Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition von Zhu, Han, Gao, Dongji, Cheng, Gaofeng, Povey, Daniel, Zhang, Pengyuan, Yan, Yonghong

Volltext

PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with Phoneme Distribution Predictor von Wu, Yuning, Shi, Jiatong, Qian, Tao, Gao, Dongji, Jin, Qin

Volltext bestellen

Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition von Gao, Dongji, Xu, Hainan, Raj, Desh, Perera, Leibny Paola Garcia, Povey, Daniel, Khudanpur, Sanjeev

Volltext bestellen

Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition von Zhu, Han, Gao, Dongji, Cheng, Gaofeng, Povey, Daniel, Zhang, Pengyuan, Yan, Yonghong

Volltext bestellen

HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation von Xiao, Cihan, Xinyuan, Henry Li, Yang, Jinyi, Gao, Dongji, Wiesner, Matthew, Duh, Kevin, Khudanpur, Sanjeev

Volltext bestellen

Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts von Gao, Dongji, Wiesner, Matthew, Xu, Hainan, Garcia, Leibny Paola, Povey, Daniel, Khudanpur, Sanjeev

Volltext bestellen

EURO: ESPnet Unsupervised ASR Open-source Toolkit von Gao, Dongji, Shi, Jiatong, Chuang, Shun-Po, Garcia, Leibny Paola, Lee, Hung-yi, Watanabe, Shinji, Khudanpur, Sanjeev

Volltext bestellen

Bridging Speech and Textual Pre-trained Models with Unsupervised ASR von Shi, Jiatong, Hsu, Chan-Jan, Chung, Holam, Gao, Dongji, Garcia, Paola, Watanabe, Shinji, Lee, Ann, Lee, Hung-yi

Volltext bestellen

Decoupling recognition and transcription in Mandarin ASR von Yuan, Jiahong, Cai, Xingyu, Gao, Dongji, Zheng, Renjie, Huang, Liang, Church, Kenneth

Volltext bestellen

PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with Phoneme Distribution Predictor von Wu, Yuning, Shi, Jiatong, Qian, Tao, Gao, Dongji, Qin, Jin

Volltext

Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition von Gao, Dongji, Xu, Hainan, Raj, Desh, Leibny Paola Garcia Perera, Povey, Daniel, Khudanpur, Sanjeev

Volltext

Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition von Zhu, Han, Gao, Dongji, Cheng, Gaofeng, Povey, Daniel, Zhang, Pengyuan, Yan, Yonghong

Volltext

HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation von Xiao, Cihan, Henry Li Xinyuan, Yang, Jinyi, Gao, Dongji, Wiesner, Matthew, Duh, Kevin, Khudanpur, Sanjeev

Volltext

Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts von Gao, Dongji, Wiesner, Matthew, Xu, Hainan, Leibny Paola Garcia, Povey, Daniel, Khudanpur, Sanjeev

Volltext

EURO: ESPnet Unsupervised ASR Open-source Toolkit von Gao, Dongji, Shi, Jiatong, Shun-Po Chuang, Leibny Paola Garcia, Hung-yi, Lee, Watanabe, Shinji, Khudanpur, Sanjeev

Volltext

Bridging Speech and Textual Pre-trained Models with Unsupervised ASR von Shi, Jiatong, Chan-Jan, Hsu, Chung, Holam, Gao, Dongji, Garcia, Paola, Watanabe, Shinji, Lee, Ann, Hung-yi, Lee

Volltext

Decoupling recognition and transcription in Mandarin ASR von Yuan, Jiahong, Cai, Xingyu, Gao, Dongji, Zheng, Renjie, Huang, Liang, Church, Kenneth

Volltext

Calcium-added sweets and its production technology von DONGJI GAO

Volltext bestellen

Domestic drinking-water purifier von DONGJI GAO

Volltext bestellen

MULTIFUNCITONAL PRAM von GAO DONGJI

Volltext bestellen