Entry Chen:2009:WTM from talip.bib

Last update: Sun Oct 15 02:55:04 MDT 2017                Valid HTML 3.2!

Index sections

Top | Symbols | Numbers | Math | A | B | C | D | E | F | G | H | I | J | K | L | M | N | O | P | Q | R | S | T | U | V | W | X | Y | Z

BibTeX entry

@Article{Chen:2009:WTM,
  author =       "Berlin Chen",
  title =        "Word Topic Models for Spoken Document Retrieval and
                 Transcription",
  journal =      j-TALIP,
  volume =       "8",
  number =       "1",
  pages =        "2:1--2:??",
  month =        mar,
  year =         "2009",
  CODEN =        "????",
  DOI =          "https://doi.org/10.1145/1482343.1482345",
  ISSN =         "1530-0226 (print), 1558-3430 (electronic)",
  ISSN-L =       "1530-0226",
  bibdate =      "Mon Mar 23 16:32:22 MDT 2009",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/talip.bib",
  abstract =     "Statistical language modeling (LM), which aims to
                 capture the regularities in human natural language and
                 quantify the acceptability of a given word sequence,
                 has long been an interesting yet challenging research
                 topic in the speech and language processing community.
                 It also has been introduced to information retrieval
                 (IR) problems, and provided an effective and
                 theoretically attractive probabilistic framework for
                 building IR systems. In this article, we propose a word
                 topic model (WTM) to explore the co-occurrence
                 relationship between words, as well as the long-span
                 latent topical information, for language modeling in
                 spoken document retrieval and transcription. The
                 document or the search history as a whole is modeled as
                 a composite WTM model for generating a newly observed
                 word. The underlying characteristics and different
                 kinds of model structures are extensively investigated,
                 while the performance of WTM is thoroughly analyzed and
                 verified by comparison with the well-known
                 probabilistic latent semantic analysis (PLSA) model as
                 well as the other models. The IR experiments are
                 performed on the TDT Chinese collections (TDT-2 and
                 TDT-3), while the large vocabulary continuous speech
                 recognition (LVCSR) experiments are conducted on the
                 Mandarin broadcast news collected in Taiwan.
                 Experimental results seem to indicate that WTM is a
                 promising alternative to the existing models.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Asian Language Information
                 Processing",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J820",
  keywords =     "adaptation; information retrieval; language model;
                 speech recognition; word topic model",
}

Related entries