Entry Chen:2008:TTR 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:2008:TTR,
  author =       "Jiang-Chun Chen and Jyh-Shing Roger Jang",
  title =        "{TRUES}: {Tone Recognition Using Extended Segments}",
  journal =      j-TALIP,
  volume =       "7",
  number =       "3",
  pages =        "10:1--10:??",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "https://doi.org/10.1145/1386869.1386872",
  ISSN =         "1530-0226 (print), 1558-3430 (electronic)",
  ISSN-L =       "1530-0226",
  bibdate =      "Fri Aug 22 13:11:51 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/talip.bib",
  abstract =     "Tone recognition has been a basic but important task
                 for speech recognition and assessment of tonal
                 languages, such as Mandarin Chinese. Most previously
                 proposed approaches adopt a two-step approach where
                 syllables within an utterance are identified via forced
                 alignment first, and tone recognition using a variety
                 of classifiers---such as neural networks, Gaussian
                 mixture models (GMM), hidden Markov models (HMM),
                 support vector machines (SVM)---is then performed on
                 each segmented syllable to predict its tone. However,
                 forced alignment does not always generate accurate
                 syllable boundaries, leading to unstable
                 voiced-unvoiced detection and deteriorating performance
                 in tone recognition. Aiming to alleviate this problem,
                 we propose a robust approach called Tone Recognition
                 Using Extended Segments (TRUES) for HMM-based
                 continuous tone recognition. The proposed approach
                 extracts an unbroken pitch contour from a given
                 utterance based on dynamic programming over time-domain
                 acoustic features of average magnitude difference
                 function (AMDF). The pitch contour of each syllable is
                 then extended for tri-tone HMM modeling, such that the
                 influence from inaccurate syllable boundaries is
                 lessened. Our experimental results demonstrate that the
                 proposed TRUES achieves 49.13\% relative error rate
                 reduction over that of the recently proposed supratone
                 modeling, which is deemed the state of the art of tone
                 recognition that outperforms several previously
                 proposed approaches. The encouraging improvement
                 demonstrates the effectiveness and robustness of the
                 proposed TRUES, as well as the corresponding pitch
                 determination algorithm which produces unbroken pitch
                 contours.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Asian Language Information
                 Processing",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J820",
  keywords =     "context-dependent tone modeling; continuous tone
                 recognition; extended segment for tone recognition;
                 HMM; Mandarin Chinese; supratone modeling",
}

Related entries