Long Short-Term Memory for Speaker Generalization in Supervised Speech Separation.
Jitong ChenDeLiang WangPublished in: INTERSPEECH (2016)
Keyphrases
- speech recognition
- audio visual
- speaker recognition
- automatic speech recognition
- speaker verification
- speaker identification
- speaker diarization
- prosodic features
- speaker dependent
- automatic speech recognition systems
- vocal tract
- speech signal
- speech synthesis
- semi supervised
- hidden markov models
- recurrent neural networks
- text to speech
- acoustic features
- speech recognizer
- long short term memory
- broadcast news
- learning algorithm
- speech sounds
- unsupervised learning
- acoustic models
- probabilistic neural network
- automatic transcription
- gaussian mixture model
- phoneme recognition
- audio stream
- multi modal
- language model
- constructive induction
- feature selection
- supervised learning
- visual speech
- information retrieval
- speaker independent
- vector quantization
- speech recognition systems
- human computer interaction
- visual information
- visual data
- emotion recognition
- machine learning