生的模式
Pooja Gambhir, A. Dev, Poonam Bansal
{"title":"Patterns of Vowel Production in the Speakers of Sanskrit Language","authors":"Pooja Gambhir, A. Dev, Poonam Bansal","doi":"10.1109/O-COCOSDA202257103.2022.9997868","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997868","url":null,"abstract":"Sanskrit is a lexically productive language that undergoes euphonic assimilation of phones at word boundaries. It exhibits variations in pronunciations and spelling conventions. This paper introduces the Vowel Triangle plot of Sanskrit vowel-sounds pronunciations using their F1-F2 values generated from PRAAT software. The work was conducted on spoken word utterances (single utterance) of eight male and eight female subjects, fluent in speaking Sanskrit Shlokas. The paper also presents visible and notable similarities and differences in the spoken Sanskrit and Hindi vowel systems through their Spectrogram-based Vowel Triangle System analysis. Since there has been a developing cultural trend of treating Hindi as the sole inheritor of Sanskrit because of religious ideologies, it is often assumed that the language structure of both the Sanskrit and Hindi languages is the same or similar in most cases. However, in the context of a Speech community, linguistic research has shown considerable differences in the phonetic and phonological views of the languages, even between spoken Hindi and Sanskrit. This study can further help in future studies of under-resourced language and speech recognition approaches, considering their phonetic and phonological insights. These inferences demand an extensive study of phonemic and intonational Sanskrit language due to their originating influence in the realistic environment.","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":"129 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":"123597642","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}
引用次数: 1
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书