Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- articleNovember 2008
A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System
IEICE - Transactions on Information and Systems (TROIS), Volume E91-D, Issue 11Pages 2693–2700https://doi.org/10.1093/ietisy/e91-d.11.2693In a hidden Markov model (HMM), state duration probabilities decrease exponentially with time, which fails to adequately represent the temporal structure of speech. One of the solutions to this problem is integrating state duration probability ...
- articleSeptember 2008
HMM-Based Mask Estimation for a Speech Recognition Front-End Using Computational Auditory Scene Analysis
IEICE - Transactions on Information and Systems (TROIS), Volume E91-D, Issue 9Pages 2360–2364https://doi.org/10.1093/ietisy/e91-d.9.2360In this paper, we propose a new mask estimation method for the computational auditory scene analysis (CASA) of speech using two microphones. The proposed method is based on a hidden Markov model (HMM) in order to incorporate an observation that the mask ...
- articleMay 2007
A Hidden Semi-Markov Model-Based Speech Synthesis System
IEICE - Transactions on Information and Systems (TROIS), Volume E90-D, Issue 5Pages 825–834https://doi.org/10.1093/ietisy/e90-d.5.825A statistical speech synthesis system based on the hidden Markov model (HMM) was recently proposed. In this system, spectrum, excitation, and duration of speech are modeled simultaneously by context-dependent HMMs, and speech parameter vector sequences ...
- articleMarch 2007
State Duration Modeling for HMM-Based Speech Synthesis
IEICE - Transactions on Information and Systems (TROIS), Volume E90-D, Issue 3Pages 692–693https://doi.org/10.1093/ietisy/e90-d.3.692This paper describes the explicit modeling of a state duration's probability density function in HMM-based speech synthesis. We redefine, in a statistically correct manner, the probability of staying in a state for a time interval used to obtain the ...
- articleFebruary 2007
Adaptive Tuning of Buffer Pool Size in Database Server Based on Iterative Algorithm
IEICE - Transactions on Information and Systems (TROIS), Volume E90-D, Issue 2Pages 594–597https://doi.org/10.1093/ietisy/e90-d.2.594One of the system greatly affecting the performance of a database server is the size-division of buffer pools. This letter proposes an adaptive control method of the buffer pool sizes. This method obtains the nearly optimal division using only observed ...
-
- articleFebruary 2007
Reducing Computation Time of the Rapid Unsupervised Speaker Adaptation Based on HMM-Sufficient Statistics
IEICE - Transactions on Information and Systems (TROIS), Volume E90-D, Issue 2Pages 554–561https://doi.org/10.1093/ietisy/e90-d.2.554In real-time speech recognition applications, there is a need to implement a fast and reliable adaptation algorithm. We propose a method to reduce adaptation time of the rapid unsupervised speaker adaptation based on HMM-Sufficient Statistics. We use ...
- articleFebruary 2007
Average-Voice-Based Speech Synthesis Using HSMM-Based Speaker Adaptation and Adaptive Training
IEICE - Transactions on Information and Systems (TROIS), Volume E90-D, Issue 2Pages 533–543https://doi.org/10.1093/ietisy/e90-d.2.533In speaker adaptation for speech synthesis, it is desirable to convert both voice characteristics and prosodic features such as F0 and phone duration. For simultaneous adaptation of spectrum, F0 and phone duration within the HMM framework, we need to ...
- articleFebruary 2007
Constructing a Multilayered Boundary to Defend against Intrusive Anomalies
IEICE - Transactions on Information and Systems (TROIS), Volume E90-D, Issue 2Pages 490–499https://doi.org/10.1093/ietisy/e90-d.2.490We propose a model for constructing a multilayered boundary in an information system to defend against intrusive anomalies by correlating a number of parametric anomaly detectors. The model formulation is based on two observations. First, anomaly ...
- articleJanuary 2007
Two-Band Excitation for HMM-Based Speech Synthesis
IEICE - Transactions on Information and Systems (TROIS), Volume E90-D, Issue 1Pages 378–381https://doi.org/10.1093/ietisy/e90-1.1.378This letter describes a two-band excitation model for HMM-based speech synthesis. The HMM-based speech synthesis system generates speech from the HMM training data of the spectral and excitation parameters. Synthesized speech has a typical quality of "...
- articleJanuary 2007
Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005
IEICE - Transactions on Information and Systems (TROIS), Volume E90-D, Issue 1Pages 325–333https://doi.org/10.1093/ietisy/e90-1.1.325In January 2005, an open evaluation of corpus-based text-to-speech synthesis systems using common speech datasets, named Blizzard Challenge 2005, was conducted. Nitech group participated in this challenge, entering an HMM-based speech synthesis system ...
- articleSeptember 2006
Robust Scene Extraction Using Multi-Stream HMMs for Baseball Broadcast
IEICE - Transactions on Information and Systems (TROIS), Volume E89-D, Issue 9Pages 2553–2561https://doi.org/10.1093/ietisy/e89-d.9.2553In this paper, we propose a robust statistical framework for extracting scenes from a baseball broadcast video. We apply multi-stream hidden Markov models (HMMs) to control the weights among different features. To achieve a large robustness against new ...
- articleJuly 2006
HHMM Based Recognition of Human Activity*This paper was presented at MVA2005.
IEICE - Transactions on Information and Systems (TROIS), Volume E89-D, Issue 7Pages 2180–2185https://doi.org/10.1093/ietisy/e89-d.7.2180In this paper, we present a method for recognition of human activity as a series of actions from an image sequence. The difficulty with the problem is that there is a chicken-egg dilemma that each action needs to be extracted in advance for its ...
- articleJuly 2006
Surface Reconstruction from Stereo Data Using a Three-Dimensional Markov Random Field Model
IEICE - Transactions on Information and Systems (TROIS), Volume E89-D, Issue 7Pages 2028–2035https://doi.org/10.1093/ietisy/e89-d.7.2028In the present paper, we propose a method for reconstructing the surfaces of objects from stereo data. Both the fitness of stereo data to surfaces and interrelation between the surfaces are defined in the framework of a three-dimensional (3-D) Markov ...
- articleMay 2006
Non-saturated Throughput Analysis of IEEE 802.11 Ad Hoc Networks
IEICE - Transactions on Information and Systems (TROIS), Volume E89-D, Issue 5Pages 1676–1678https://doi.org/10.1093/ietisy/e89-d.5.1676This letter presents a simple but accurate analytical model to evaluate the throughput of IEEE 802.11 distributed coordination function in non-saturated conditions. The influence of offered load on the throughput of both basic and RTS/CTS access ...
- articleMarch 2006
A Non-stationary Noise Suppression Method Based on Particle Filtering and Polyak Averaging
IEICE - Transactions on Information and Systems (TROIS), Volume E89-D, Issue 3Pages 922–930https://doi.org/10.1093/ietisy/e89-d.3.922This paper addresses a speech recognition problem in non-stationary noise environments: the estimation of noise sequences. To solve this problem, we present a particle filter-based sequential noise estimation method for front-end processing of speech ...
- articleMarch 2006
What HMMs Can Do
IEICE - Transactions on Information and Systems (TROIS), Volume E89-D, Issue 3Pages 869–891https://doi.org/10.1093/ietisy/e89-d.3.869Since their inception almost fifty years ago, hidden Markov models (HMMs) have have become the predominant methodology for automatic speech recognition (ASR) systems---today, most state-of-the-art speech systems are HMM-based. There have been a number ...
- articleDecember 2005
Robust Speech Recognition Using Discrete-Mixture HMMs
IEICE - Transactions on Information and Systems (TROIS), Volume E88-D, Issue 12Pages 2811–2818https://doi.org/10.1093/ietisy/e88-d.12.2811This paper introduces new methods of robust speech recognition using discrete-mixture HMMs (DMHMMs). The aim of this work is to develop robust speech recognition for adverse conditions that contain both stationary and non-stationary noise. In particular,...
- articleDecember 2005
Behavioral Analysis of a Fault-Tolerant Software System with Rejuvenation
IEICE - Transactions on Information and Systems (TROIS), Volume E88-D, Issue 12Pages 2681–2690https://doi.org/10.1093/ietisy/e88-d.12.2681In recent years, considerable attention has been devoted to continuously running software systems whose performance characteristics are smoothly degrading in time. Software aging often affects the performance of a software system and eventually causes ...
- articleSeptember 2005
Tree-Structured Clustering Methods for Piecewise Linear-Transformation-Based Noise Adaptation
IEICE - Transactions on Information and Systems (TROIS), Volume E88-D, Issue 9Pages 2168–2176https://doi.org/10.1093/ietisy/e88-d.9.2168This paper proposes the application of tree-structured clustering to the processing of noisy speech collected under various SNR conditions in the framework of piecewise-linear transformation (PLT)-based HMM adaptation for noisy speech. Three kinds of ...
- articleJune 2005
Extension of Hidden Markov Models for Multiple Candidates and Its Application to Gesture Recognition
IEICE - Transactions on Information and Systems (TROIS), Volume E88-D, Issue 6Pages 1239–1247https://doi.org/10.1093/ietisy/e88-d.6.1239We propose a modified Hidden Markov Model (HMM) with a view to improve gesture recognition using a moving camera. The conventional HMM is formulated so as to deal with only one feature candidate per frame. However, for a mobile robot, the background and ...