A Discriminative Training Framework using N-Best Speech Recognition Transcriptions and Scores for Spoken Utterance Classification.
Sibel YamanLi DengDong YuYe-Yi WangAlex AceroPublished in: ICASSP (4) (2007)
Keyphrases
- speech recognition
- automatic speech recognition
- discriminative training
- hidden markov models
- pattern recognition
- speech signal
- language model
- broadcast news
- noisy environments
- speech synthesis
- minimum classification error
- speech recognizer
- speaker identification
- probabilistic model
- conversational speech
- speech retrieval
- spontaneous speech
- speech recognition systems
- classification accuracy
- feature extraction
- speaker independent
- machine learning
- feature vectors
- face recognition
- feature selection
- computer vision