Now showing items 389-408 of 639

  • On-line Overlaid-Handwriting Recognition Based on Substroke HMMs. 

    Shimodaira, Hiroshi; Sudo, Takashi; Nakai, Mitsuru; Sagayama, Shigeki (2003)
    This study discusses the subject of training data selection for neural networks using back propagation. We have made only one assumption that there are no overlapping of training data belonging to different classes, in ...
  • Open Access and Research Assessment: Dealing with UK Open Access Requirements in Practice 

    Tate, Dominic (IOS Press, 2015-08)
    This paper describes research-funder and research assessment policies in the UK and assesses the impact that these policies are having in the transition towards research outputs being made available on an open access basis.
  • Open-source Software for Developing Anthropomorphic Spoken Dialog Agents 

    Shin-ichi, Kawamoto; Shimodaira, Hiroshi; Nitta, Tsuneo; Nishimoto, Takuya; Nakamura, Satoshi; Itou, Katsunobu; Morishima, Shigeo; Yotsukura, Tatsuo; Kai, Atsuhiko; Lee, Akinobu; Yamashita, Yoichi; Kobayashi, Takao; Tokuda, Keiichi; Hirose, Keikichi; Minematsu, Nobuaki; Yamada, Atsushi; Den, Yasuharu; Utsuro, Takehito; Sagayama, Shigeki (2002)
    An architecture for highly-interactive human-like spoken-dialog agent is discussed in this paper. In order to easily integrate the modules of different characteristics including speech recognizer, speech synthesizer, ...
  • Opportunities for computer-aided instruction in phonetics and speech communication provided by the internet. 

    Huckvale, M; Benoit, C; Bowerman, Chris; Eriksson, A; Rosner, M; Tatham, M; Williams, Briony (International Speech Communication Association, 1997)
    Spoken language engineering is starting to deliver technological products to the commercial market and has an important future role in supporting the multilingual structures of modern Europe. The field will be driven ...
  • Optimal control with adaptive internal dynamics models 

    Mitrovic, Djordje; Klanke, Stefan; Vijayakumar, Sethu (2008)
    Optimal feedback control has been proposed as an attractive movement generation strategy in goal reaching tasks for anthropomorphic manipulator systems. The optimal feedback control law for systems with non-linear dynamics ...
  • Optimal Feedback Control for Anthropomorphic Manipulators 

    Mitrovic, Djordje; Nagashima, Sho; Klanke, Stefan; Matsubara, Takamitsu; Vijayakumar, Sethu (2010)
    We study target reaching tasks of redundant anthropomorphic manipulators under the premise of minimal energy consumption and compliance during motion. We formulate this motor control problem in the framework of ...
  • Optimising selection of units from speech databases for concatenative synthesis. 

    Black, Alan W; Campbell, Nick (International Speech Communication Association, 1995)
    Concatenating units of natural speech is one method of speech synthesis1. Most such systems use an inventory of fixed length units, typically diphones or triphones with one instance of each type. An alternative is to use ...
  • Optimizing Phonetic Encoding for Viennese Unit Selection Speech Synthesis 

    Pucher, Michael; Neubarth, Friedrich; Strom, Volker (2010)
    While developing lexical resources for a particular language variety (Viennese), we experimented with a set of 5 different phonetic encodings, termed phone sets, used for unit selection speech synthesis. We started with a ...
  • An Overview of the SPRACH System for the Transcription of Broadcast News 

    Cook, Gary; Christie, James; Ellis, Dan; Fosler-Lussier, Eric; Gotoh, Yoshihiko; Kingsbury, Brian; Morgan, Nelson; Renals, Steve; Robinson, Tony; Williams, Gethin (1999)
    This paper describes the SPRACH system developed for the 1998 Hub-4E broadcast news evaluation. The system is based on the connectionist-HMM framework and uses both recurrent neural network and multi-layer perceptron ...
  • Parallel Computational Modelling of Inelastic Neutron Scattering in Multi-node and Multi-core Architectures 

    Garba, M.T.; Gonzales-Velez, H.; Roach, D.L. (2010-11-26)
    This paper examines the initial parallel implementation of SCATTER, a computationally intensive inelastic neutron scattering routine with polycrystalline averaging capability, for the General Utility Lattice Program (GULP). ...
  • A Parallel Training Algorithm for Hierarchical Pitman-Yor Process Language Models 

    Huang, Songfang; Renals, Steve (2009)
    The Hierarchical Pitman Yor Process Language Model (HPYLM) is a Bayesian language model based on a non-parametric prior, the Pitman-Yor Process. It has been demonstrated, both theoretically and practically, that the HPYLM ...
  • Participant Subjectivity and Involvement as a Basis for Discourse Segmentation 

    Niekrasz, John; Moore, Johanna (2009)
    We propose a framework for analyzing episodic conversational activities in terms of expressed relationships between the participants and utterance content. We test the hypothesis that linguistic features which express such ...
  • Past the Kalashnikov: Youth, Politics and the State in Eritrea 

    Dorman, Sara Rich (2004-06-17)
    The paper examines the politics of the National Union of Eritrean Youth and Students (NUEYS), University students, and National Service. It proposes that these cases provide a useful perspective from which to think ...
  • Patient Confidentiality in Scotland: an overview 

    Muir, Rod (AHRC Research Centre for Studies in Intellectual Property and Technology Law, 2005-09)
    Paper presented by Muir and Laurie for the Privacy Workshop, chaired by Edwards and held in September 2005.
  • Pen pressure features for writer-independent on-line handwriting recognition based on substroke HMM 

    Nakai, Mitsuru; Sudo, Takashi; Shimodaira, Hiroshi; Sagayama, Shigeki (IEEE Computer Society, 2002-08)
    This paper discusses the use of pen pressure as a feature in writer-independent on-line handwriting recognition. We propose two kinds of features related to pen pressure: one is the pressure representing pen ups and downs ...
  • Perceptual weighting and phonemic awareness in pre-reading and early-reading children. 

    Mayo, Catherine (International Congress of Phonetic Sciences, 1999)
    While metalinguistic awareness and speech perception have been found to each be related to numerous other linguistic processes, e.g. reading acquisition, phonological development, phonological disorders, it is only ...
  • Performance Evaluation of The Speaker-Independent HMM-based Speech Synthesis System "HTS-2007" for the Blizzard Challenge 2007 

    Yamagishi, Junichi; Tokuda, Keiichi; Toda, Tomoki; Heiga, Zen; Nose, Takashi (2008)
    This paper describes a speaker-independent/adaptive HMM-based speech synthesis system developed for the Blizzard Challenge 2007. The new system, named HTS-2007, employs speaker adaptation (CSMAPLR+MAP), feature-space ...
  • Performance of concrete in fire: a review of the state of the art, with a case study of the windsor tower fire 

    Fletcher, Ian A; Borg, Audun; Hitchen, Neil; Welch, Stephen (Universidade de Aveiro, 2006-05)
    This paper provides a “State of the Art” review on current research into the effects of fire exposures upon concrete. The principal influences of high temperature in concrete are loss of compressive strength and spalling, ...
  • Personalising speech-to-speech translation in the EMIME project 

    Kurimo, Mikko; Byrne, William; Dines, John; Garner, Philip N.; Gibson, Matthew; Guan, Yong; Hirsimaki, Teemu; Karhila, Reima; King, Simon; Liang, Hui; Oura, Keiichiro; Saheer, Lakshmi; Shannon, Matt; Shiota, Sayaka; Tian, Jilei; Tokuda, Keiichi; Wester, Mirjam; Wu, Yi-Jian; Yamagishi, Junichi (2010)
    In the EMIME project we have studied unsupervised cross-lingual speaker adaptation. We have employed an HMM statistical framework for both speech recognition and synthesis which provides transformation mechanisms to adapt ...
  • Phone Classification in Pseudo-Euclidean Vector Spaces 

    Gutkin, Alexander; King, Simon (2004-10)
    Recently we have proposed a structural framework for modelling speech, which is based on patterns of phonological distinctive features, a linguistically well-motivated alternative to standard vector-space acoustic models ...