2006 IEEE Spoken Language Technology Workshop

10-13 Dec. 2006

Filter Results

Displaying Results 1 - 25 of 80
  • 2006 IEEE ACL Spoken Language Technology Workshop - Cover

    Publication Year: 2006, Page(s): C1
    Request permission for reuse | PDF file iconPDF (43 KB)
    Freely Available from IEEE
  • 2006 IEEE Spoken Language Technology Workshop

    Publication Year: 2006, Page(s): i
    Request permission for reuse | PDF file iconPDF (27 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2006, Page(s): ii
    Request permission for reuse | PDF file iconPDF (76 KB)
    Freely Available from IEEE
  • General Chairs' Welcome

    Publication Year: 2006, Page(s): iii
    Request permission for reuse | PDF file iconPDF (46 KB) | HTML iconHTML
    Freely Available from IEEE
  • Organizing Committee

    Publication Year: 2006, Page(s): iv
    Request permission for reuse | PDF file iconPDF (98 KB)
    Freely Available from IEEE
  • [Breaker page]

    Publication Year: 2006, Page(s): vi
    Request permission for reuse | PDF file iconPDF (10 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2006, Page(s):vii - xiii
    Request permission for reuse | PDF file iconPDF (113 KB)
    Freely Available from IEEE
  • [Breaker page]

    Publication Year: 2006, Page(s): xiv
    Request permission for reuse | PDF file iconPDF (11 KB)
    Freely Available from IEEE
  • Speech technology opportunities and challenges

    Publication Year: 2006, Page(s): 1
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (33 KB)

    Summary form only given. Two forces are in pursuit of discovering the possibilities of speech technology automation. First is the global research and development community which has been hard at work for improving the performance and usability of the technology. Second is the business community which constantly evaluates the performance of the technology against the expectation of the user communi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • No more strings, please

    Publication Year: 2006, Page(s): 2
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (32 KB)

    Summary form only given. In natural language research, many (grammar) trees were felled in 1992, to make room for the highly successful string-based HMM industry. A small literature survived on parsing (putting a tree on a string) and syntactic language modeling (putting a weight on a string). However, trees are making a comeback. Tree transformations are turning out to be very useful in large-sca... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information extraction from speech

    Publication Year: 2006, Page(s): 3
    Cited by:  Papers (32)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (31 KB)

    Summary form only given. The state of the art in automatic speech recognition has reached the point that searching for and extracting information from large speech repositories or streaming audio has become a growing reality. This paper summarizes the technologies that have been instrumental in making audio as searchable as text, including speech recognition, speaker clustering, segmentation, and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Graph-based methods for language processing and information retrieval

    Publication Year: 2006, Page(s): 4
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (55 KB)

    Summary form only given. A number of problems in information retrieval and natural language processing can be approached using graph theory. Some representative examples in IR include Brin and Page's Pagerank and Kleinberg's HITS for document ranking using graph-based random walk models. In NLP, one could mention Pang and Lee's work on sentiment analysis using graph min- cuts, Mihalcea's work on w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Voice-activated question answering

    Publication Year: 2006, Page(s): 5
    Cited by:  Papers (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (32 KB)

    Summary form only given. Text-based Question Answering technology has made significant progress in the last few years. Cellular phones are now shipping with integrated web browsers. It is clear the next step is to integrate voice input and output with Question Answering systems to alleviate the keyword bottleneck of cellular phones. This talk presents some issues specific to designing VAQA systems... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spoken language understanding for conversational dialog systems

    Publication Year: 2006, Page(s): 6
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (32 KB)

    Summary form only given. Requirements for spoken language understanding for spoken dialog systems can range from the recognition of key words and phrases to a deeper understanding of the speaker's intentions. It is important to take account of the functional requirements of the overall system in order to determine the approaches and technologies that are most relevant for a particular type of dial... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applications of spoken language technology and systems

    Publication Year: 2006, Page(s): 7
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (32 KB)

    Summary form only given. Over the past twenty years, we have seen an increasing number of successful deployments of spoken language technology. But, there is not a single market where these systems have become truly ubiquitous. In this talk, I will discuss the use of speech technology in mobile devices. Because of the particular features and constraints of these devices (personal device, increasin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using POMDPS for dialog management

    Publication Year: 2006, Page(s):8 - 13
    Cited by:  Papers (15)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (646 KB) | HTML iconHTML

    This paper explains how partially observable Markov decision processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken dialog systems. It briefly summarises the basic mathematics and explains why exact optimisation is intractable. It then describes a form of approximation called the Hidden Information State model which does scale and which ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Understanding and modeling communication scenes

    Publication Year: 2006, Page(s): 14
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (32 KB) | HTML iconHTML

    This paper discusses the technologies required to better understand and model human-human communication, and to use the resulting technologies to build computer-enhanced communication tools. As networks and computers become more pervasive, groups are increasingly using technology to assist communication and collaboration and to reduce travel needs. The addition of new technologies based on advance... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Widening the NLP pipeline for spoken language processing

    Publication Year: 2006, Page(s): 15
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (60 KB) | HTML iconHTML

    Summary form only given. A typical text-based natural language application (eg. machine translation, summarization, information extraction) consists of a pipeline of preprocessing steps such as tokenization, stemming, part-of-speech tagging, named entity detection, chunking, parsing. Information flows downstream through the preprocessing steps along a narrow pipe: each step transforms a single inp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recent advances in automatic speech summarization

    Publication Year: 2006, Page(s):16 - 21
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (124 KB) | HTML iconHTML

    Speech summarization technology, which extracts important information and removes irrelevant information from speech, is expected to play an important role in building speech archives and improving the efficiency of spoken document retrieval. However, speech summarization has a number of significant challenges that distinguish it from general text summarization. Fundamental problems with speech su... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel DTW-based distance measure for speaker segmentation

    Publication Year: 2006, Page(s):22 - 25
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (634 KB) | HTML iconHTML

    We present a novel distance measure for comparing two speech segments that uses a local version of the well-known DTW algorithm. Our approach is based on the idea of finding word-level speech patterns that are repeated by the same speaker. Using this distance measure, we develop a speaker segmentation procedure and apply it to the task of segmenting multi-speaker lectures. We demonstrate that our ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved summarization of chinese spoken documents by probabilistic latent semantic analysis (PLSA) with further analysis and integrated scoring

    Publication Year: 2006, Page(s):26 - 29
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (575 KB) | HTML iconHTML

    In a previous paper [1] two new scoring measures, topic significance (TS) and topic entropy (TE), obtained from probabilistic latent semantic analysis (PLSA) were shown to outperform very successful baseline significance score (SS) in selecting the important sentences for summarization of spoken documents. In this paper extensive experiments using the ROUGE scores with respect to different paramet... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Domain-independent topic segmentation using a string kernel on recognized sub-word sequences

    Publication Year: 2006, Page(s):30 - 33
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (108 KB) | HTML iconHTML

    The goal of the present paper is to explore the feasibility of a topic segmentation method without using large vocabulary continuous speech recognition (LVCSR). The proposed method is domain-independent in the sense that it is not constrained by vocabulary and does not require training data. For a sequence of sub-word units obtained using a continuous sub-word recognizer, the proposed method merge... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Summarization of spoken lectures based on linguistic surface and prosodic information

    Publication Year: 2006, Page(s):34 - 37
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (560 KB) | HTML iconHTML

    We aim to extract automatically the summarization of spoken lectures for conferences and classes. For this purpose, at first we compared results of summarization extracted by human subjects. We found large differences with every subject. Then we investigated the relations between linguistic surface information and human results, and we obtained useful linguistic surface information. Next, we summa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulation analysis for interactive retrieval of spoken documents with key terms ranked by reinforcement learning

    Publication Year: 2006, Page(s):38 - 41
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (139 KB) | HTML iconHTML

    Unlike written documents, spoken documents are difficult to display on the screen; it is also difficult for users to browse these documents during retrieval. It has been proposed recently to use interactive multi-modal dialogues to help the user navigate through a spoken document archive to retrieve the desired documents. This interaction is based on a topic hierarchy constructed by the key terms ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discriminatively trained spoken document similarity models and their application to probabilistic latent semantic analysis

    Publication Year: 2006, Page(s):42 - 45
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (220 KB) | HTML iconHTML

    This paper presents a novel framework for discriminatively training spoken document similarity models. Traditional similarity methods such as Vector Space Modeling and Probabilistic Latent Semantic Analysis suffer from a mismatch in modeling and evaluation objective functions. This work proposes reconciling this mismatch by using a discriminative training process in conjunction with prior knowledg... View full abstract»

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