CONSIDERING THE PECULIARITY OF SPONTANEOUS SPEECH AT THE DEVELOPING AUTOMATIC SPEECH RECOGNITION SYSTEM
Annotation
An approach to automatic processing of spontaneous Russian speech, consisting in recognition of nonphonemic elements and modeling of alternative variants of word pronunciation, is considered. A set of acoustic and lexical models, that are intended for separation of noises from keywords and that take into account possible elements of spontaneous speech, is represented. An algorithm of creation of alternative transcriptions by extended transcribing rules is presented. Experimental results are represente
Keywords
Постоянный URL
Articles in current issue
- AGENT-BASED SYSTEM MODELING LANGUAGE
- AGENT-BASED APPROACH FOR CONFIGURATION OF VIRTUAL ENTERPRISES
- BUILDING COOPERATIVE SELF-ORGANISING NETWORKS: MAJOR TASKS AND TECHNOLOGIES
- ANALYSIS OF CREDIT BASED MECHANISM OF NETWORK WORM EPIDEMICS DETECTION AND CONTAINMENT
- SOFTWARE PROTECTION MODEL BASED ON REMOTE ENTRUSTING MECHANISM
- FILTERING POLICY VERIFICATION BASED ON EVENT CALCULUS AND ABDUCTION REASONING
- TESTING PROCESS OF FUNCTIONAL MODELS TRANSFORMATION BASED ON HYBRID METHODS
- COMPARISON OF METHODS FOR LOCALISATION OF MULTIMODAL SYSTEM USER BY HIS SPEECH
- AUTOMATIC SYNTACTIC ANALYSIS OF RUSSIAN TEXTS BASED ON THE PHRASESTRUCTURE GRAMMAR
- CHOOSING THE MODEL OF FUNCTIONING OF A TECHNICAL SYSTEM FROM THE SET OF ITS ALTERNATIVE MODELS
- DYNAMIC MODEL OF INTEGRATED PLANNING AND SCHEDULING FOR MODERNIZATION AND FUNCTIONING OF INFORMATION SYSTEM
- USING MULTI-AGENT SIMULATOR FOR MODELING DISTRIBUTED SYSTEM
- INTELLIGENT MONITORING SYSTEM OF THE ESPECIALLY DANGEROUS PROCESSES