Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition.
Felix WeningerMarco GaudesiRalf LeiboldRoberto GemelloPuming ZhanPublished in: ASRU (2021)
Keyphrases
- speech recognition
- bit rate
- hidden markov models
- language model
- speech synthesis
- automatic speech recognition
- pattern recognition
- speech processing
- speech recognition systems
- speaker identification
- speech understanding
- speech recognizer
- noisy environments
- speech signal
- video coding
- keyword spotting
- speech recognition errors
- speech retrieval
- speech recognition technology
- image quality
- motion estimation
- information retrieval
- speech recognizers
- speaker adaptation
- computer vision