Mixture Encoder for Joint Speech Separation and Recognition.
Simon BergerPeter VietingChristoph BöddekerRalf SchlüterReinhold Haeb-UmbachPublished in: INTERSPEECH (2023)
Keyphrases
- recognition engine
- recognition rate
- speech recognition
- object recognition
- recognition accuracy
- speech corpus
- feature extraction
- recognition algorithm
- continuous speech recognition
- automatic speech recognition systems
- activity recognition
- noisy environments
- speech sounds
- mixture model
- spoken words
- speech recognition systems
- blind separation
- phoneme recognition
- pattern recognition
- digit recognition
- text recognition
- speech synthesis
- low complexity
- action recognition
- bit rate
- expectation maximization
- motion estimation
- word recognition
- automatic recognition
- gesture recognition
- character recognition
- gaussian mixture model
- rate distortion