Minimum Classification Error Training of Hidden Conditional Random Fields for Speech and Speaker Recognition

Hidden Conditional Neural Fields for Continuous Phoneme Speech Recognition

In this paper, we propose Hidden Conditional Neural Fields (HCNF) for continuous phoneme speech recognition, which are a combination of Hidden Conditional Random Fields (HCRF) and a MultiLayer Perceptron (MLP), and inherit their merits, namely, the discriminative property for sequences from HCRF and the ability to extract non-linear features from an MLP. HCNF can incorporate many types of featu...

Large-margin conditional random fields for single-microphone speech separation

Conditional random field (CRF) formulations for singlemicrophone speech separation are improved by large-margin parameter estimation. Speech sources are represented by acoustic state sequences from speaker-dependent acoustic models. The large-margin technique improves the classification accuracy of acoustic states by reducing generalization error in the training phase. Non-linear mappings inspi...

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words

Monotone string-to-string translation for NLU and ASR tasks

Monotone string-to-string translation problems have to be tackled as part of almost all stateof-the-art natural language understanding and large vocabulary continuous speech recognition systems. In this work, two such tasks will be investigated in detail and improved using conditional random fields, namely concept tagging and grapheme-to-phoneme conversion. Concept tagging is usually one of the...