December 2013 Vol. 11 No. 12

Feature Articles: Front-line of Speech, Language, and Hearing Research for Heartfelt Communications

• Advanced Research in Speech, Language, and Hearing for Communication of the Future

  

  Abstract
  Research at NTT Communication Science Laboratories draws on both information science and human science with the aim of building a new technical infrastructure that will connect humans and information. These Feature Articles introduce new trends in the fields of speech, language, and hearing, which have a relatively long history of basic research.

• Recent Innovations in NTT’s Statistical Machine Translation

  

  Abstract
  English and Japanese have very different word orders, and they are probably one of the most difficult language pairs to translate. We developed a new method of translating English to Japanese that takes advantage of the head-final linguistic nature of Japanese. It first changes the word order in an English sentence into that of a Japanese sentence and then translates the reordered English sentence into Japanese. We found that our method dramatically improved the accuracy of English-to-Japanese translation. We also found that the method is highly effective for Chinese-to-Japanese translation.

• Advances in Multi-speaker Conversational Speech Recognition and Understanding

  

  Abstract
  Opportunities have been increasing in recent years for ordinary people to use speech recognition technology. For example, we can easily operate smartphones using voice commands. However, attempts to construct a device that can recognize human conversation have produced unsatisfactory results in terms of accuracy and usability because current technology is not designed for this purpose. At NTT Communication Science Laboratories, our goal is to create a new technology for multi-speaker conversational speech recognition and understanding. In this article, we review the technology we have developed and present our meeting analysis system that can accurately recognize who spoke when, what, to whom, and how in meeting situations.

• Speech Recognition Based on Unified Model of Acoustic and Language Aspects of Speech

  

  Abstract
  Automatic speech recognition has been attracting a lot of attention recently and is considered an important technique to achieve natural interaction between humans and machines. However, recognizing spontaneous speech is still considered to be difficult owing to the wide variety of patterns in spontaneous speech. We have been researching ways to overcome this problem and have developed a method to express both the acoustic and linguistic aspects of speech recognizers in a unified representation by integrating powerful frameworks of deep learning and a weighted finite-state transducer. We evaluated the proposed method in an experiment to recognize a lecture speech dataset, which is considered as a spontaneous speech dataset, and confirmed that the proposed method is promising for recognizing spontaneous speech.

• Speaking Rhythm Extraction and Control by Non-negative Temporal Decomposition

  

  Abstract
  Speaking rhythm plays an important role in speech production and the perception of non-native languages. This article introduces a novel method for extracting and controlling speaking rhythm from speech signals using non-negative temporal decomposition.

• Link between Hearing and Bodily Sensations

  

  Abstract
  As humans, we know the size and shape of our own body, and we believe that our body is stable and maintains a consistent shape. However, some acoustic manipulations can induce illusions related to the body. These illusions indicate that hearing plays an important role in the sensations we perceive in our own body. This article presents an overview of such illusions and discusses the relationships between the sense of hearing and bodily sensations.

Regular Articles

• Efficient Mining Algorithms for Large-scale Graphs

  

  Abstract
  This article describes efficient graph mining algorithms designed for analyzing large-scale graph data such as social graphs. Graph mining is a technique to analyze the structure of graphs consisting of nodes and edges. We have developed efficient algorithms for two mining tasks: clustering and computing personalized PageRank, for large-scale graphs.

Global Standardization Activities

• Trends Concerning Standardization of OpenADR

  

  Abstract
  Automated demand response (ADR) technology is drawing worldwide attention alongside renewable energy technologies as a countermeasure against global warming and rising energy costs. In Japan, standardization of ADR has progressed rapidly as a promising power-saving measure since the Great East Japan Earthquake of March 2011, and Demand Response Interface Specification Version 1.0 was adopted by the JSCA (Japan Smart Community Alliance) Smart House/Building Standardization and Business Promotion Study Group organized by METI (Ministry of Economy, Trade and Industry of Japan) in May 2013. This article describes OpenADR 2.0, the international standard that forms the basis of the abovementioned Japanese specification.

Practical Field Information about Telecommunication Technologies

• Enhancing the Reliability of Aerial Iron Fittings (Span Clamps and Outdoor Wire Anchors)

  

  Abstract
  In this article, we introduce how to enhance the reliability of aerial iron fittings (span clamps and outdoor wire anchors). This is the twentieth in a bimonthly series on the theme of practical field information on telecommunication technologies. This month’s contribution is from the Materials Engineering Group, Technical Assistance and Support Center, Maintenance and Service Operations Department, Network Business Headquarters, NTT EAST.

Information

• Report on NTT Communication Science Laboratories Open House 2013

  

  Abstract
  Open House 2013 was held in June at NTT Communication Science Laboratories in Keihanna Science City, Kyoto. Over 1000 people visited the facility on June 6 and 7 to enjoy 6 talks and 30 exhibits introducing our latest research activities and efforts in the fields of information and human sciences. This article reports on the main activities conducted during the open house.

Papers Published in Technical Journals and Conference Proceedings

• Papers Published in Technical Journals and Conference Proceedings