Mouth Region Localization Method Based on Gaussian Mixture Model von Kumatani, Kenichi, Stiefelhagen, Rainer

Volltext

Beamforming With a Maximum Negentropy Criterion von Kumatani, K., McDonough, J., Rauch, B., Klakow, D., Garner, P.N., Weifeng Li

Volltext

Adaptive Beamforming With a Minimum Mutual Information Criterion von Kumatani, K., Gehrig, T., Mayer, U., Stoimenov, E., McDonough, J., Wolfel, M.

Volltext

Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal von Park, Tae Jin, Kumatani, Kenichi, Dimitriadis, Dimitrios

Volltext bestellen

Multilingual Speech Recognition using Knowledge Transfer across Learning Processes von Lahiri, Rimita, Kumatani, Kenichi, Sun, Eric, Qian, Yao

Volltext bestellen

Block-wise incremental adaptation algorithm for maximum kurtosis beamforming von Kumatani, K., McDonough, J., Raj, B.

Volltext

On the combination of voice prompt suppression with maximum kurtosis beamforming von McDonough, J., Raj, B., Kumatani, K.

Volltext

Maximum negentropy beamforming using complex generalized Gaussian distribution model von Kumatani, K, Rauch, B, McDonough, J, Klakow, D

Volltext

Deploying self-supervised learning in the wild for hybrid automatic speech recognition von Karimi, Mostafa, Liu, Changliang, Kumatani, Kenichi, Qian, Yao, Wu, Tianyu, Wu, Jian

Volltext bestellen

Sequence-level self-learning with multiple hypotheses von Kumatani, Kenichi, Dimitriadis, Dimitrios, Gaur, Yashesh, Gmyr, Robert, Eskimez, Sefik Emre, Li, Jinyu, Zeng, Michael

Volltext

Robust Multi-channel Speech Recognition using Frequency Aligned Network von Park, Taejin, Kumatani, Kenichi, Wu, Minhua, Sundaram, Shiva

Volltext bestellen

Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning von Wager, Sanna, Khare, Aparna, Wu, Minhua, Kumatani, Kenichi, Sundaram, Shiva

Volltext

UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset von Wang, Chengyi, Wu, Yu, Liu, Shujie, Li, Jinyu, Qian, Yao, Kumatani, Kenichi, Wei, Furu

Volltext bestellen

State Synchronous Modeling on Phone Boundary for Audio Visual Speech Recognition and Application to Muti-View Face Images von Kumatani, K., Stiefelhagen, R.

Volltext

Dynamic Gradient Aggregation for Federated Domain Adaptation von Dimitriadis, Dimitrios, Kumatani, Kenichi, Gmyr, Robert, Gaur, Yashesh, Eskimez, Sefik Emre

Volltext bestellen

An information filter for voice prompt suppression von McDonough, J., Wei Chu, Kumatani, K., Raj, B., Lehman, J. F.

Volltext

Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal von Tae Jin Park, Kumatani, Kenichi, Dimitriadis, Dimitrios

Volltext

Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition von Kumatani, Kenichi, Gmyr, Robert, Salinas, Felipe Cruz, Liu, Linquan, Zuo, Wei, Patel, Devang, Sun, Eric, Shi, Yu

Volltext bestellen

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data von Wang, Chengyi, Wu, Yu, Qian, Yao, Kumatani, Kenichi, Liu, Shujie, Wei, Furu, Zeng, Michael, Huang, Xuedong

Volltext bestellen

Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition von Wu, Minhua, Kumatani, Kenichi, Sundaram, Shiva, Strom, Nikko, Hoffmeister, Bjorn

Volltext