Kazuki Konno

  • Citations Per Year
Learn More
This paper investigates speaker-independent speech recognition with speaker-class models. In previous studies based on this method, the number of speaker classes was relatively small and it was difficult to improve the performance significantly over the baseline. In this work, as many as 500 speaker-class models are used to enable more precise modeling of(More)
This paper proposes a new speech recognition method based on speaker-class (SC) models. In previous studies based on this approach, Gaussian-mixture-model-based hidden Markov models (GMM-HMMs) have mainly been used as acoustic models. In this work, SC models that have deep neural network (DNN)-based HMM (DNN-HMM) structures are investigated and used for(More)
Countries in the Organization of Economic Co-operation and Development (OECD) vary widely in their ratio of capital tax rates to labor tax rates. This paper’s motivation is the strong negative correlation between the capital/labor tax ratio and old dependency ratio (de…ned as the ratio of population older than 65 years old to population between 20 and 65(More)
It is well known that deep learning-based speech recognition improves performance significantly. In deep learning based systems, the deep neural network hidden Markov model (DNN-HMM) is used as an acoustic model (AM). Recently, speaker adaptation techniques based on DNN-HMM have also been investigated. The aim of this work is to improve the performance of(More)
This paper uses the political economy model of Battaglini and Coate (2008) to analyze the impact of a balanced budget rule that requires that legislators do not run deficits. It considers both a strict rule which cannot be circumvented and a rule that can be overridden by a super-majority of legislators. A strict rule leads to a gradual but substantial(More)
  • 1