wav2vec and its current potential to Automatic Speech Recognition in German for the usage in Digital History: A comparative assessment of available ASR-technologies for the use in cultural heritage contexts.
Michael FleckWolfgang GöderlePublished in: CoRR (2023)
Keyphrases
- automatic speech recognition
- cultural heritage
- speech recognition
- digital objects
- web based technologies
- digital libraries
- speech signal
- digital archives
- hidden markov models
- multimedia
- conversational speech
- speech retrieval
- digital collections
- word error rate
- digital media
- spontaneous speech
- cidoc crm
- knowledge society
- spoken words
- broadcast news
- noisy environments
- virtual museum
- acoustic features
- recognition errors
- word recognition
- speech corpus
- speech recognizer
- web technologies
- learning systems
- language model
- social media
- pattern recognition
- speech recognizers
- neural network