Modern information seekers face dynamic streams of large‐scale heterogeneous data that are both intimidating and overwhelming. They need a strategy to filter this barrage of massive data sets, and to find all of the information responding to their information needs, despite the pressures imposed by schedules and budgets. In this applied research, we present an exploratory search strategy that allows professional information seekers to efficiently and effectively triage all of the data. We demonstrate that exploratory search is particularly useful for information filtering and large‐scale information triage, regardless of the language of the data, and regardless of the particular industry, whether finance, medical, business, government, information technology, news, or legal. Our strategy reduces a dauntingly large volume of information into a manageable, high‐precision data set, suitable for focused reading. This strategy is interdisciplinary, integrating concepts from information filtering, information triage, and exploratory search. Key aspects include advanced search software, interdisciplinary paired search, asynchronous collaborative search, attention to linguistic phenomena, and aggregated search results in the form of a search matrix or search grid. We present the positive results of a task‐oriented evaluation in a real‐world setting, discuss these results from a qualitative perspective, and share future research areas.

Part-of-speech tagging is needed for French Text-to-Speech (TTS) synthesis to disambiguate the pronunciation of homograph heterophones, liaison instances, and eventually to model intonational contours. A core problem in the part-of-speech tagging in French TTS is to decide on the tagset used for the tagger and the tagset needed by TTS. We carried out a number of experiments on several sizes of tagsets as well as on several algorithms to investigate this problem. Our experiment results suggest that there may be an optimal tagset to be used for the part-of-speech disambiguation in French TTS. This optimal tagset contains a slightly larger number of tags than the tagset that is needed by TTS for pronunciation disambiguation and intonational modeling purposes. In our experiments, the optimal tagset gives a 98.4 % tagging accuracy for TTS, when a trigram Hidden Markov Model tagger is used. 1.

These experiments investigate whether the perceptual boundary between [a] and [a:] is affected by the differing phonotactics of the Sino-Japanese and Foreign strata of the Japanese lexicon. We presented a range of edited natural vowels from [a] to [a:] at the end of carrier nonwords of the form [CoC'__] and asked subjects to judge whether the final vowel was long or short, while C and C ' were varied to make 9 carriers ranging from very Sino-Japanese-like to very Foreign-like. The perceptual boundary between [a] and [a:] was affected by both C and C', shifting through about 20 msec—a larger and more robust effect than was obtained in a word-superiority experiment with the same paradigm and subjects. These results cast doubt on explanations of phonotactic effects based on lexical-activation spreading. The influence of C at a distance of three phonemes from the ambiguous segment cannot be explained by simple segment-to-segment transitional probabilities.

We present in this paper a novel subspace approach for single channel speech enhancement and speech recognition in highly noisy environments.Our algorithm is based on principal component analysis and the optimal subspace selection is provided by a minimum description length criterion.This choice overcomes the limitations encountered with other selection criteria, like the overestimation of the signal{plus{ noise subspace or the need for empirical parameters.We h a v e also extended our subspace algorithm to take into account the case of colored noise.The performance evaluation shows that our method provides a higher noise reduction and a lower signal distortion than existing enhancement methods and that speech recognition in noise is improved.Our algorithm succeeds in extracting the relevant features of speech even in highly noisy conditions without introducing artefacts such a s \ m usical noise".

We present an approach to information retrieval based on context distance and morphology. Context distance is a measure we use to assess the closeness of word meanings. This context distance model measures semantic distances between words using the local contexts of words within a single document as well as the lexical co-occurrence information in the set of documents to be retrieved. We also propose to integrate the context distance model with morphological analysis in determining word similarity so that the two can enhance each other. Using the standard vector-space model, we evaluated the proposed method on a subset of TREC-4 corpus (AP88 and AP90 collection, 158,240 documents, 49 queries). Results show that this method improves the 11-point average precision by 8.6%.

A system for the automatic production of controlled index terms is presented using linguistically-motivated techniques. This includes a finite-state part of speech tagger, a derivational morphological processor for analysis and generation, and a unification-based shallow-level parser using transformational rules over syntactic patterns. The contribution of this research is the successful combination of parsing over a seed term list coupled with derivational morphology to achieve greater coverage of multi-word terms for indexing and retrieval. Final results are evaluated for precision and recall, and implications for indexing and retrieval are discussed.

Controlling timing in text-to-speech synthesis systems is complicated, because there are many contextual factors that affect timing; moreover, which factors matter and what their precise effects are varies among languages. We describe here a language-independent approach for duration control. At run time, a language-independent timing module accesses languagespecific tables. These tables specify which sub-classes of the feature space (i.e., all combinations of context and phone identity) are homogeneous in the specific sense that the same factors have similar effects on the cases in a sub-class. Within a sub-class, durations are modeled by simple arithmetic models such as multiplicative, additive, or – more generally – sums-ofproducts models. Exploratory statistical methods (supervised) and parameter estimation techniques (unsupervised) are used for

No abstract available.

An understanding system, designed for both speech and text input, has been implemented based on statistical representation of task specific semantic knowledge. The core of the system is the conceptual decoder, which extracts the words and their association to the conceptual structure of the task directly from the acoustic signal. The conceptual information, which is also used to clarify the English sentences, is encoded following a statistical paradigm. A template generator and an SQL (structured query language) translator process the sentence and produce SQL code for querying a relational database. Results of the system on the official DARPA test are given.>

A word-based morphological analyzer and a dictionary for recognizing inflected forms of French words have been built by adapting the UDICT system. We describe the adaptations, emphasizing mechanisms developed to handle French verbs. This work lays the groundwork for doing French derivational morphology and morphology for other languages.