DOCX《S15》

S15.

10 文本自动发音翻译 K.M.・阿卜杜勒・阿齐兹 英国诺丁汉大学电机电子工程系 摘要 自动翻译文本语音是最有用的,当不局限于一个现有的词汇. 潜在的质量有明显的改进语音输出复杂等演讲芯片将有更多的控制参数. 这个质量改善需要更大的计算资源处理等过程中作为文本正常化和一种应用音位变体字符串的算法. 许多的过程都是理想的适于做并发运行. 一个multi-transputer系统建立了奥坎:安排上,完成该文本自动语音转换. 摘要 The automatic translation of text to speech is most useful when not restricted to a pre-stored vocabulary. 自动翻译文本语音是最有用的,当不局限于一个pre-stored词汇. The potential quality of speech output has improved dramatically as the complexity of speech synthesis chips incorporate a greater number of control parameters. 潜在的质量有明显的改进语音输出复杂等演讲芯片将有更多的控制参数. This improvement in quality necessitates greater computing resources for handling such processes as text normalisation and the application of an allophone string generation algorithm. 这个质量改善需要更大的计算资源处理等过程中作为文本正常化和一种应用音位变体字符串的算法. Many of the processes involved are ideally suited to be run concurrently. 许多的过程都是理想的适于做并发运行. A multi-transputer systerm programmed in Occam has been constructed to perform this automatic text to speech conversion. 一个multi-transputer系统建立了奥坎:安排上,完成该文本自动语音转换. INTRODUCTION 论文简介 In the past,the simplest approach to unrestricted text to speech translation used a small set of letter to word rules 11.2.31 each specifyihg a pronunciation for one or more letters in any one context. 在过去,最简单的方法来限制使用文本语音翻译一小组给词的发音规则specifyihg 11.2.31每一个或多个字符在任何一个背景. Unless this approach yielded sufficient intelligibility,the routine addition of text to speech translation to computer systems was unlikely since more elaborate approaches embodying large pronunciation dictionaries or linguistics use too much of the available sequential computing resources [4]. 除非这个方法取得足够的清晰度,常务增加文本语音翻译的计算机系统不太可能更详细的方法从大的发音字典或语言学体现使用太多的可获得连续计算资源[4]. The recent introduction of complex speech synthesis chip sets incorporating such features as stress, speed, pitch, amplitude and prosody information has further compounded the processing problems involved in the translation. 最近引入复杂的语音合成芯片集合把这样的特征,压力大、速度、沥青、振幅和韵律信息处理问题不可开交参与翻译. A typical method for performing text to speech conversion requires several computational stages as is shown in Figure 1. 为执行典型方法文本语音转换需要几个计算阶段 如图1所示. The text normalisation stage converts the text into a standard form of text suitable for further processing. 文本正常化把文本转换阶段的标准形式的文本适合进一步的加工. Thir is achieved by expanding abreviations, handling punctuations and altering non-alphabetic characters. Another stage is required for the generation of a phoneme string for the pronunciation of words that are exceptions to the pronunciation rule. These words require the use of a special dictionary. For words that have a standard pronunciation a stage is required for the application of a phoneme string generation algorithm using context sensitive rules. 以达到扩大abreviations同名,处理的符号,改变去非字母字符.需要另一个阶段生成线音位的字的读音,是例外的发音规则.这些话需要使用一种特殊的字典.说不出话来,有一个标准发音阶段中的应用要求音位的字符串生成算法利用上下文敏感的规则. The phoneme strings producted may require further computation to interpret the correct versions of each phoneme using syntactic information and stress patterns for conversion into allophones. 弦音位生产计算可能需要进一步研究历史时,那些解释正确的版本的每个音素摘要采用句法信息和压力模式转变成了变体的. The parameter generator then converts the selected sounds into the speech parameters for the synthesiser to create speech. 参数发生器然后转换选定的语音转换成语音合成器参数创建的演说. The standard pronunciation algorithm stage comprises several processes.The recognition algorithm is based around one character within a character string. This character string can vary from one to three characters long,also associated with each string is a suffix and a prefix character. The characters can be letters, other characters, voiced consonants,vowel cluster etc. The processes involved in the pronunciation algorithm initially requires the identification of a letter character.Associated with each letter character is a set of rules. Once the correct rule set has been identified, then the specific rule from within the rule set must be found. This is achieved by studying the character string lengths and matching the prefix character, second character,third character and suffix character to the entries within the rule set. Associated with each rule entry is a string of allophones, thus when the relevant rule has been found from within the rule set, the correct allophone string can be passed to the sound section. 标准读音算法由一些阶段过程.识别算法是基于一个字符在一个字符串.这个字符串将不同三个大字长,也伴随每一个字符串是一个后缀和前缀的性格.字符就被信件,其它的字符,表示辅音、元音聚类等.所涉及的过程,在发音算法的识别最初要求信的性格.每个字母的性格是相关的一套规则.一旦正确的规则集已经确认,那麽特定的规则从内规........