Josef V. Psutka

automatic speech recognition (3) pronunciation embedding (2) spoken term detection (2) siamese neural network (2) self-supervised learning (2) recurrent neural network (1) language model (1) siamese network (1) multilingual model (1) lstm network (1) cosine distance (1) wav2vec 2.0 (1) monolingual model (1) hearing impairment (1) multilingual speech recognition (1) transformer-based speech recognition (1) out-of-vocabulary term (1) live subtitling (1) oral history (1) transformer model (1)