Data-Driven Pronunciation Modeling of Swiss German Dialectal Speech for Automatic Speech Recognition.
Michael StadtschnitzerChristoph SchmidtPublished in: LREC (2018)
Keyphrases
- automatic speech recognition
- speech recognition
- data driven
- speech signal
- word error rate
- spontaneous speech
- broadcast news
- hidden markov models
- speech corpus
- conversational speech
- acoustic models
- spoken words
- speech synthesis
- acoustic features
- speech recognizers
- noisy environments
- speech retrieval
- discriminative training
- recognition errors
- speech recognizer
- speaker identification
- word recognition
- speech sounds
- speaker independent
- language model
- image processing