CHiME-6 Challenge: Tackling Multispeaker Speech Recognition for Unsegmented Recordings

Shinji Watanabe, Michael Mandel, Jon Barker, +18

EngineeringMachine LearningChime Speech SeparationChime-6 ChallengeSpeech Recognition +15

End-to-End Neural Speaker Diarization with Permutation-Free Objectives

Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, +2

Natural Language ProcessingSpeech PerceptionEngineeringMachine LearningPermutation-free Objectives +13

End-to-End Neural Speaker Diarization with Self-Attention

Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, +3

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

Natural Language ProcessingEngineeringHealth SciencesDeep LearningBlstm Blocks +11

End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors

Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, +2

EngineeringHealth SciencesMulti-speaker Speech RecognitionAttractor CalculationSpeaker Diarization +11

CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings

Shinji Watanabe, Michael Mandel, Jon Barker, +18

arXiv (Cornell University)

EngineeringMachine LearningChime Speech SeparationChime-6 ChallengeSpeech Recognition +15

Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR

Naoyuki Kanda, Christoph Boeddeker, Jens Heitkaemper, +4

Source SeparationEngineeringMachine LearningCommunicationSpeech Recognition +20

Speaker Diarization with Region Proposal Network

Zili Huang, Shinji Watanabe, Yusuke Fujita, +4

Diarization DatasetsEngineeringMachine LearningDeep LearningHealth Sciences +12

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

Encoder-Decoder Based Attractors for End-to-End Neural Diarization

Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, +2

IEEE/ACM Transactions on Audio Speech and Language Processing

EngineeringMachine LearningAutoencodersUnknown NumberRecurrent Neural Network +16

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