A Speaker Adaptive DNN Training Approach for Speaker-Independent Acoustic Inversion.
Leonardo BadinoLuca FranceschiRaman AroraMichele DoniniMassimiliano PontilPublished in: INTERSPEECH (2017)
Keyphrases
- speaker independent
- acoustic models
- speech recognition
- hidden markov models
- speaker dependent
- training process
- speaker identification
- speech recognizer
- automatic speech recognition
- digit recognition
- broadcast news
- language model
- speaker adaptation
- discriminative training
- speech synthesis
- speech signal
- neural network
- training set
- pattern recognition
- speech recognition systems
- information retrieval
- gaussian mixture model
- spoken language
- support vector machine
- image processing