Unsupervised speaker adaptation of DNN-HMM by selecting similar speakers for lecture transcription.
Masato MimuraTatsuya KawaharaPublished in: APSIPA (2014)
Keyphrases
- speaker adaptation
- speech recognition
- maximum likelihood
- automatic speech recognition
- hidden markov models
- speech recognition systems
- speaker independent
- speech recognizer
- speaker dependent
- handwriting recognition
- semi supervised
- speech synthesis
- language model
- pattern recognition
- unsupervised learning
- digit recognition
- feature vectors
- computer vision