Refine
Year of publication
- 2005 (35) (remove)
Document Type
- Part of a Book (19)
- Conference Proceeding (11)
- Article (3)
- Preprint (1)
- Working Paper (1)
Language
- English (35) (remove)
Has Fulltext
- yes (35)
Is part of the Bibliography
- no (35)
Keywords
- Englisch (13)
- Deutsch (9)
- Massenmedien (4)
- Computerlinguistik (3)
- Mediensprache (3)
- Russisch (3)
- Semantik (3)
- Annotation (2)
- Auszeichnungssprache (2)
- Automatische Spracherkennung (2)
Publicationstate
- Veröffentlichungsversion (12)
- Postprint (5)
- Zweitveröffentlichung (1)
Reviewstate
- (Verlags)-Lektorat (11)
- Peer-Review (3)
- Review-Status-unbekannt (1)
Publisher
We present an implemented XML data model and a new, simplified query language for multi-level annotated corpora. The new query language involves automatic conversion of queries into the underlying, more complicated MMAXQL query language. It supports queries for sequential and hierarchical, but also associative (e.g. coreferential) relations. The simplified query language has been designed with non-expert users in mind.
This English language version (translated by Martin Wynne) is a reworked and slightly abridged version of the paper given in Canterbury in February 1999. A German language version has appeared as Hellmann, Manfred W.: ‘Wörter in Texten der Wendezeit’ 1989-1990 - Ein Wörterbuch zur lexikographischen Erschließung des ‘Wendekorpus’ in Jordanova, Ljubima (edj: 10 godini promjana v Iztotschna Evropa (10 Jahre Wende in Osteuropa), (= Socio- linguistika Bd. 4), BULLEKS: Sofia (Bulgaria) 1999, S. 11-39.
The naturalness of synthetic speech depends strongly on the prediction of appropriate prosody. For the present study the original annotation of the German speech database “Kiel Corpus of Read Speech” was extended automatically with syntactic features, word frequency, and syllable boundaries. Several classification and regression trees for predicting symbolic prosody features, postlexical phonological processes, duration, and F0 were trained on this database. The perceptual evaluation showed that the overall perceptual quality of the German text-to-speech system MARY can be significantly improved by training all models that contribute to prosody prediction on the same database. Furthermore, it showed that the error introduced by symbolic prosody prediction perceptually equals the error produced by a direct method that does not exploit any symbolic prosody features.
This paper is concerned with a novel methodology for generating phonetic questions used in tree-based state tying for speech recognition. In order to implement a speech recognition system, language-dependent knowledge which goes beyond annotated material is usually required. The approach presented here generates phonetic questions for decision trees are based on a feature table that summarizes the articulatory characteristics of each sound. On the one hand, this method allows better language-specific triphone models to be defined given only a feature-table as linguistic input. On the other hand, the feature-table approach facilitates efficient definition of triphone models for other languages since again only a feature table for this language is required. The approach is exemplified with speech recognition systems for English and Thai.
In this paper, I argue against the analyses of the there-construction by Moro (1997) and Hoekstra & Mulder (1990) and for an analysis in the frame of Williams (1994), Hazout (2004) from two angles. First of all, Moro and Hoekstra & Mulder do not correctly predict the behaviour of the there-construction under wh-movement; second, from a semantic point of view, the predicate in the small clause structure is the postverbal DP and not there. Alternatively, I follow the proposal by Williams (1994) in which there is the subject of predication and I will point out a direction to analyse the problematic wh-movement data within this framework.
HMMs are the dominating technique used in speech recognition today since they perform well in overall phone recognition. In this paper, we show the comparison of HMM methods and machine learning techniques, such as neural networks, decision trees and ensemble classifiers with boosting and bagging in the task of articulatory-acoustic feature classification. The experimental results show that HMM methods work well for the classification of such features as vocalic. However, decision tree and bagging outperform HMMs for the fricative classification task since the data skewness is much higher than for the feature vocalic classification task. This demonstrates that HMMs do not perform as well as decision trees and bagging in highly skewed data settings.
This paper provides a lexicalist formal description of preposition-pronoun contraction (PPC) in Polish, using the theoretical framework of HPSG. Considering the behaviour of PPC with respect to the prosodic, categorial, syntactic and semantic properties, the assumption can be made that each PPC is a morphological unit with prepositional status. The crucial difference between a PPC and a typical preposition consists, besides the phonological form, in the valence properties. While a typical preposition realizes its complement externally via general constraints on phrase structure, the realization of a PPC argument is effected internally by virtue of its lexical entry. Here, we will provide the appropriate implicational lexical constraints that license both typical Ps and PPCs.