MaLa-ASR: Multimedia-Assisted LLM-Based ASR.
Guanrou YangZiyang MaFan YuZhifu GaoShiliang ZhangXie ChenPublished in: CoRR (2024)
Keyphrases
- automatic speech recognition
- multimedia
- speech recognition
- speech retrieval
- metadata
- learning environment
- noisy environments
- data sets
- spontaneous speech
- multimedia communication
- word error rate
- multimedia information retrieval
- multimedia content
- speech signal
- digital video
- multimedia systems
- conversational speech
- multimedia data
- evolutionary algorithm
- expert systems
- image processing
- learning algorithm
- genetic algorithm
- machine learning
- data mining
- databases