TAILIEUCHUNG - Báo cáo khoa học: "How spoken language corpora can refine current speech motor training methodologies"

The growing availability of spoken language corpora presents new opportunities for enriching the methodologies of speech and language therapy. In this paper, we present a novel approach for constructing speech motor exercises, based on linguistic knowledge extracted from spoken language corpora. In our study with the Dutch Spoken Corpus, syllabic inventories were obtained by means of automatic syllabification of the spoken language data. | How spoken language corpora can refine current speech motor training methodologies Federico Sangati Institute for Logic Language and Computation Daniil Umanski Niels O. Schiller Leiden Institute for Brain and Cognition Leiden University The Netherlands University of Amsterdam the Netherlands Abstract The growing availability of spoken language corpora presents new opportunities for enriching the methodologies of speech and language therapy. In this paper we present a novel approach for constructing speech motor exercises based on linguistic knowledge extracted from spoken language corpora. In our study with the Dutch Spoken Corpus syllabic inventories were obtained by means of automatic syllabification of the spoken language data. Our experimental syllabification method exhibited a reliable performance and allowed for the acquisition of syllabic tokens from the corpus. Consequently the syllabic tokens were integrated in a tool for clinicians a result which holds the potential of contributing to the current state of speech motor training methodologies. 1 Introduction Spoken language corpora are often accessed by linguists who need to manipulate specifically defined speech stimuli in their experiments. However this valuable resource of linguistic information has not yet been systematically applied for the benefit of speech therapy methodologies. This is not surprising considering the fact that spoken language corpora have only appeared relatively recently and are still not easily accessible outside the NLP community. Existing applications for selecting linguistic stimuli although undoubtedly useful are not based on spoken language data and are generally not designed for utilization by speech therapists per se Aichert et al. 2005 . As a first attempt to bridge this gap a mechanism is proposed for utilizing the relevant linguistic information to the service of clinicians. In coordination with .

• Báo cáo khoa học
• language corpora
• refine current speech motor
• training methodologies
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Effect of Cross Language IR
• Bilingual Lexicon Acquisition
• Comparable Corpora
• scientific reports
• model language
• process natural language
• Exploiting Comparable Corpora
• Bilingual Dictionaries
• Cross Language Text Categorization
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Word Alignment
• Languages with Scarce Resources
• Bilingual Corpora of Other Language Pairs
• Scaling to Very Very Large Corpora
• Michele Banko and Eric Brill
• Natural Language Disambiguation
• Bilingual Terminology Acquisition
• Comparable Corpora and Phrasal
• Translation to Cross Language Information Retrieval
• Bringing corpora into language classrooms
• English corpus based discourses
• Teach linking devices
• Writing lessons
• Application of connectors in formal writing
• Large linguistically processed Web corpora
• multiple languages
• Marco Baroni
• Detecting Highly Confident Word Translations
• Any Prior Knowledge
• Multilingual Term Extraction
• Domain specific Corpora
• Morphological Structure
• Validation of sub sentential paraphrases acquired
• parallel monolingual corpora
• Houda Bouamor
• On the use of Comparable
• Corpora to improve
• SMT performance
• Learning Translations
• Named Entity Phrases
• Parallel Corpora
• Analysing Wikipedia
• Gold Standard Corpora
• NER Training
• The Corpora Management
• System Based on Java
• Oracle Technologies
• A Method for Effective
• Scalable Mining of Named Entity Transliterations
• Large Comparable Corpora
• Deriving Generalized Knowledge from Corpora
• WordNet Abstraction
• Benjamin Van Durme
• Feature based Method
• Document Alignment
• Comparable News Corpora
• Finite Structure Query
• A Tool for Querying Syntactically
• Annotated Corpora
• Creating a Multilingual Collocation Dictionary
• Large Text Corpora
• Luka Nerima
• Power Law Distributions
• Paraphrases Extracted
• Bilingual Corpora
• Development of Corpora
• the CLaRK System
• The BulTreeBank Project Experience
• Toward Statistical Machine Translation
• Alexandre Klementiev
• An Alignment Method
• Noisy Parallel Corpora
• Image Processing Techniques
• Lecture Natural language processing
• Natural language processing
• Natural language
• Language processing
• Computational linguistics
• Parallel corpora application