基于深度前编码卷积网络的汉越语音翻译方法

语音翻译是将源语言语音翻译为目标语言文本的过程.传统序列到序列模型应用到语音翻译领域时,模型对于序列长度较为敏感,编码端特征提取和局部依赖建模压力较大.针对这一问题,本文基于Transformer网络构建语音翻译模型,使用深度卷积网络对音频频谱特征进行前编码处理,通过对音频序列进行下采样,对音频频谱中的时频信息进行局部依赖建模和深层特征提取,缓解编码器的建模压力,实现了汉越双语的语音到文本互译.实验结果表明,提出方法取得很好效果,相比基准系统获得了约19%的性能提升.     

汉蒙翻译模型中的依存语法与形态信息应用研究

该文提出将源语言句法信息和目标语言形态信息引入汉蒙机器翻译的模型构造中,以降低译文的词形错误率等问题。在源语言端,利用汉语依存句法分析器获取依存树,将依存句法信息以标注形式记在每个词上;在目标语言端,分析并获取蒙古语形态信息;利用LOP思想将源语言依存句法信息和目标语言形态信息引入翻译模型构造中。实验表明,其BLEU评分比传统的短语统计翻译模型有明显提高。该方法通过词、短语、句法三层面信息的结合,实现了汉蒙两种语言语法结构的平衡,特别适合于源语言形态信息贫乏而目标语言形态信息丰富的统计机器翻译系统。     

神经机器翻译前沿综述

机器翻译是指通过计算机将源语言句子翻译到与之语义等价的目标语言句子的过程,是自然语言处理领域的一个重要研究方向。神经机器翻译仅需使用神经网络就能实现从源语言到目标语言的端到端翻译,目前已成为机器翻译研究的主流方向。该文选取了近期神经机器翻译的几个主要研究领域,包括同声传译、多模态机器翻译、非自回归模型、篇章翻译、领域自适应、多语言翻译和模型训练,并对这些领域的前沿研究进展做简要介绍。     

使用词对齐半监督对抗学习的汉越跨语言摘要生成方法

跨语言摘要是将输入的源语言文本生成目标语言摘要的过程.目前跨语言摘要任务大多是借助于机器翻译,而针对越南语这类低资源语言,机器翻译效果不佳是汉越跨语言摘要面临的挑战.针对该问题,提出了一种基于词对齐的半监督对抗学习汉越跨语言摘要生成方法,其思想是将汉越双语对齐到同一空间,得到对齐的双语特征,然后同时利用双语特征生成跨语...     

融合图像注意力的多模态机器翻译模型

已有工作表明,融入图像视觉语义信息可以提升文本机器翻译模型的效果。已有的工作多数将图片的整体视觉语义信息融入到翻译模型,而图片中可能包含不同的语义对象,并且这些不同的局部语义对象对解码端单词的预测具有不同程度的影响和作用。基于此,该文提出一种融合图像注意力的多模态机器翻译模型,将图片中的全局语义和不同部分的局部语义信息与源语言文本的交互信息作为图像注意力融合到文本注意力权重中,从而进一步增强解码端隐含状态与源语言文本的对齐信息。在多模态机器翻译数据集Multi30k上英语—德语翻译对以及人工标注的印尼语—汉语翻译对上的实验结果表明,该文提出的模型相比已有的基于循环神经网络的多模态机器翻译模型效果具有较好的提升,证明了该模型的有效性。     

Transformer在语音识别任务中的研究现状与展望

Transformer作为一种新的深度学习算法框架,得到了越来越多研究人员的关注,成为目前的研究热点.Transformer模型中的自注意力机制受人类只关注于重要事物的启发,只对输入序列中重要的信息进行学习.对于语音识别任务来说,重点是把输入语音序列的信息转录为对应的语言文本.过去的做法是将声学模型、发音词典和语言模型组成语音识别系统来实现语音识别任务,而Transformer可以将声学、发音和语言模型集成到单个神经网络中形成端到端语音识别系统,解决了传统语音识别系统的强制对齐和多模块训练等问题.因此,探讨Transformer在语音识别任务中存在的问题是非常有必要的.首先介绍Transformer的模型结构,并且从输入语音序列、深层模型结构和模型推理过程三方面对语音识别任务面临的问题进行分析;其次对现阶段解决语音识别中Transformer模型存在输入语音序列、深层模型结构和模型推理过程的问题进行方法总结和简要概述;最后对Transformer在语音识别任务中的应用方向进行总结和展望.     

基于深层声学特征的端到端语音分离

提出基于深层声学特征的端到端单声道语音分离算法,传统声学特征提取方法需要经过傅里叶变换、离散余弦变换等操作,会造成语音能量损失以及长时间延迟.为了改善这些问题,提出了以语音信号的原始波形作为深度神经网络的输入,通过网络模型来学习语音信号的更深层次的声学特征,实现端到端的语音分离.客观评价实验说明,本文提出的分离算法不仅有效地提升了语音分离的性能,也减少了语音分离算法的时间延迟.     

基于端到端技术的藏语语音识别*

现阶段基于链接时序分类技术的端到端的大规模连续语音识别成为研究热点,文中将其应用于藏语识别中,取得优于主流的双向长短时记忆网络性能.在基于端到端的语音识别中,不需要发音字典等语言学知识,识别性能无法得到保证.文中提出将已有的语言学知识结合至端到端的声学建模中,采用绑定的三音子作为建模单元,解决建模单元的稀疏性问题,大幅提高声学建模的区分度和鲁棒性.在藏语测试集上,通过实验证明文中方法提高基于链接时序分类技术的声学模型的识别率,并验证语言学知识和基于端到端声学建模技术结合的有效性.     

融合覆盖机制的多模态神经机器翻译

多模态神经机器翻译是指直接采用神经网络,以端到端方式融合图像和文本两种模态信息,以此进行翻译建模的机器学习方法。传统多模态机器翻译,是在将源语言翻译成目标语言时,借助图像中的重要特征信息优化翻译过程。但是观察发现,图像里的信息不一定出现在文本中,对翻译也会带来干扰;与参考译文对比,翻译结果中出现了过翻译和欠翻译的情况。针对以上问题,该文提出一种融合覆盖机制双注意力解码方法,用于优化现有多模态神经机器翻译模型。该模型借助覆盖机制分别作用于源语言和源图像,在注意力计算过程中,可以减少对过去重复信息的关注。在WMT16、WMT17测试集上进行实验,验证了上述方法的有效性,在WMT16英德和英法以及WMT17英德和英法测试集上,对比基准系统BLEU值分别提升了1.2,0.8,0.7和0.6个百分点。     

日本专家谈机器翻译系统

一、序(略)二、机器翻译的历史与现状(略)三、机器翻译的方法及富士通采取的措施机器翻译共有以下三种方法:1.直译法将输入的源语言的词或句子直接代换成与目标语言相对应的词或句子,然后再适当调整其语序的翻译方法即为直译法。这种方法最广泛地应用于早期的机器翻译系统中。时至今日,仍有许多人在研究用经改进更完善的直译法的高级机译系统。2.变换法这种翻译法首先要在源语言和目标语言之间设定一组能相应表现两种语言句型或在一定程度上表现语意的中间语言。在翻译时,首先要将源语言的语句变换成为源语言的中间语言表现形式,然后将其译成目标语言的中间语言     

An end-to-end model for cross-lingual transformation of paralinguistic information

Speech translation is a technology that helps people communicate across different languages. The most commonly used speech translation model is composed of automatic speech recognition, machine translation and text-to-speech synthesis components, which share information only at the text level. However, spoken communication is different from written communication in that it uses rich acoustic cues such as prosody in order to transmit more information through non-verbal channels. This paper is concerned with speech-to-speech translation that is sensitive to this paralinguistic information. Our long-term goal is to make a system that allows users to speak a foreign language with the same expressiveness as if they were speaking in their own language. Our method works by reconstructing input acoustic features in the target language. From the many different possible paralinguistic features to handle, in this paper we choose duration and power as a first step, proposing a method that can translate these features from input speech to the output speech in continuous space. This is done in a simple and language-independent fashion by training an end-to-end model that maps source-language duration and power information into the target language. Two approaches are investigated: linear regression and neural network models. We evaluate the proposed methods and show that paralinguistic information in the input speech of the source language can be reflected in the output speech of the target language.     

基于LSTM的蒙汉机器翻译的研究

由于内蒙古地区蒙汉机器翻译水平落后、平行双语语料规模较小,利用传统的统计机器翻译方法会出现数据稀疏以及训练过拟合等问题,导致翻译质量不高。针对这种情况,提出基于LSTM的蒙汉神经机器翻译方法,通过利用长短时记忆模型构建端到端的神经网络框架并对蒙汉机器翻译系统进行建模。为了更有效地理解蒙古语语义信息,根据蒙古语的特点将蒙古文单词分割成词素形式,导入模型,并在模型中引入局部注意力机制计算与目标词有关联的源语词素的权重,获得蒙古语和汉语词汇间的对齐概率,从而提升翻译质量。实验结果表明,该方法相比传统蒙汉翻译系统提高了翻译质量。     

Statistical Translation of Text and Speech: First Results with the RWTH System

In this paper, we describe a first version of a system for statisticaltranslation and present experimental results. The statistical translationapproach uses two types of information: a translation model and a languagemodel. The language model used is a standard bigram model. The translationmodel is decomposed into lexical and alignment models. After presenting the details of the alignment model, we describe the search problem and present a dynamic programming-based solution for the special case of monotone alignments.So far, the system has been tested on two limited-domain tasks for which abilingual corpus is available: the EuTrans traveller task (Spanish–English,500-word vocabulary) and the Verbmobil task (German–English, 3000-wordvocabulary). We present experimental results on these tasks. In addition to the translation of text input, we also address the problem of speech translation and suitable integration of the acoustic recognition process and the translation process.     

Simultaneous translation of lectures and speeches

With increasing globalization, communication across language and cultural boundaries is becoming an essential requirement of doing business, delivering education, and providing public services. Due to the considerable cost of human translation services, only a small fraction of text documents and an even smaller percentage of spoken encounters, such as international meetings and conferences, are translated, with most resorting to the use of a common language (e.g. English) or not taking place at all. Technology may provide a potentially revolutionary way out if real-time, domain-independent, simultaneous speech translation can be realized. In this paper, we present a simultaneous speech translation system based on statistical recognition and translation technology. We discuss the technology, various system improvements and propose mechanisms for user-friendly delivery of the result. Over extensive component and end-to-end system evaluations and comparisons with human translation performance, we conclude that machines can already deliver comprehensible simultaneous translation output. Moreover, while machine performance is affected by recognition errors (and thus can be improved), human performance is limited by the cognitive challenge of performing the task in real time.     

基于中心语块扩展的短语对齐

短语等价对在词典编纂、机器翻译和跨语言信息检索中有着广泛的应用．提出了一种新的短语对齐方法，使用可信度较高的词典对齐结果来抽取源语言短语的译文中心语块，依据译文扩展可信度来确定源语言短语的译文统计边界．从译文中心语块出发，结合译文统计边界生成源语言短语的所有候选译文．对候选译文进行评价，从中选出最可靠的译文．同时利用贪心算法消除源语言短语译文边界之间的交叉冲突．实验结果表明，所提出的方法在开放测试中其正确率达到了82．76％，性能好于其他方法．     

MARS: A Statistical Semantic Parsing and Generation-Based Multilingual Automatic tRanslation System

We present MARS (Multilingual Automatic tRanslation System), a research prototype speech-to-speech translation system. MARS is aimed at two-way conversational spoken language translation between English and Mandarin Chinese for limited domains, such as air travel reservations. In MARS, machine translation is embedded within a complex speech processing task, and the translation performance is highly effected by the performance of other components, such as the recognizer and semantic parser, etc. All components in the proposed system are statistically trained using an appropriate training corpus. The speech signal is first recognized by an automatic speech recognizer (ASR). Next, the ASR-transcribed text is analyzed by a semantic parser, which uses a statistical decision-tree model that does not require hand-crafted grammars or rules. Furthermore, the parser provides semantic information that helps further re-scoring of the speech recognition hypotheses. The semantic content extracted by the parser is formatted into a language-independent tree structure, which is used for an interlingua based translation. A Maximum Entropy based sentence-level natural language generation (NLG) approach is used to generate sentences in the target language from the semantic tree representations. Finally, the generated target sentence is synthesized into speech by a speech synthesizer.Many new features and innovations have been incorporated into MARS: the translation is based on understanding the meaning of the sentence; the semantic parser uses a statistical model and is trained from a semantically annotated corpus; the output of the semantic parser is used to select a more specific language model to refine the speech recognition performance; the NLG component uses a statistical model and is also trained from the same annotated corpus. These features give MARS the advantages of robustness to speech disfluencies and recognition errors, tighter integration of semantic information into speech recognition, and portability to new languages and domains. These advantages are verified by our experimental results.     

基于多重线性回归模型的翻译等价对获取

翻译等价对在词典编纂、机器翻译和跨语言信息检索中有着广泛的应用。文章从双语句对的译文等价树中抽取翻译等价对。使用译文直译率、短语对齐概率和目标语-源语言短语长度差异等特征对自动获取的等价对进行评价。提出了一种基于多重线性回归模型的等价对评价方法,并结合N-Best策略对候选翻译等价对进行过滤。实验结果表明:在开放测试中,基于多重线性回归模型的等价对评价及过滤方法其性能要优于其它方法。