Contextual-Utterance Training for Automatic Speech Recognition.
Alejandro Gomez-AlanisLukas DrudeAndreas SchwarzRupak Vignesh SwaminathanSimon WieslerPublished in: CoRR (2022)
Keyphrases
- automatic speech recognition
- speech recognition
- conversational speech
- discriminative training
- speech signal
- acoustic models
- speech segments
- speech retrieval
- word error rate
- hidden markov models
- language model
- spoken words
- broadcast news
- spontaneous speech
- recognition errors
- noisy environments
- word recognition
- speech recognizer
- speech synthesis
- pattern recognition
- acoustic features
- compound words