This study investigates durational and spectral variation in syllable-onset /l/s dependent on voicing in the coda. 1560 pairs of (C)lVC monosyllables differing in the voicing of the final stop were read by 4 British English speakers. Onset /l/ was longer before voiced than voiceless codas, and darker (for 3 speakers) as measured by F2 frequency and spectral centre of gravity. Differences due to other variables (lexical status, isolation/carrier context, syllable onset, vowel quality and regional accent) are outlined. It is proposed that coda voicing is a feature associated with the whole syllable, phonetically implemented as a variety of properties spread throughout the syllabic domain. Implications for word recognition are outlined.
{"title":"Syllable-onset acoustic properties associated with syllable-coda voicing","authors":"N. Nguyen, S. Hawkins","doi":"10.21437/ICSLP.1998-736","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-736","url":null,"abstract":"This study investigates durational and spectral variation in syllable-onset /l/s dependent on voicing in the coda. 1560 pairs of (C)lVC monosyllables differing in the voicing of the final stop were read by 4 British English speakers. Onset /l/ was longer before voiced than voiceless codas, and darker (for 3 speakers) as measured by F2 frequency and spectral centre of gravity. Differences due to other variables (lexical status, isolation/carrier context, syllable onset, vowel quality and regional accent) are outlined. It is proposed that coda voicing is a feature associated with the whole syllable, phonetically implemented as a variety of properties spread throughout the syllabic domain. Implications for word recognition are outlined.","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131233228","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}
In this paper, we propose a keyword extraction method for dictation of radio news which consists of several domains. In our method, newspaper articles which are au-tomatically classi(cid:12)ed into suitable domains are used in order to calculate feature vectors. The feature vectors show term-domain interdependence and are used for selecting a suitable domain of each part of radio news. Keywords are extracted by using the selected domain. The results of keyword extraction experiments showed that our methods are e(cid:11)ective for keyword extraction of radio news.
{"title":"Keyword extraction of radio news using domain identification based on categories of an encyclopedia","authors":"Yoshimi Suzuki, Fumiyo Fukumoto, Y. Sekiguchi","doi":"10.21437/ICSLP.1998-508","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-508","url":null,"abstract":"In this paper, we propose a keyword extraction method for dictation of radio news which consists of several domains. In our method, newspaper articles which are au-tomatically classi(cid:12)ed into suitable domains are used in order to calculate feature vectors. The feature vectors show term-domain interdependence and are used for selecting a suitable domain of each part of radio news. Keywords are extracted by using the selected domain. The results of keyword extraction experiments showed that our methods are e(cid:11)ective for keyword extraction of radio news.","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130922119","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}
F. Berthommier, H. Glotin, Emmanuel Tessier, H. Bourlard
Keywords: speech Reference EPFL-CONF-82470 URL: http://publications.idiap.ch/downloads/reports/1998/glotin-icslp98.pdf Record created on 2006-03-10, modified on 2017-05-10
{"title":"Interfacing of CASA and partial recognition based on a multistream technique","authors":"F. Berthommier, H. Glotin, Emmanuel Tessier, H. Bourlard","doi":"10.21437/ICSLP.1998-317","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-317","url":null,"abstract":"Keywords: speech Reference EPFL-CONF-82470 URL: http://publications.idiap.ch/downloads/reports/1998/glotin-icslp98.pdf Record created on 2006-03-10, modified on 2017-05-10","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131245521","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}
Accurate estimation of segmental durations is crucial for natural-sounding text-to-speech (TTS) synthesis. This paper presents a model of vowel duration used in the Bell Labs JapaneseTTS system. We describe the constraints on vowel devoicing, and effects of factors such as phone identity, surrounding phone identities, accentuation, syllabic structure, and phrasal position on the duration of both long and short vowels. A Sum-of-Products ap-proach is used to model key interactions observed in the data, and to predict values of factor combinations not found in the speech database. We report root mean squared deviations between observed and predicted durations ranging from 8 to 15 ms, and an overall correlation of 0.89. in Tokyo Japanese read speech for in Labs JapaneseTTS
{"title":"Modeling vowel duration for Japanese text-to-speech synthesis","authors":"J. Venditti, J. V. Santen","doi":"10.21437/ICSLP.1998-46","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-46","url":null,"abstract":"Accurate estimation of segmental durations is crucial for natural-sounding text-to-speech (TTS) synthesis. This paper presents a model of vowel duration used in the Bell Labs JapaneseTTS system. We describe the constraints on vowel devoicing, and effects of factors such as phone identity, surrounding phone identities, accentuation, syllabic structure, and phrasal position on the duration of both long and short vowels. A Sum-of-Products ap-proach is used to model key interactions observed in the data, and to predict values of factor combinations not found in the speech database. We report root mean squared deviations between observed and predicted durations ranging from 8 to 15 ms, and an overall correlation of 0.89. in Tokyo Japanese read speech for in Labs JapaneseTTS","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133605068","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}
In this paper we propose a set of features based on group delay spectrum for speech recognition systems. These features appear to be more robust to channel variations and environmental changes compared to features based on Melspectral coefficients. The main idea is to derive cepstrumlike features from group delay spectrum instead of deriving them from power spectrum. The group delay spectrum is computed from modified auto-correlation-like function. The effectiveness of the new feature set is demonstrated by the results of both speaker-independent (SI) and speaker-dependent (SD) recognition tasks. Preliminary results indicate that using the new features, we can obtain results comparable to Mel cepstra and PLP cepstra in most of the cases and a slight improvement in noisy cases. More optimization of the parameters is needed to fully exploit the nature of the new features.
{"title":"Robust features for speech recognition systems","authors":"A. Bayya, B. Yegnanarayana","doi":"10.21437/ICSLP.1998-316","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-316","url":null,"abstract":"In this paper we propose a set of features based on group delay spectrum for speech recognition systems. These features appear to be more robust to channel variations and environmental changes compared to features based on Melspectral coefficients. The main idea is to derive cepstrumlike features from group delay spectrum instead of deriving them from power spectrum. The group delay spectrum is computed from modified auto-correlation-like function. The effectiveness of the new feature set is demonstrated by the results of both speaker-independent (SI) and speaker-dependent (SD) recognition tasks. Preliminary results indicate that using the new features, we can obtain results comparable to Mel cepstra and PLP cepstra in most of the cases and a slight improvement in noisy cases. More optimization of the parameters is needed to fully exploit the nature of the new features.","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133693995","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}
We describe the attempt to synthesize emotional speech with a concatenative speech synthesizer using a parameter space cover-ing not only f0, duration and amplitude, but also voice quality parameters, spectral energy distribution, harmonics-to-noise ratio, and articulatory precision. The application of these extended parameter set offers the possibility to combine the high segmental quality of concatenative synthesis with a wider range of control settings needed for the synthesis of natural affected speech.
{"title":"Generating emotional speech with a concatenative synthesizer","authors":"E. Rank, Hannes Pirker","doi":"10.21437/ICSLP.1998-134","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-134","url":null,"abstract":"We describe the attempt to synthesize emotional speech with a concatenative speech synthesizer using a parameter space cover-ing not only f0, duration and amplitude, but also voice quality parameters, spectral energy distribution, harmonics-to-noise ratio, and articulatory precision. The application of these extended parameter set offers the possibility to combine the high segmental quality of concatenative synthesis with a wider range of control settings needed for the synthesis of natural affected speech.","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133405570","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}
In this study a data-based approach to intonation modeling is presented. The model incorporates knowledge from intonation theories like the expected types of F 0 movements and syllable anchoring. The knowledge is integrated into the model using an appropriate approximation function for F 0 parametrization. The F 0 parameters that result from the parametrization are predicted from a set of features using neural nets. The quality of the generated contours is assessed by means of numerical measures and perception tests. They show that the basic hypotheses about intonation description and modeling are in principle correct and that they have the potential to be successfully applied to speech synthesis. We argue for a clear interface with a linguistic description (using pitch-accent and boundary labels as input) and discourse structure (using pitch-range normalized F 0 parameters), even though current text-to-speech systems usually still do not have the capability to predict most of the appropriate information.
{"title":"Describing intonation with a parametric model","authors":"G. Möhler","doi":"10.21437/ICSLP.1998-59","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-59","url":null,"abstract":"In this study a data-based approach to intonation modeling is presented. The model incorporates knowledge from intonation theories like the expected types of F 0 movements and syllable anchoring. The knowledge is integrated into the model using an appropriate approximation function for F 0 parametrization. The F 0 parameters that result from the parametrization are predicted from a set of features using neural nets. The quality of the generated contours is assessed by means of numerical measures and perception tests. They show that the basic hypotheses about intonation description and modeling are in principle correct and that they have the potential to be successfully applied to speech synthesis. We argue for a clear interface with a linguistic description (using pitch-accent and boundary labels as input) and discourse structure (using pitch-range normalized F 0 parameters), even though current text-to-speech systems usually still do not have the capability to predict most of the appropriate information.","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133107530","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}
In this paper the performance of an automatic transcription tool is evaluated. The transcription tool is a Continuous Speech Recognizer (CSR) running in forced recognition mode. For evaluation the performance of the CSR was compared to that of nine expert listeners. Both man and the machine carried out exactly the same task: deciding whether a segment was present or not in 467 cases. It turned out that the performance of the CSR is comparable to that of the experts.
{"title":"The selection of pronunciation variants: comparing the performance of man and machine","authors":"J. Kessens, M. Wester, C. Cucchiarini, H. Strik","doi":"10.21437/ICSLP.1998-604","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-604","url":null,"abstract":"In this paper the performance of an automatic transcription tool is evaluated. The transcription tool is a Continuous Speech Recognizer (CSR) running in forced recognition mode. For evaluation the performance of the CSR was compared to that of nine expert listeners. Both man and the machine carried out exactly the same task: deciding whether a segment was present or not in 467 cases. It turned out that the performance of the CSR is comparable to that of the experts.","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131409908","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}
The ability to understand speech in 27 hearing impaired children was assessed using the BKB/A Picture Related Sentence test for children. The mean sentence score for the group was 72% (range 100-18%). Language scores (CELF-R) and Verbal Scale IQ (WISC-R) scores were significantly below the norm (72.8 and 89.2 respectively). Performance Scale IQ scores were slightly above the norm (106.3). Sentences scores were correlated significantly with language score (r = 0.49). Further investigation showed that the predicability of language scores could be improved when sensation level was taken into account. Sensation level was negatively correlated with language scores (r = - 0.51), demonstrating that children with better language abilities perceived speech at relatively lower intensity levels. The observed sensation levels from the group were compared with the expected levels for normally hearing children. This difference measure yielded a correlation coefficient of - 0.73 with language scores.
{"title":"Predicting language scores from the speech perception scores of hearing-impaired children","authors":"L. Martin, J. Bench","doi":"10.21437/ICSLP.1998-786","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-786","url":null,"abstract":"The ability to understand speech in 27 hearing impaired children was assessed using the BKB/A Picture Related Sentence test for children. The mean sentence score for the group was 72% (range 100-18%). Language scores (CELF-R) and Verbal Scale IQ (WISC-R) scores were significantly below the norm (72.8 and 89.2 respectively). Performance Scale IQ scores were slightly above the norm (106.3). Sentences scores were correlated significantly with language score (r = 0.49). Further investigation showed that the predicability of language scores could be improved when sensation level was taken into account. Sensation level was negatively correlated with language scores (r = - 0.51), demonstrating that children with better language abilities perceived speech at relatively lower intensity levels. The observed sensation levels from the group were compared with the expected levels for normally hearing children. This difference measure yielded a correlation coefficient of - 0.73 with language scores.","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133782634","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}
This paper discusses the problem of handling “foreign” speech sounds in Swedish speech technology systems, in particular speech synthesis. A production study is made, where it is shown that Swedish ...
本文讨论了瑞典语语音技术系统中“外来”语音的处理问题，特别是语音合成问题。一项生产研究表明，瑞典…
{"title":"How to handle \"foreign\" sounds in Swedish text-to-speech conversion: approaching the 'xenophone' problem","authors":"R. Eklund, Anders Lindström","doi":"10.21437/ICSLP.1998-54","DOIUrl":"https://doi.org/10.21437/ICSLP.1998-54","url":null,"abstract":"This paper discusses the problem of handling “foreign” speech sounds in Swedish speech technology systems, in particular speech synthesis. A production study is made, where it is shown that Swedish ...","PeriodicalId":117113,"journal":{"name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115376217","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：