Sprache im 20. Jahrhundert. Gegenwartssprache
Refine
Document Type
- Conference Proceeding (2)
- Article (1)
- Part of a Book (1)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4)
Keywords
- Automatische Spracherkennung (4) (remove)
Publicationstate
- Postprint (1)
- Veröffentlichungsversion (1)
- Zweitveröffentlichung (1)
Reviewstate
- (Verlags)-Lektorat (1)
- Peer-Review (1)
Publisher
- Bibliographisches Institut (1)
- Narr (1)
- Wydawnictwo Poznańskie (1)
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.
The aim of this paper is to highlight the actual need for corpora that have been annotated based on acoustic information. The acoustic information should be coded in features or properties and is needed to inform further processing systems, i.e. to present a basis for a speech recognition system using linguistic information. Feature annotation of existing corpora in combination with segmental annotation can provide a powerful training material for speech recognition systems, but will as well challenge the further processing of features to segments and syllables. We present here the theoretical preliminaries for our multilingual feature extraction system, that we are currently working on.
The development of tools for computer-assisted transcription and analysis of extensive speech corpora is one main issue at the Institute of German Language (IDS) and the Institute of Natural Language Processing (IMS). Corpora of natural spoken dialogue have been transcribed, and the analogue recordings of these discourses are digitized. An automatic segmentation system is employed which is based on Hidden Markov Models. The orthographic representation of the speech signal is transformed into a phonetic representation, the phonetic transcription is transformed into a system-internal representation, and the time alignment between text and speech signal follows. In this article, we also describe the retrieval software Cosmas II and its special features for searching discourse transcripts and playing time aligned passages.