中文文—语转换系统中多音字问题研究
|
摘要
计算机文-语转换技术(Text-to-Speech,简称TTS)指利用计算机程序将既定的可视文本信息转换成语音的过程。这一系统广泛地涉及了语言学、语音学、计算机编程、数字信号处理等领域,是一门综合了多学科多领域的技术项目。我们接触的拼音输入法、图书拼音排序检索、各种音序排序、汉语的语音教学软件的运用、各类电子产品的语音朗读功能的改进、自动介绍或者答复系统以及盲人用品和儿童玩具的开发、甚至包括机器人制造以及未来语音操控系统在各领域的实现,都离不开这一技术手段。作为一项高度要求理论性与实用性相结合的技术,TTS在产生之初就备受各学科学者的高度重视。如何提高TTS系统中语音合成的流畅度、自然度与准确率成为这一技术必须关注的焦点。其中,汉语多音字读音自动标注的准确率更成为文-语转换技术的难点之一。
本文的研究对象在于,确定《现代汉语词典》(第5版)(以下简称《现汉》)中921个多音字及其音项在CCL现代汉语语料库中的语用频率,以字频为基础,进而从语言学理论的角度出发,为TTS处理中多音字问题的解决提出一种新思路。
文章的主要内容包括三个部分,第一部分,对《现汉》中多音字的数目进行统计,确定以921个多音字为研究对象,并对每个多音字的词性及进行统计。第二部分,在CCL现代汉语语料库中对这921个多音字的字频进行语用频率统计。根据统计结果和累计频率的计算,最终将这些多音字分出高、中、低三个频级。对各频级的多音字每个音项的使用频率进行统计,分出高频音、低频音两个音级,对在语料库中只占1%的低频多音字采用常读音默认的方法进行处理。第三部分,对中、高频多音字进行分类,综合运用多音节词排除法、词性确定法和附带常用多音字词库法等方法进行处理。对那些各音项语用频率相当、词性区别不明显的可独立成词的多音字,则逐条梳理其所有语料,总结其出现的语境,为多音字构建规则。
Computer Text-to-Speech Technology (Text-to-Speech, referred to as TTS) refers to the use of computer programs to established visual text into speech process. Because of the system include linguistics, phonetics, computer programming, digital signal processing and other fields, it is a comprehensive multi-disciplinary technical projects in many fields.We touch input method, Library, various scheduling problems, the use of Chinese language teaching software, all kinds of electronic products to improve voice reading function to automatically introduce or reply system and the blind development of supplies and children's toys, and even robots manufacturing and future voice-control system to achieve in all areas,which are inseparable from the technical means. As a highly theoretical and practical combination of technology,TTS received the great attention from various disciplines and scholars at the beginning of language translation technology in the production.How to improve TTS’s speech synthesis fluency, naturalness and accuracy of the technology have become the focus of attention. Among them, the Chinese pronunciation of polyphonic accuracy of automatic tagging has become one of the difficulties language translation technology in the system of TTS.
Object of this paper is to determine the "Modern Chinese Dictionary" (5th Edition) (hereinafter referred to as "Modern Chinese ") in 921 polyphones and pronunciation items in the CCL of modern Chinese corpus, the Pragmatic frequency to frequency-based word, and then from the perspective of linguistic theory, a new idea comes up for the TTS system of polyphone solution to the problem.
Article mainly includes three parts, in the first part,according to the "Modern Chinese" in the polyphonic character of the number of statistical, I got 921 polyphones as the object of study, each polyphones’s part of speech and the number of polyphonic words were Statisted. The second part, in CCL modern Chinese corpus on these 921 polyphones’s frequency and frequency statistics were pragmatic. According to statistics, the cumulative frequency of the calculation results and the final separation of these words pronunciation, high frequency and low frequency levels. On the frequency of each word-class polyphones frequency of use of the statistical items, separate the regular pronunciation, second pronunciation, the pronunciation of three rare audio level.In the corpus only 1% of the low-frequency polyphones pronunciation using the default method of constant handling.The third part, the high-frequency words were classified more sound, and the integrated use of multi-syllable words of elimination, parts of speech determine the law and with common polyphones thesaurus other methods,which need processing. The tone of those items very pragmatic frequency, part of speech can not distinctive of a separate polyphones, then using statistical methods build rules for polyphones, according to different types separately.
本文的研究对象在于,确定《现代汉语词典》(第5版)(以下简称《现汉》)中921个多音字及其音项在CCL现代汉语语料库中的语用频率,以字频为基础,进而从语言学理论的角度出发,为TTS处理中多音字问题的解决提出一种新思路。
文章的主要内容包括三个部分,第一部分,对《现汉》中多音字的数目进行统计,确定以921个多音字为研究对象,并对每个多音字的词性及进行统计。第二部分,在CCL现代汉语语料库中对这921个多音字的字频进行语用频率统计。根据统计结果和累计频率的计算,最终将这些多音字分出高、中、低三个频级。对各频级的多音字每个音项的使用频率进行统计,分出高频音、低频音两个音级,对在语料库中只占1%的低频多音字采用常读音默认的方法进行处理。第三部分,对中、高频多音字进行分类,综合运用多音节词排除法、词性确定法和附带常用多音字词库法等方法进行处理。对那些各音项语用频率相当、词性区别不明显的可独立成词的多音字,则逐条梳理其所有语料,总结其出现的语境,为多音字构建规则。
Computer Text-to-Speech Technology (Text-to-Speech, referred to as TTS) refers to the use of computer programs to established visual text into speech process. Because of the system include linguistics, phonetics, computer programming, digital signal processing and other fields, it is a comprehensive multi-disciplinary technical projects in many fields.We touch input method, Library, various scheduling problems, the use of Chinese language teaching software, all kinds of electronic products to improve voice reading function to automatically introduce or reply system and the blind development of supplies and children's toys, and even robots manufacturing and future voice-control system to achieve in all areas,which are inseparable from the technical means. As a highly theoretical and practical combination of technology,TTS received the great attention from various disciplines and scholars at the beginning of language translation technology in the production.How to improve TTS’s speech synthesis fluency, naturalness and accuracy of the technology have become the focus of attention. Among them, the Chinese pronunciation of polyphonic accuracy of automatic tagging has become one of the difficulties language translation technology in the system of TTS.
Object of this paper is to determine the "Modern Chinese Dictionary" (5th Edition) (hereinafter referred to as "Modern Chinese ") in 921 polyphones and pronunciation items in the CCL of modern Chinese corpus, the Pragmatic frequency to frequency-based word, and then from the perspective of linguistic theory, a new idea comes up for the TTS system of polyphone solution to the problem.
Article mainly includes three parts, in the first part,according to the "Modern Chinese" in the polyphonic character of the number of statistical, I got 921 polyphones as the object of study, each polyphones’s part of speech and the number of polyphonic words were Statisted. The second part, in CCL modern Chinese corpus on these 921 polyphones’s frequency and frequency statistics were pragmatic. According to statistics, the cumulative frequency of the calculation results and the final separation of these words pronunciation, high frequency and low frequency levels. On the frequency of each word-class polyphones frequency of use of the statistical items, separate the regular pronunciation, second pronunciation, the pronunciation of three rare audio level.In the corpus only 1% of the low-frequency polyphones pronunciation using the default method of constant handling.The third part, the high-frequency words were classified more sound, and the integrated use of multi-syllable words of elimination, parts of speech determine the law and with common polyphones thesaurus other methods,which need processing. The tone of those items very pragmatic frequency, part of speech can not distinctive of a separate polyphones, then using statistical methods build rules for polyphones, according to different types separately.
引文
①廉轲,《应当重视现代汉字中的多音字》,渤海学刊,1993年第3期
②苏培成《现代汉字学纲要》,北京大学,2002
①GB12000·1-90《汉语信息处理词汇01部分:基本术语》中国标准出版社1991
①参见吕艳辉《基于语料库的现代汉语准口语计量研究》山东大学2005年硕士论文第16页
[1]中国社会科学院语言研究所词典编辑室.《现代汉语词典》(第五版)[M].商务印书馆,2005年6月.
[2]苏培成.现代汉字学纲要[M].北京:北京大学出版社,2002.
[3]周有光.汉字和文化问题[M].沈阳:辽宁人民出版社,2000.
[4]王力.汉语史稿[M].北京:中华书局,2004.
[5]裘锡圭.文字学概要[M].北京:商务印书馆,2002.
[6]徐世荣.普通话语音知识[M].北京:文字改革出版社,1980.
[7]唐作藩.音韵学教程[M].北京:北京大学出版社,1987.
[8]邹韶华.语用频率效应研究[M].北京:商务印书馆,2001.
[9]靳光瑾.中文信息处理若干重要问题[M].北京:科学出版社,2003.
[10]武占坤,王勤.现代汉语词汇概要[M].呼和浩特:内蒙古人民出版,1983.
[11]孙玉文.汉语变调构词研究[M].北京:北京大学出版社,1999.
[12]王力.论审音原则[J].中国语文第6期,1965.
[13]周有光.现代汉字中的多音字问题[J].中国语文,1979,(6).
[14]徐世荣.《审音表》剖析[J].语文建设,1995,(11).
[15]刘景勇,柴佩琪.汉语TTS系统中多音字问题的一种有效解决方案[J].微型电脑应用,2005,(4).
[16]龚群虎.汉语文-语转换处理中的语言学问题[J].汕头大学学报(人文科学版),第15卷1999,(3).
[17]张莉.河北地名特殊读音字例析[J].汉字文化,1998,(4).
[18]李如龙.论音义相生[J].暨南学报(哲学社会科学),1997,(3).
[19]高健.基于神经网络的汉字多音字标音处理方法[J].番禺职业技术学院学报,第3卷第2期.
[20]赖兴邦.宋词字-音转换中多音字处理研究[J].福建电脑,2008,(5).
[21]谭沅湘.多音字的语文教学应用角度考察及“以字为本”原理[J].北京教育学院学报, 2004,(6).
[22]曹先擢.浅谈普通话异读词审音的研究[J].语言文字应用,2008,(3) .
[23]应志伟.文语转换系统中基于语料的汉语自动分词研究[J]计算机应用,第20卷(2) .
[24]杨华.多音误读与语用频率的关系[J].语言文字应用,2003,(2) .
[25]张力.中文TTS系统中多音字的一种解决方案[J].计算机应用与软件,2008,(2) .
[26]杨宪泽.汉语同音字和多音字处理方法研究[J].计算机与现代化,2006,(2) .
[27]范明.汉语字音转换中的多层面多音字读音消歧[J].计算机工程与应用,2006,(2) .
[28]张子荣,初敏.解决多音字文-语转换的一种统计学习方法[J].中文信息学报,第16卷,(3) .
[29]穗志方.宋代名家诗自动注音研究及系统实现[J].中文信息学报,第12卷,(2) .
[30]马志强.一种给批量汉字加注带有声调拼音的方法[J].微电子学与计算机,第25卷,(4) .
[31]潘以锋.计算机在汉字自动注音中的应用[J].上海师范大学学报(自然科学版),第25卷,(4) .
[32]许嘉璐.中文信息处理技术现状及相关语言文字研究[J].软件世界,1996年,(4).
[33]杨宪泽.自然语言处理的一些方法研究[J].西南民族大学学报(自然科学版),第31卷,(4).
[34]李如龙,吴茗.略论对外汉语词汇教学的两个原则[J].语言教学与研究,2005,(2).
[35]李如龙.关于多音字的精简问题[J].文字改革,1984,(1).
[36]徐世荣.荧屏正音[J].语文建设,1995,(12).
[37]谭沅湘.多音字的语文教学应用角度考察及“以字为本”原理[J].北京教育学院学报,2004,(6).
[38]石安石.多音字不是不同的字[J].语文建设,1995,(6).
[39]张觉.关于“异读字”正名[J].学术研究,2002,(12).
[40]徐世荣.一字多音的产生、发展及其原因——《多音字汇览》序[J].语言教学与研究,1988,(9).
[41]王强军,张莉,张普.面向术语提取和定义识别的评测语料库建设[A].第三届全国信息检索与内容安全学术会议论文集[C].2007.
[42]郑泽之,王强军,张普,陈双新.基于大规模DCC语料库《现代汉语常用词表》、《现代汉语通用字表》收字情况统计分析[A]. Advances in Computation of Oriental Languages--Proceedings ofthe 20th International Conference on Computer Processing of Oriental Languages.2003.
[43]郑敏,蔡莲红.一种新的基于规则的多音字自动注音方法[A].第二届全国学生计算语言学研讨会论文集[C].2004.
[44] GB12000·1-90《汉语信息处理词汇01部分:基本术语》[S].中国标准出版社1991.
[45]罗文洁.《现代汉语词典》中的多音节异音同形词分析[D].曲阜师范大学硕士论文,2007.
[46]孙强.现代汉语多音字研究[D].四川大学博士论文,2007.
[47]刘春丽.汉语多音字研究[D].黑龙江大学硕士学位论文,2005.
[48]张莉霞.从《现代汉语词典》与《普通话异读词审音表》的比较看多音误读现象[D].西北大学硕士论文,2007.
[49]吕艳辉.基于语料库的现代汉语准口语计量研究[D].山东大学硕士论文,2005.
[50]申金女.《文语转换系统若干问题研究》[D].北京邮电大学硕士研究生学位论文,2006.
②苏培成《现代汉字学纲要》,北京大学,2002
①GB12000·1-90《汉语信息处理词汇01部分:基本术语》中国标准出版社1991
①参见吕艳辉《基于语料库的现代汉语准口语计量研究》山东大学2005年硕士论文第16页
[1]中国社会科学院语言研究所词典编辑室.《现代汉语词典》(第五版)[M].商务印书馆,2005年6月.
[2]苏培成.现代汉字学纲要[M].北京:北京大学出版社,2002.
[3]周有光.汉字和文化问题[M].沈阳:辽宁人民出版社,2000.
[4]王力.汉语史稿[M].北京:中华书局,2004.
[5]裘锡圭.文字学概要[M].北京:商务印书馆,2002.
[6]徐世荣.普通话语音知识[M].北京:文字改革出版社,1980.
[7]唐作藩.音韵学教程[M].北京:北京大学出版社,1987.
[8]邹韶华.语用频率效应研究[M].北京:商务印书馆,2001.
[9]靳光瑾.中文信息处理若干重要问题[M].北京:科学出版社,2003.
[10]武占坤,王勤.现代汉语词汇概要[M].呼和浩特:内蒙古人民出版,1983.
[11]孙玉文.汉语变调构词研究[M].北京:北京大学出版社,1999.
[12]王力.论审音原则[J].中国语文第6期,1965.
[13]周有光.现代汉字中的多音字问题[J].中国语文,1979,(6).
[14]徐世荣.《审音表》剖析[J].语文建设,1995,(11).
[15]刘景勇,柴佩琪.汉语TTS系统中多音字问题的一种有效解决方案[J].微型电脑应用,2005,(4).
[16]龚群虎.汉语文-语转换处理中的语言学问题[J].汕头大学学报(人文科学版),第15卷1999,(3).
[17]张莉.河北地名特殊读音字例析[J].汉字文化,1998,(4).
[18]李如龙.论音义相生[J].暨南学报(哲学社会科学),1997,(3).
[19]高健.基于神经网络的汉字多音字标音处理方法[J].番禺职业技术学院学报,第3卷第2期.
[20]赖兴邦.宋词字-音转换中多音字处理研究[J].福建电脑,2008,(5).
[21]谭沅湘.多音字的语文教学应用角度考察及“以字为本”原理[J].北京教育学院学报, 2004,(6).
[22]曹先擢.浅谈普通话异读词审音的研究[J].语言文字应用,2008,(3) .
[23]应志伟.文语转换系统中基于语料的汉语自动分词研究[J]计算机应用,第20卷(2) .
[24]杨华.多音误读与语用频率的关系[J].语言文字应用,2003,(2) .
[25]张力.中文TTS系统中多音字的一种解决方案[J].计算机应用与软件,2008,(2) .
[26]杨宪泽.汉语同音字和多音字处理方法研究[J].计算机与现代化,2006,(2) .
[27]范明.汉语字音转换中的多层面多音字读音消歧[J].计算机工程与应用,2006,(2) .
[28]张子荣,初敏.解决多音字文-语转换的一种统计学习方法[J].中文信息学报,第16卷,(3) .
[29]穗志方.宋代名家诗自动注音研究及系统实现[J].中文信息学报,第12卷,(2) .
[30]马志强.一种给批量汉字加注带有声调拼音的方法[J].微电子学与计算机,第25卷,(4) .
[31]潘以锋.计算机在汉字自动注音中的应用[J].上海师范大学学报(自然科学版),第25卷,(4) .
[32]许嘉璐.中文信息处理技术现状及相关语言文字研究[J].软件世界,1996年,(4).
[33]杨宪泽.自然语言处理的一些方法研究[J].西南民族大学学报(自然科学版),第31卷,(4).
[34]李如龙,吴茗.略论对外汉语词汇教学的两个原则[J].语言教学与研究,2005,(2).
[35]李如龙.关于多音字的精简问题[J].文字改革,1984,(1).
[36]徐世荣.荧屏正音[J].语文建设,1995,(12).
[37]谭沅湘.多音字的语文教学应用角度考察及“以字为本”原理[J].北京教育学院学报,2004,(6).
[38]石安石.多音字不是不同的字[J].语文建设,1995,(6).
[39]张觉.关于“异读字”正名[J].学术研究,2002,(12).
[40]徐世荣.一字多音的产生、发展及其原因——《多音字汇览》序[J].语言教学与研究,1988,(9).
[41]王强军,张莉,张普.面向术语提取和定义识别的评测语料库建设[A].第三届全国信息检索与内容安全学术会议论文集[C].2007.
[42]郑泽之,王强军,张普,陈双新.基于大规模DCC语料库《现代汉语常用词表》、《现代汉语通用字表》收字情况统计分析[A]. Advances in Computation of Oriental Languages--Proceedings ofthe 20th International Conference on Computer Processing of Oriental Languages.2003.
[43]郑敏,蔡莲红.一种新的基于规则的多音字自动注音方法[A].第二届全国学生计算语言学研讨会论文集[C].2004.
[44] GB12000·1-90《汉语信息处理词汇01部分:基本术语》[S].中国标准出版社1991.
[45]罗文洁.《现代汉语词典》中的多音节异音同形词分析[D].曲阜师范大学硕士论文,2007.
[46]孙强.现代汉语多音字研究[D].四川大学博士论文,2007.
[47]刘春丽.汉语多音字研究[D].黑龙江大学硕士学位论文,2005.
[48]张莉霞.从《现代汉语词典》与《普通话异读词审音表》的比较看多音误读现象[D].西北大学硕士论文,2007.
[49]吕艳辉.基于语料库的现代汉语准口语计量研究[D].山东大学硕士论文,2005.
[50]申金女.《文语转换系统若干问题研究》[D].北京邮电大学硕士研究生学位论文,2006.