Mikko Kurimo

Latest

• Advances in subword-based HMM-DNN speech recognition across languages
• First-pass decoding with n-gram approximation of RNNLM: The problem of rare words
• The Aalto system based on fine-tuned AudioSet features for DCASE2018 task2 - general purpose audio tagging
• First-pass decoding with n-gram approximation of RNNLM: The problem of rare words
• New Baseline in Automatic Speech Recognition for Northern Sámi
• Aalto system for the 2017 Arabic multi-genre broadcast challenge
• Character-based units for Unlimited Vocabulary Continuous Speech Recognition
• Automatic Speech Recognition with Very Large Conversational Finnish and Estonian Vocabularies
• Improved Subword Modeling for WFST-Based Speech Recognition
• Automatic Construction of the Finnish Parliament Speech Corpus
• Reading validation for pronunciation evaluation in the Digitala project
• Towards SamiTalk: A Sami-Speaking Robot Linked to Sami Wikipedia
• Automatic Speech Recognition for Northern Sámi with comparison to other Uralic Languages
• Morfessor 2.0: Toolkit for statistical morphological segmentation
• Morfessor 2.0: Python Implementation and Extensions for Morfessor Baseline
• Creating synthetic voices for children by adapting adult average voice using stacked transformations and VTLN
• Using stacked transformations for recognizing foreign accented speech