Switching Independent Vector Analysis and its Extension to Blind and Spatially Guided Convolutional Beamforming Algorithms von Nakatani, Tomohiro, Ikeshita, Rintaro, Kinoshita, Keisuke, Sawada, Hiroshi, Kamo, Naoyuki, Araki, Shoko

Volltext

Blind Signal Dereverberation Based on Mixture of Weighted Prediction Error Models von Ikeshita, Rintaro, Kamo, Naoyuki, Nakatani, Tomohiro

Volltext

Online Speech Dereverberation Using Mixture of Multichannel Linear Prediction Models von Ikeshita, Rintaro, Kinoshita, Keisuke, Kamo, Naoyuki, Nakatani, Tomohiro

Volltext

Target Speech Extraction with Conditional Diffusion Model von Kamo, Naoyuki, Delcroix, Marc, Nakatani, Tomohiro

Volltext bestellen

Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition von Ogawa, Atsunori, Moriya, Takafumi, Kamo, Naoyuki, Tawara, Naohiro, Delcroix, Marc

Volltext bestellen

Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over von Ogawa, Atsunori, Kamo, Naoyuki, Matsuura, Kohei, Ashihara, Takanori, Moriya, Takafumi, Kano, Takatomo, Tawara, Naohiro, Delcroix, Marc

Volltext bestellen

REVERBERATION REMOVAL DEVICE, PARAMETER ESTIMATION DEVICE, REVERBERATION REMOVAL METHOD, PARAMETER ESTIMATION METHOD, AND PROGRAM von NAKATANI, Tomohiro, KAMO, Naoyuki, IKESHITA, Rintaro

Volltext bestellen

Target Speech Extraction with Conditional Diffusion Model von Kamo, Naoyuki, Delcroix, Marc, Nakatani, Tomohiro

Volltext

FILTER GENERATION APPARATUS, FILTER GENERATION METHOD, AND PROGRAM von NAKATANI, Tomohiro, KAMO, Naoyuki, KINOSHITA, Keisuke, IKESHITA, Rintaro

Volltext bestellen

Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition von Sato, Hiroshi, Ochiai, Tsubasa, Delcroix, Marc, Kinoshita, Keisuke, Kamo, Naoyuki, Moriya, Takafumi

Volltext

NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge von Kamo, Naoyuki, Tawara, Naohiro, Ando, Atsushi, Kano, Takatomo, Sato, Hiroshi, Ikeshita, Rintaro, Moriya, Takafumi, Horiguchi, Shota, Matsuura, Kohei, Ogawa, Atsunori, Plaquet, Alexis, Ashihara, Takanori, Ochiai, Tsubasa, Mimura, Masato, Delcroix, Marc, Nakatani, Tomohiro, Asami, Taichi, Araki, Shoko

Volltext bestellen

Switching Independent Vector Analysis and Its Extension to Blind and Spatially Guided Convolutional Beamforming Algorithms von Nakatani, Tomohiro, Ikeshita, Rintaro, Kinoshita, Keisuke, Sawada, Hiroshi, Kamo, Naoyuki, Araki, Shoko

Volltext bestellen

Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition von Ogawa, Atsunori, Moriya, Takafumi, Kamo, Naoyuki, Tawara, Naohiro, Delcroix, Marc

Volltext

Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition von Sato, Hiroshi, Ochiai, Tsubasa, Delcroix, Marc, Kinoshita, Keisuke, Moriya, Takafumi, Kamo, Naoyuki

Volltext

ACOUSTIC SIGNAL ENHANCEMENT DEVICE, ACOUSTIC SIGNAL ENHANCEMENT METHOD, AND PROGRAM von SAWADA, Hiroshi, NAKATANI, Tomohiro, KAMO, Naoyuki, KINOSHITA, Keisuke, ARAKI, Shoko, IKESHITA, Rintaro

Volltext bestellen

Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over von Ogawa, Atsunori, Kamo, Naoyuki, Matsuura, Kohei, Ashihara, Takanori, Moriya, Takafumi, Kano, Takatomo, Tawara, Naohiro, Delcroix, Marc

Volltext

Convolutive Transfer Function Invariant SDR training criteria for Multi-Channel Reverberant Speech Separation von Boeddeker, Christoph, Zhang, Wangyou, Nakatani, Tomohiro, Kinoshita, Keisuke, Ochiai, Tsubasa, Delcroix, Marc, Kamo, Naoyuki, Qian, Yanmin, Haeb-Umbach, Reinhold

Volltext bestellen

End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend von Zhang, Wangyou, Boeddeker, Christoph, Watanabe, Shinji, Nakatani, Tomohiro, Delcroix, Marc, Kinoshita, Keisuke, Ochiai, Tsubasa, Kamo, Naoyuki, Haeb-Umbach, Reinhold, Qian, Yanmin

Volltext

ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration von Li, Chenda, Shi, Jing, Zhang, Wangyou, Aswin Shanmugam Subramanian, Chang, Xuankai, Kamo, Naoyuki, Hira, Moto, Hayashi, Tomoki, Boeddeker, Christoph, Chen, Zhuo, Watanabe, Shinji

Volltext

The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans von Watanabe, Shinji, Boyer, Florian, Chang, Xuankai, Guo, Pengcheng, Hayashi, Tomoki, Higuchi, Yosuke, Hori, Takaaki, Huang, Wen-Chin, Inaguma, Hirofumi, Kamo, Naoyuki, Karita, Shigeki, Li, Chenda, Shi, Jing, Subramanian, Aswin Shanmugam, Zhang, Wangyou

Volltext bestellen