Multi-Space Probability Distribution HMM

Keiichi Tokuda, Takashi Masuko, Noboru Miyazaki, +1

IEICE Transactions on Information and Systems

EngineeringSpeech RecognitionStatistical Signal ProcessingData SciencePattern Recognition +16

Noise robust voice activity detection based on periodic to aperiodic component ratio

Kentaro Ishizuka, Tomohiro Nakatani, Masakiyo Fujimoto, +1

Speech Communication

EngineeringHealth SciencesVoiceComponent RatioNoise +10

Understanding unsegmented user utterances in real-time spoken dialogue systems

Mikio Nakano, Noboru Miyazaki, Jun-ichi Hirasawa, +2

EngineeringSpoken Language ProcessingSpoken Dialog SystemCommunicationUnsegmented User Utterances +18

Evaluating discourse understanding in spoken dialogue systems

Ryuichiro Higashinaka, Noboru Miyazaki, Mikio Nakano, +1

ACM Transactions on Speech and Language Processing

EngineeringSpoken Language ProcessingRhetoricSpoken Dialog SystemCommunication +16

Noise robust front-end processing with voice activity detection based on periodic to aperiodic component ratio

Kentaro Ishizuka, Tomohiro Nakatani, Masakiyo Fujimoto, +1

EngineeringRobust Front-end ProcessingVoiceHealth SciencesComponent Ratio +11

WIT

Mikio Nakano, Noboru Miyazaki, Norihito Yasuda, +4

Natural Language ProcessingIncremental Understanding MechanismConversational User InterfaceEngineeringDialogue Management +13

New feature parameters for detecting misunderstandings in a spoken dialogue system

Jun-ichi Hirasawa, Noboru Miyazaki, Mikio Nakano, +1

EngineeringSpoken Language ProcessingSpoken Dialog SystemCommunicationCorpus Linguistics +16

Pitch pattern generation using multispace probability distribution HMM

Takashi Masuko, Keiichi Tokuda, Noboru Miyazaki, +1

Systems and Computers in Japan

EngineeringPitch Pattern GenerationPhonologyAcoustic ModelingSpeech Recognition +21

Speech feature extraction method using subband-based periodicity and nonperiodicity decomposition

Kentaro Ishizuka, Tomohiro Nakatani, Yasuhiro Minami, +1

The Journal of the Acoustical Society of America

EngineeringFeature ExtractionSpeech RecognitionPeriodicity MeasurementsNoise +15