Discovering phonetic inventories with crosslingual automatic speech recognition.
Piotr ZelaskoSiyuan FengLaureano Moro-VelázquezAli AbavisaniSaurabhchand BhatiOdette ScharenborgMark Hasegawa-JohnsonNajim DehakPublished in: Comput. Speech Lang. (2022)
Keyphrases
- automatic speech recognition
- speech recognition
- speech sounds
- word error rate
- speech signal
- broadcast news
- hidden markov models
- automatically generated
- acoustic models
- spoken term detection
- conversational speech
- speech recognizer
- pattern recognition
- speech retrieval
- speech segments
- language model
- spoken words
- speech synthesis
- speaker independent
- acoustic features
- noisy environments
- speaker identification
- word recognition
- recognition errors
- spontaneous speech
- spoken document retrieval
- discriminative training
- speech corpus
- neural network
- speaker adaptation
- bayesian networks