摘要翻译：
用于自动语音识别(ASR)的多语言模型很有吸引力，因为它们可以从更多的训练数据中受益，并更好地适应资源不足的语言。然而，单语语境依赖模型的初始化会导致语境依赖状态的爆炸。连接主义时态分类(CTC)是一个潜在的解决方案，因为它能很好地处理单音标签。我们在适应和规则化技术的背景下研究多语言CTC，这些技术在更传统的背景下被证明是有益的。多语言模型被训练为使用CTC损失函数对基于通用国际音标(IPA)的电话机建模。研究了学习隐单位贡献(LHUC)在语言适应性训练中的应用。此外，为了缓解跨语言适应中的过适应问题，本文还对跨语言适应过程中的辍学现象进行了研究和测试。实验表明，应用LHUC可以提高通用音素CTC系统的性能，并且在跨语言适应过程中对新音素具有扩展性。在有限的数据上，所有参数的更新显示出一致的改进。在自适应过程中引入dropout可以进一步提高系统的性能，并在有限的数据条件下实现深度神经网络/隐马尔可夫模型（Deep Neural Network/Hidden Markov Model，DNN/HMM)系统的竞争性能。
---
英文标题：
《Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic
  Model》
---
作者：
Sibo Tong, Philip N. Garner, Herv\'e Bourlard
---
最新提交年份：
2018
---
分类信息：

一级分类：Electrical Engineering and Systems Science        电气工程与系统科学
二级分类：Audio and Speech Processing        音频和语音处理
分类描述：Theory and methods for processing signals representing audio, speech, and language, and their applications. This includes analysis, synthesis, enhancement, transformation, classification and interpretation of such signals as well as the design, development, and evaluation of associated signal processing systems. Machine learning and pattern analysis applied to any of the above areas is also welcome.  Specific topics of interest include: auditory modeling and hearing aids; acoustic beamforming and source localization; classification of acoustic scenes; speaker separation; active noise control and echo cancellation; enhancement; de-reverberation; bioacoustics; music signals analysis, synthesis and modification; music information retrieval;  audio for multimedia and joint audio-video processing; spoken and written language modeling, segmentation, tagging, parsing, understanding, and translation; text mining; speech production, perception, and psychoacoustics; speech analysis, synthesis, and perceptual modeling and coding; robust speech recognition; speaker recognition and characterization; deep learning, online learning, and graphical models applied to speech, audio, and language signals; and implementation aspects ranging from system architecture to fast algorithms.
处理代表音频、语音和语言的信号的理论和方法及其应用。这包括分析、合成、增强、转换、分类和解释这些信号，以及相关信号处理系统的设计、开发和评估。机器学习和模式分析应用于上述任何领域也是受欢迎的。感兴趣的具体主题包括：听觉建模和助听器；声波束形成与声源定位；声场景分类；说话人分离；有源噪声控制和回声消除；增强；去混响；生物声学；音乐信号的分析、合成与修饰；音乐信息检索；多媒体音频和联合音视频处理；口语和书面语建模、切分、标注、句法分析、理解和翻译；文本挖掘；言语产生、感知和心理声学；语音分析、合成、感知建模和编码；鲁棒语音识别；说话人识别与特征描述；应用于语音、音频和语言信号的深度学习、在线学习和图形模型；以及从系统架构到快速算法的实现方面。
--
一级分类：Computer Science        计算机科学
二级分类：Sound        声音
分类描述：Covers all aspects of computing with sound, and sound as an information channel. Includes models of sound, analysis and synthesis, audio user interfaces, sonification of data, computer music, and sound signal processing. Includes ACM Subject Class H.5.5, and intersects with H.1.2, H.5.1, H.5.2, I.2.7, I.5.4, I.6.3, J.5, K.4.2.
涵盖了声音计算的各个方面，以及声音作为一种信息通道。包括声音模型、分析和合成、音频用户界面、数据的可听化、计算机音乐和声音信号处理。包括ACM学科类H.5.5，并与H.1.2、H.5.1、H.5.2、I.2.7、I.5.4、I.6.3、J.5、K.4.2交叉。
--

---
英文摘要：
  Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from monolingual context-dependent models leads to an explosion of context-dependent states. Connectionist Temporal Classification (CTC) is a potential solution to this as it performs well with monophone labels.   We investigate multilingual CTC in the context of adaptation and regularisation techniques that have been shown to be beneficial in more conventional contexts. The multilingual model is trained to model a universal International Phonetic Alphabet (IPA)-based phone set using the CTC loss function. Learning Hidden Unit Contribution (LHUC) is investigated to perform language adaptive training. In addition, dropout during cross-lingual adaptation is also studied and tested in order to mitigate the overfitting problem.   Experiments show that the performance of the universal phoneme-based CTC system can be improved by applying LHUC and it is extensible to new phonemes during cross-lingual adaptation. Updating all the parameters shows consistent improvement on limited data. Applying dropout during adaptation can further improve the system and achieve competitive performance with Deep Neural Network / Hidden Markov Model (DNN/HMM) systems on limited data.
---
PDF链接：
https://arxiv.org/pdf/1711.10025