Explainability of Speech Recognition Transformers via Gradient-Based Attention Visualization.
Tianli SunHaonan ChenGuosheng HuLianghua HeCairong ZhaoPublished in: IEEE Trans. Multim. (2024)
Keyphrases
- speech recognition
- hidden markov models
- language model
- speech processing
- speech synthesis
- speech recognizer
- speech signal
- pattern recognition
- automatic speech recognition
- speech recognition technology
- keyword spotting
- speech recognizers
- speech understanding
- speech recognition systems
- noisy environments
- speaker independent
- speaker identification
- isolated word
- computer vision
- speaker dependent
- self organizing maps
- background noise
- handwriting recognition
- feature selection