2017/01/01 by Marian Tietz, Tayfun Alpay, Johannes Twiefel +1 · 7 citations
Computer Science · #Artificial intelligence #Artificial neural network #Baseline (sea) #Computer science #Field (mathematics) #Hidden Markov model #Machine learning #Music and Audio Processing #Pattern recognition (psychology) #Recurrent neural network #Speech Recognition and Synthesis #Speech and Audio Processing #Speech recognition #Supervised learning #TIMIT #Task (project management) #cs.CL #cs.LG #cs.NE
paper · pdf · doi:10.1007/978-3-319-68600-4_1
published in Lecture notes in computer science, 3-10 (Springer Science+Business Media)
openalex publication_date 2017/01/01 · arxiv created 2017/09/18 · arxiv updated 2017/09/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Ladder networks are a notable new concept in the field of semi-supervised learning by showing state-of-the-art results in image recognition tasks while being compatible with many existing neural architectures. We present the recurrent ladder network, a novel modification of the ladder network, for semi-supervised learning of recurrent neural networks which we evaluate with a phoneme recognition task on the TIMIT corpus. Our results show that the model is able to consistently outperform the baseline and achieve fully-supervised baseline performance with only 75% of all labels which demonstrates that the model is capable of using unsupervised data as an effective regulariser.