Beam-TasNet: Time-domain Audio Separation Network Meets Frequency-domain Beamformer

Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, +3

High Asr PerformanceEngineeringHealth SciencesMulti-speaker Speech RecognitionPhonetics +13

How bad are artifacts?: Analyzing the impact of speech enhancement errors on ASR

Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, +4

Interspeech 2022

EngineeringSpeech EnhancementSpeech RecognitionSpeech CodingNoise +16

The Hitachi/JHU CHiME-5 system: Advances in speech recognition for everyday home environments using multiple microphone arrays

Naoyuki Kanda, Rintaro Ikeshita, Shota Horiguchi, +13

EngineeringHitachi/jhu Chime-5 SystemHealth SciencesChime ChallengeRobust Speech Recognition +9

Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches

Naoyuki Kanda, Yusuke Fujita, Shota Horiguchi, +3

EngineeringSpeech EnhancementAcoustic ModelingTraining PipelineSpeech Recognition +17

Independent Vector Extraction for Fast Joint Blind Source Separation and Dereverberation

Rintaro Ikeshita, Tomohiro Nakatani

IEEE Signal Processing Letters

Source SeparationImage AnalysisEngineeringComputer EngineeringNoise +13

A Joint Diagonalization Based Efficient Approach to Underdetermined Blind Audio Source Separation Using the Multichannel Wiener Filter

Nobutaka Ito, Rintaro Ikeshita, Hiroshi Sawada, +1

IEEE/ACM Transactions on Audio Speech and Language Processing

Source SeparationDiagonal MatricesEngineeringData ScienceAudio Signal Processing +12

Block Coordinate Descent Algorithms for Auxiliary-Function-Based Independent Vector Extraction

Rintaro Ikeshita, Tomohiro Nakatani, Shoko Araki

IEEE Transactions on Signal Processing

Linear MixtureSupport Vector MachineMixture DistributionEngineeringMachine Learning +11

Blind and Neural Network-Guided Convolutional Beamformer for Joint Denoising, Dereverberation, and Source Separation

Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, +2

Source SeparationEngineeringSpeech EnhancementNoise ReductionSpeech Recognition +19

DNN-supported Mask-based Convolutional Beamforming for Simultaneous Denoising, Dereverberation, and Source Separation

Tomohiro Nakatani, Riki Takahashi, Tsubasa Ochiai, +4

Source SeparationEngineeringSpeech EnhancementSpeech RecognitionDeblurring +14

Blind Signal Dereverberation Based on Mixture of Weighted Prediction Error Models

Rintaro Ikeshita, Naoyuki Kamo, Tomohiro Nakatani

IEEE Signal Processing Letters

Source SeparationBlind Signal DereverberationEngineeringAcoustic ModelingNoise Reduction +14