“My Small Slim Greek ASR System” or Automatic Speech Recognition of Modern Greek Broadcast News
نویسندگان
چکیده
In this paper we report on the development of a Modern Greek large-vocabulary continuous-speech recognition system. We discuss lexical modelling with respect to pronuciation generation and examine its effects on word accuracies. Peculiarities of Modern Greek as a highly inflectional language and their challenges for speech recognition are addressed.
منابع مشابه
Development of a Modern Greek Broadcast-News Corpus and Speech Recognition System
We report on the creation of a Modern Greek broadcast-news corpus as a pre-requisite to build a large-vocabulary continuous-speech recognition system. We discuss lexical modelling with respect to pronuciation generation and examine the effects of the lexicon size on word accuracies. Peculiarities of Modern Greek as a highly inflectional language and their challenges for speech recognition are d...
متن کاملLanguage and variety verification on broadcast news for Portuguese
This paper describes a language/accent verification system for Portuguese, that explores different type of properties: acoustic, phonotactic and prosodic. The two-stage system is designed to be used as a pre-processing module for the Portuguese Automatic Speech Recognition (ASR) system developed at INESC-ID. As the ASR system is applied everyday to transcribe the evening news from a Portuguese ...
متن کاملSummarization of Broadcast News Using Speaker Tracking
In this paper we demonstrate an automatic summarization system for broadcast news shows. The proposed technique does not require ASR transcripts or human reference summaries. The system exploits the role of anchor speaker in a news show by tracking his/her speech to construct indicative extractive summaries. Speaker tracking is done by autoassociative neural network model. Summaries are generat...
متن کاملTranscrigal: A Bilingual System for Automatic Indexing of Broadcast News
This paper describes a Broadcast News (BN) database called Transcrigal-DB. The news shows are mainly in Galician language, although around 11% of data is in Spanish. This database has been constructed for automatic speech recognition (ASR) purposes. A BN-ASR reference system is also described and evaluated on the test partition of Transcrigal-DB. The reference system has been designed having in...
متن کاملVOXALEAD: A Scalable Video Search Engine Based On Content
Most news organizations provide immediate access to topical news broadcasts through RSS streams or podcasts. Until recently, applications have not permitted a user to perform content based search within a longer spoken broadcast to find the segment that might interest them. Recent progress in both automatic speech recognition (ASR) and natural language processing (NLP) has produced robust tools...
متن کامل