Kazutaka Maruyama

Learn More
Speech acoustics is inevitably distorted by non-linguistic features such as vocal tract length, gender, age, microphone, room, line, hearing characteristics, and so on. Recently, a novel acoustic representation of speech was proposed, called the acoustic universal structure[1, 2]. It discards all the absolute properties of speech events and captures only(More)
Speech acoustics varies from speaker to speaker, microphone to microphone, room to room, line to line, etc. Physically speaking, every speech sample is distorted. Socially speaking, however, speech is the easiest communication media for humans. In order to cope with the inevitable distortions, speech engineers have built HMMs with speech data of hundreds or(More)
Because the number of Web pages is very huge, and still increasing, many people have difficulty to reach pages they want. Although social bookmarking and search engines are helpful, users still have to find pages themselves. Our goal is to recommend Web pages which are supposed to be interesting for a user, without active effort by the user. We first(More)
In recent years, social networking services have come into wide use to people. Especially, one of micro blog services, Twitter is a significant service. Twitter user gets information by following other users whose tweets match his interest. Retweet is one of Twitter functions which spreads tweets to other users. Using retweets, one can read tweets(More)
A program for self assessment of Japanese pronunciation by English-speaking learners was developed using a language model built with input from a language teacher in collaboration with speech engineers. This collaboration enhanced the program’s capacity for accurate assessment and provides practical support to users by linking evaluation with feedback, and(More)
Browsing histories are often used to build user profiles for browsing supports and personalizations. But, the browsing history also contains HTTP requests generated concomitantly with user activity(concomitant request), which must be removed in order to build correct user profiles. Current filtering methods are based on rather simple characteristics of(More)
This paper describes the development of an estimator of perceptual femininity (PF) of an input utterance using speaker recognition techniques. The estimator was designed for its clinical use and the target speakers are gender identity disorder (GID) clients, especially MtF (male to female) transsexuals. The voice therapy for MtFs is composed of three kinds(More)