2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)最新文献
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357869
Askar Rozi, Dong Wang, Zhiyong Zhang, T. Zheng
Few research has been conducted on Uyghur speaker recognition. Among the limited works, researchers usually collect small speech databases and publish results based on their own private data. This `close-door evaluation' makes most of the publications doubtable. This paper publishes an open and free speech database THUYG-20 SRE and a benchmark for Uyghur speaker recognition. The database is based on the THUYG-20 speech corpus we recently released, and the benchmark involves recognition tasks with various training/enrollment/test conditions. We provide a complete description for the database as well as the benchmark, and present an i-vector baseline system constructed using the Kaldi toolkit.
关于维吾尔语说话人识别的研究很少。在有限的工作中，研究人员通常收集小型语音数据库，并根据自己的私人数据发表结果。这种“闭门造车的评估”使得大多数出版物都值得怀疑。本文发布了一个开放的自由言论数据库thuyg - g - SRE和一个维吾尔语说话人识别基准。该数据库基于我们最近发布的THUYG-20语音语料库，基准涉及各种培训/注册/测试条件下的识别任务。我们提供了数据库和基准的完整描述，并提出了使用Kaldi工具包构建的i向量基线系统。
{"title":"An open/free database and Benchmark for Uyghur speaker recognition","authors":"Askar Rozi, Dong Wang, Zhiyong Zhang, T. Zheng","doi":"10.1109/ICSDA.2015.7357869","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357869","url":null,"abstract":"Few research has been conducted on Uyghur speaker recognition. Among the limited works, researchers usually collect small speech databases and publish results based on their own private data. This `close-door evaluation' makes most of the publications doubtable. This paper publishes an open and free speech database THUYG-20 SRE and a benchmark for Uyghur speaker recognition. The database is based on the THUYG-20 speech corpus we recently released, and the benchmark involves recognition tasks with various training/enrollment/test conditions. We provide a complete description for the database as well as the benchmark, and present an i-vector baseline system constructed using the Kaldi toolkit.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129019285","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}
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357890
Hong Chen, Weijmg Zhou
In acoustic study of English diphthongs, one feature governs the diphthong formant movement is the diphthongization feature-formant rate of change. Acoustic analysis indicates that there are substantial differences on first and second formant rate of change between college EFL learners and RP speakers. Generally speaking, for fronting and backing diphthongs, change of vowel location in the production of college EFL learners are not as obvious and marked as RP speakers, that is to say, learners have trouble in sufficient realization of the gliding movement. While for centering dipthhongs, change of vowel location is excessive in the production of college EFL learners where is not necessary, and the degree of diphthongization is beyond standard realization.
{"title":"An experimental study of the production of English diphthongs by Chinese college EFL learners: An acoustic perspective","authors":"Hong Chen, Weijmg Zhou","doi":"10.1109/ICSDA.2015.7357890","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357890","url":null,"abstract":"In acoustic study of English diphthongs, one feature governs the diphthong formant movement is the diphthongization feature-formant rate of change. Acoustic analysis indicates that there are substantial differences on first and second formant rate of change between college EFL learners and RP speakers. Generally speaking, for fronting and backing diphthongs, change of vowel location in the production of college EFL learners are not as obvious and marked as RP speakers, that is to say, learners have trouble in sufficient realization of the gliding movement. While for centering dipthhongs, change of vowel location is excessive in the production of college EFL learners where is not necessary, and the degree of diphthongization is beyond standard realization.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134140982","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}
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357880
Yanyan Sui, Cuizhen Li
This paper studies the acoustic properties of segments in different syllable positions of words with tones in Standard Chinese. Through the investigation of monophthongs and aspirated stops in disyllabic words in broadcast news speech, gradient reduction is found for both vowels and consonants in the second syllable position-vowels tend to be centralized in the F1/F2 vowel space, and aspirated stops exhibit a continuum of reduction. The differentiation of syllable positions in the phonetic realization of segments is consistent with the prediction of the trochaic metrical structure hypothesis for Standard Chinese.
{"title":"Segment reduction in disyllabic words with tones in standard Chinese","authors":"Yanyan Sui, Cuizhen Li","doi":"10.1109/ICSDA.2015.7357880","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357880","url":null,"abstract":"This paper studies the acoustic properties of segments in different syllable positions of words with tones in Standard Chinese. Through the investigation of monophthongs and aspirated stops in disyllabic words in broadcast news speech, gradient reduction is found for both vowels and consonants in the second syllable position-vowels tend to be centralized in the F1/F2 vowel space, and aspirated stops exhibit a continuum of reduction. The differentiation of syllable positions in the phonetic realization of segments is consistent with the prediction of the trochaic metrical structure hypothesis for Standard Chinese.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128940852","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}
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357881
Jue Yu, D. Gibbon
We describe an inductive procedure for automatically parsing syllable sequences in speech annotations into Time Groups (TGs) based on deceleration and acceleration measures, rather than predefined units from the prosodic hierarchy. The effect of different minimal duration difference thresholds (MDDTs) on the size and relation of these TGs to different grammatical units, e.g. `word', `phrase', `sentence', is examined. The relative syllable isochrony in TGs is also determined with the nPVI measure. We found several non-trivial effects, demonstrating the plausibility of the methodology: (a) a stepwise, non-continuous relation between MDDT increases and number of induced TGs; (b) correspondence of induced TGs to sizes and ranks of grammatical units; (c) better correspondence with shorter phrasal units in the acceleration condition and longer discourse units in the deceleration condition; (d) comparability of relative isochrony using syllabic nPVI with the vocalic nPVI results from previous studies.
{"title":"Time Group types in Mandarin syllable annotations","authors":"Jue Yu, D. Gibbon","doi":"10.1109/ICSDA.2015.7357881","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357881","url":null,"abstract":"We describe an inductive procedure for automatically parsing syllable sequences in speech annotations into Time Groups (TGs) based on deceleration and acceleration measures, rather than predefined units from the prosodic hierarchy. The effect of different minimal duration difference thresholds (MDDTs) on the size and relation of these TGs to different grammatical units, e.g. `word', `phrase', `sentence', is examined. The relative syllable isochrony in TGs is also determined with the nPVI measure. We found several non-trivial effects, demonstrating the plausibility of the methodology: (a) a stepwise, non-continuous relation between MDDT increases and number of induced TGs; (b) correspondence of induced TGs to sizes and ranks of grammatical units; (c) better correspondence with shorter phrasal units in the acceleration condition and longer discourse units in the deceleration condition; (d) comparability of relative isochrony using syllabic nPVI with the vocalic nPVI results from previous studies.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130866026","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}
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357873
Bei Wang, C. Féry
This paper examines prosodic encoding of dual focus in Standard Chinese, that is, a sentence contains two foci. Five speakers read 10 SVO sentences with two lengths (short vs. long) in four focus conditions: initial, final, dual (initial+final) and neutral. Following results were obtained for the dual focus sentences: [1] There was an increase in F0 and word duration in both foci, and this to almost the same degree as their initial and final focus counterparts respectively; [2] The word following the first focus did not differ from its neutral and final counterparts in F0 and duration; [3] No prosodic boundary was inserted after the first focus and the two foci were realized in one intonational phrase. All these results held for both the short and the long sentences. From a theoretical perspective, culminativity (i.e. one metrical prominence per prosodic constituent) is violable in Chinese and focus assignment and phrasing are largely independent of each other.
{"title":"Dual-focus intonation in Standard Chinese","authors":"Bei Wang, C. Féry","doi":"10.1109/ICSDA.2015.7357873","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357873","url":null,"abstract":"This paper examines prosodic encoding of dual focus in Standard Chinese, that is, a sentence contains two foci. Five speakers read 10 SVO sentences with two lengths (short vs. long) in four focus conditions: initial, final, dual (initial+final) and neutral. Following results were obtained for the dual focus sentences: [1] There was an increase in F0 and word duration in both foci, and this to almost the same degree as their initial and final focus counterparts respectively; [2] The word following the first focus did not differ from its neutral and final counterparts in F0 and duration; [3] No prosodic boundary was inserted after the first focus and the two foci were realized in one intonational phrase. All these results held for both the short and the long sentences. From a theoretical perspective, culminativity (i.e. one metrical prominence per prosodic constituent) is violable in Chinese and focus assignment and phrasing are largely independent of each other.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115542485","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}
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357887
Peng Qin
This study offered a preliminary look at the acoustic and auditory performances in an isolated monosyllable environment of the three level tones (i.e. High, Mid and Low tones) in Thai via several relevant acoustic and perception experiments. The results show that Mid tone is the only one which can be accepted as a level tone either in production or in perception and Low tone has two main variants: low-level tone and low-falling tone. But it is quite questionable to continue to take High tone as a level tone because “level” as a sound feature cannot be pronounced and identified as a typical feature of High tone. A High tone is actually a “mid -high-level” tone. Also, the movement of contour is very important when perceiving High tone.
{"title":"The acoustic and auditory performances of the three Thai level tones","authors":"Peng Qin","doi":"10.1109/ICSDA.2015.7357887","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357887","url":null,"abstract":"This study offered a preliminary look at the acoustic and auditory performances in an isolated monosyllable environment of the three level tones (i.e. High, Mid and Low tones) in Thai via several relevant acoustic and perception experiments. The results show that Mid tone is the only one which can be accepted as a level tone either in production or in perception and Low tone has two main variants: low-level tone and low-falling tone. But it is quite questionable to continue to take High tone as a level tone because “level” as a sound feature cannot be pronounced and identified as a typical feature of High tone. A High tone is actually a “mid -high-level” tone. Also, the movement of contour is very important when perceiving High tone.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125381606","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}
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357861
R. Islam, Mingxing Xu, Yuchao Fan
This paper introduces the database of Traditional Chinese Opera for Music Genre Recognition, which is still a gap in our knowledge. The database contains different songs which are from the 14 most popular kinds of Chinese Opera, including Sichuan Opera, Beijing Opera, etc. Each Opera is then annotated between music, song and speech which are identified by acoustic waveform and spectral analysis. This breakdown is used to distinguish different types of operas. The database can be used for research concerning music genre recognition. Moreover this database can be used to analyze the relationship between the operas by comparing acoustic attributes, which can provide new perspectives and evidence for research in population migration, cultural evolution and other social investigation study in the historical development of Chinese opera.
{"title":"Chinese Traditional Opera database for Music Genre Recognition","authors":"R. Islam, Mingxing Xu, Yuchao Fan","doi":"10.1109/ICSDA.2015.7357861","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357861","url":null,"abstract":"This paper introduces the database of Traditional Chinese Opera for Music Genre Recognition, which is still a gap in our knowledge. The database contains different songs which are from the 14 most popular kinds of Chinese Opera, including Sichuan Opera, Beijing Opera, etc. Each Opera is then annotated between music, song and speech which are identified by acoustic waveform and spectral analysis. This breakdown is used to distinguish different types of operas. The database can be used for research concerning music genre recognition. Moreover this database can be used to analyze the relationship between the operas by comparing acoustic attributes, which can provide new perspectives and evidence for research in population migration, cultural evolution and other social investigation study in the historical development of Chinese opera.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131510187","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}
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357883
Ying Chen
This paper investigates the perceptual confusion pattern in the three coda nasals /-m, -n, -η/ in Southern Min for insight into the effect of tone on the identification of nasal place of articulation. A general hierarchy of perceptual confusability - m>-η>-n was found in the current set of data, which is compatible with the fact that /-m/ was lost first in the historical merger of coda nasals in Chinese. Tones with a high pitch at the ending point resulted in higher accuracy of nasal identification in complete syllables. However, there was no tonal effect on the identification of nasal murmur. Vowel duration and vowel-nasal formant transition were the perceptual cues that listeners mostly relied on.
{"title":"Exploring tonal effects on the perception of word-final nasals: A preliminary study in Southern Min","authors":"Ying Chen","doi":"10.1109/ICSDA.2015.7357883","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357883","url":null,"abstract":"This paper investigates the perceptual confusion pattern in the three coda nasals /-m, -n, -η/ in Southern Min for insight into the effect of tone on the identification of nasal place of articulation. A general hierarchy of perceptual confusability - m>-η>-n was found in the current set of data, which is compatible with the fact that /-m/ was lost first in the historical merger of coda nasals in Chinese. Tones with a high pitch at the ending point resulted in higher accuracy of nasal identification in complete syllables. However, there was no tonal effect on the identification of nasal murmur. Vowel duration and vowel-nasal formant transition were the perceptual cues that listeners mostly relied on.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127825089","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}
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357882
Xijing Luo, Jin-Song Zhang, Zuyan Wang, Hang Wang
Perceptually distinguishing between Mandarin alveolar nasal coda [n] and velar [η] are difficult for Japanese natives in learning Chinese as a second language (CSL). Discovering relations between acoustic cues and perceptual responses is important for studying CSL acquisition and computer-aided pronunciation teaching. In order to investigate the influences of nasal coda's lengths on nasal perception by Chinese and Japanese, two studies were conducted. One is a statistical comparison of Mandarin nasal codas' durations. The other one is an identification experiment in which subjects perceive stimuli with gradually-shortened nasal codas. Results reveal that the difference between durations of [n] and [η] is non-significant. Furthermore, nasal codas' length hardly affects Chinese subjects to identify nasal type, but it is a relatively great impact for Japanese. Slightly more correct responses are obtained when Japanese identify stimuli with longer codas, and those with shorter endings are more likely to be identified as non-nasals.
{"title":"Coda's duration on perception of mandarin syllables with alveolar/velar nasal endings by Japanese CSL learners","authors":"Xijing Luo, Jin-Song Zhang, Zuyan Wang, Hang Wang","doi":"10.1109/ICSDA.2015.7357882","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357882","url":null,"abstract":"Perceptually distinguishing between Mandarin alveolar nasal coda [n] and velar [η] are difficult for Japanese natives in learning Chinese as a second language (CSL). Discovering relations between acoustic cues and perceptual responses is important for studying CSL acquisition and computer-aided pronunciation teaching. In order to investigate the influences of nasal coda's lengths on nasal perception by Chinese and Japanese, two studies were conducted. One is a statistical comparison of Mandarin nasal codas' durations. The other one is an identification experiment in which subjects perceive stimuli with gradually-shortened nasal codas. Results reveal that the difference between durations of [n] and [η] is non-significant. Furthermore, nasal codas' length hardly affects Chinese subjects to identify nasal type, but it is a relatively great impact for Japanese. Slightly more correct responses are obtained when Japanese identify stimuli with longer codas, and those with shorter endings are more likely to be identified as non-nasals.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132246580","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}
Pub Date : 2015-10-01DOI: 10.1109/ICSDA.2015.7357885
S. Sinha, S. Agrawal, Aruna Jain
Regional dialect is a form of a language spoken by people in a particular geographical area. They can be distinguished by the pattern of pronunciation, grammar and the usage of words. Individual's regional association influences their speech characteristics. This uniqueness is supposed to be one of the major reasons for variability that can affect the performance of any speech recognizer. This paper presents an analysis of the first three formants, the fundamental frequency, and the pitch slope with the aim to investigate the influence of regional dialects. Four major Hindi dialects; Khari Boli, Bhojpuri, Haryanvi, and Bagheli were considered for this study on ten vowels. To study the co-articulation effect on vowels, this analysis was done at the word initial, middle and final positions. The database used for this work consists of read utterances of 30 male and 20 female speakers from each of the four dialects. The result of analysis indicates considerable differences between these acoustic features of four dialects.
{"title":"Influence of regional dialects on acoustic characteristics of Hindi vowels","authors":"S. Sinha, S. Agrawal, Aruna Jain","doi":"10.1109/ICSDA.2015.7357885","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357885","url":null,"abstract":"Regional dialect is a form of a language spoken by people in a particular geographical area. They can be distinguished by the pattern of pronunciation, grammar and the usage of words. Individual's regional association influences their speech characteristics. This uniqueness is supposed to be one of the major reasons for variability that can affect the performance of any speech recognizer. This paper presents an analysis of the first three formants, the fundamental frequency, and the pitch slope with the aim to investigate the influence of regional dialects. Four major Hindi dialects; Khari Boli, Bhojpuri, Haryanvi, and Bagheli were considered for this study on ten vowels. To study the co-articulation effect on vowels, this analysis was done at the word initial, middle and final positions. The database used for this work consists of read utterances of 30 male and 20 female speakers from each of the four dialects. The result of analysis indicates considerable differences between these acoustic features of four dialects.","PeriodicalId":290790,"journal":{"name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129830305","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：