2012 8th International Symposium on Chinese Spoken Language Processing

5-8 Dec. 2012

Filter Results

Displaying Results 1 - 25 of 113
  • [USB label]

    Publication Year: 2012, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (60 KB)
    Freely Available from IEEE
  • [Front cover]

    Publication Year: 2012, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (625 KB)
    Freely Available from IEEE
  • Hub page

    Publication Year: 2012, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (269 KB)
    Freely Available from IEEE
  • Session list

    Publication Year: 2012, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (20 KB)
    Freely Available from IEEE
  • ISCSLP 2012 table of contents

    Publication Year: 2012, Page(s):1 - 16
    Request permission for commercial reuse | PDF file iconPDF (70 KB)
    Freely Available from IEEE
  • ISCSLP 2012 brief author index

    Publication Year: 2012, Page(s):1 - 6
    Request permission for commercial reuse | PDF file iconPDF (34 KB)
    Freely Available from IEEE
  • ISCSLP 2012 detailed author index

    Publication Year: 2012, Page(s):1 - 46
    Request permission for commercial reuse | PDF file iconPDF (121 KB)
    Freely Available from IEEE
  • [Frequently asked questions]

    Publication Year: 2012, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (126 KB)
    Freely Available from IEEE
  • [Frequently asked questions]

    Publication Year: 2012, Page(s):1 - 5
    Request permission for commercial reuse | PDF file iconPDF (455 KB)
    Freely Available from IEEE
  • Welcome message from the conference chair

    Publication Year: 2012, Page(s):i - ii
    Request permission for commercial reuse | PDF file iconPDF (104 KB) | HTML iconHTML
    Freely Available from IEEE
  • Welcome message from the technical program chairs

    Publication Year: 2012, Page(s):iii - iv
    Request permission for commercial reuse | PDF file iconPDF (136 KB) | HTML iconHTML
    Freely Available from IEEE
  • Organizing committee

    Publication Year: 2012, Page(s): v
    Request permission for commercial reuse | PDF file iconPDF (92 KB)
    Freely Available from IEEE
  • Scientific committee

    Publication Year: 2012, Page(s): vi
    Request permission for commercial reuse | PDF file iconPDF (116 KB)
    Freely Available from IEEE
  • Acknowledgments

    Publication Year: 2012, Page(s): vii
    Request permission for commercial reuse | PDF file iconPDF (971 KB)
    Freely Available from IEEE
  • Program at a glance

    Publication Year: 2012, Page(s):viii - xxi
    Request permission for commercial reuse | PDF file iconPDF (404 KB)
    Freely Available from IEEE
  • Keynotes [5 abstracts]

    Publication Year: 2012, Page(s):xxii - xxvi
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (439 KB)

    Summary form only given. Provides an abstract for each of the four keynote presentations and a brief professional biography of each presenter. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tutorials [3 abstracts]

    Publication Year: 2012, Page(s):xxvii - xxxi
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (392 KB)

    Presents abstracts of tutorials from the conference proceedings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Alternative hypothesis generation using a weighted kernel feature matrix for ASR substitution error correction

    Publication Year: 2012, Page(s):1 - 5
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (327 KB) | HTML iconHTML

    Although automatic speech recognition (ASR) has been successfully used in several applications, it is still non-robust and imprecise especially in a harsh environment wherein the input speech is of low quality. Robust error correction for ASR outputs thus becomes important in addition to improving recognition performance. In recent approaches to error correction, linguistic or domain information i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speaker-ensemble hidden Markov modeling for automatic speech recognition

    Publication Year: 2012, Page(s):6 - 10
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (191 KB) | HTML iconHTML

    This paper proposes a new hidden Makov model (HMM) which we call speaker-ensemble HMM (SE-HMM). An SE-HMM is a multi-path HMM in which each path is an HMM constructed from the training data of a different speaker. SE-HMM may be considered a form of template-based acoustic model where speaker-specific acoustic templates are compressed statistically into speaker-specific HMMs. However, one has the f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A synchronized pruning composition algorithm of weighted finite state transducers for large vocabulary speech recognition

    Publication Year: 2012, Page(s):11 - 15
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (239 KB) | HTML iconHTML

    The use of weighted finite state transducer (WFST) has been a very attractive approach for large vocabulary continuous speech recognition(LVCSR). Composition is an important operation for combining different levels of WFSTs. However, the general composition algorithm may generate non-coaccessible states, which may require a large amount of memory space, especially for LVCSR applications. The gener... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Context dependant phone mapping for cross-lingual acoustic modeling

    Publication Year: 2012, Page(s):16 - 20
    Cited by:  Papers (4)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (127 KB) | HTML iconHTML

    This paper presents a novel method for acoustic modeling with limited training data. The idea is to leverage on a well-trained acoustic model of a source language. In this paper, a conventional HMM/GMM triphone acoustic model of the source language is used to derive likelihood scores for each feature vector of the target language. These scores are then mapped to triphones of the target language us... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative study of fMPE and RDLT approaches to LVCSR

    Publication Year: 2012, Page(s):21 - 24
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (249 KB) | HTML iconHTML

    This paper presents a comparative study of two discriminatively trained feature transform approaches, namely feature-space minimum phone error (fMPE) and region-dependent linear transform (RDLT), to large vocabulary continuous speech recognition (LVCSR). Experiments are performed on an LVCSR task of conversational telephone speech transcription using about 2,000 hours training data. Starting from ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A cross-dialect comparison of vowel dispersion and vowel variability

    Publication Year: 2012, Page(s):25 - 29
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (600 KB)

    The study is a cross-dialect comparison of the vowel systems of different inventories across five Chinese dialects in terms of vowel dispersion and vowel variability. The dialects include Meixian Kejia or Hakka with 5 vowels, Hong Kong Cantonese with 7 vowels, Fuzhou with 8 vowels, Ningbo with 10 vowels, and Wenling with 11 vowels. Formant frequencies were obtained through spectral analysis of spe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analyzing semantic orientation of terms using Affinity Propagation

    Publication Year: 2012, Page(s):30 - 34
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (125 KB) | HTML iconHTML

    The aim of term semantic orientation analysis is to mine the sentiment polarity of words and phrases from their contexts. This paper presents a novel algorithm called Affinity Propagation to analyze semantic orientations of terms. Specifically, we build an informative graph from text corpus using an efficient Word Activation Force model and regard each term as a node in the graph. Then we propagat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Effects of excitation spread on the intelligibility of Mandarin speech in cochlear implant simulations

    Publication Year: 2012, Page(s):35 - 39
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (304 KB) | HTML iconHTML

    Noisy listening conditions remain challenging for most cochlear implant patients. The present study simulated the effects of decay rates of excitation spread in cochlear implants on the intelligibility of Mandarin speech in noise. Mandarin sentence and tone stimuli were processed by noise-vocoder, and presented to normal-hearing listeners for identification. The decay rates of excitation spread we... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.