Recycle Your Wav2Vec2 Codebook: A Speech Perceiver for Keyword Spotting.
Guillermo CámbaraJordi LuqueMireia FarrúsPublished in: COLING (2022)
Keyphrases
- keyword spotting
- speech recognition
- speech processing
- vector quantization
- hidden markov models
- speech signal
- printed documents
- pattern recognition
- signal processing
- bag of words
- automatic speech recognition
- language model
- image representation
- speaker identification
- feature vectors
- natural language processing
- character recognition
- text classification
- noisy environments
- artificial intelligence
- image retrieval
- image classification
- multimedia systems
- handwritten documents
- image processing