Search Results - "Luo, Ne"

A Further Study of Unsupervised Pretraining for Transformer Based Speech Recognition by Jiang, Dongwei, Li, Wubo, Zhang, Ruixiong, Cao, Miao, Luo, Ne, Han, Yang, Zou, Wei, Han, Kun, Li, Xiangang

“…The construction of an effective good speech recognition system typically requires large amounts of transcribed data, which is expensive to collect. To…”
Get full text

Didispeech: A Large Scale Mandarin Speech Corpus by Guo, Tingwei, Wen, Cheng, Jiang, Dongwei, Luo, Ne, Zhang, Ruixiong, Zhao, Shuaijiang, Li, Wubo, Gong, Cheng, Zou, Wei, Han, Kun, Li, Xiangang

“…This paper introduces a new open-sourced Mandarin speech corpus, called DiDiSpeech. It consists of about 800 hours of speech data at 48kHz sampling rate from…”
Get full text

Mutual-optimization Towards Generative Adversarial Networks For Robust Speech Recognition by Ding, Ke, Luo, Ne, Xu, Yanyan, Ke, Dengfeng, Su, Kaile

“…In the context of Automatic Speech Recognition (ASR), improving the noise robustness remains an intractable task. Speech enhancement, combined with Generative…”
Get full text

A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition by Jiang, Dongwei, Li, Wubo, Zhang, Ruixiong, Cao, Miao, Luo, Ne, Han, Yang, Zou, Wei, Li, Xiangang

“…Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many…”
Get full text

Improving Transformer-based Speech Recognition Using Unsupervised Pre-training by Jiang, Dongwei, Lei, Xiaoning, Li, Wubo, Luo, Ne, Hu, Yuxuan, Zou, Wei, Li, Xiangang

“…Speech recognition technologies are gaining enormous popularity in various industrial applications. However, building a good speech recognition system usually…”
Get full text

DiDiSpeech: A Large Scale Mandarin Speech Corpus by Guo, Tingwei, Wen, Cheng, Jiang, Dongwei, Luo, Ne, Zhang, Ruixiong, Zhao, Shuaijiang, Li, Wubo, Gong, Cheng, Zou, Wei, Han, Kun, Li, Xiangang

“…This paper introduces a new open-sourced Mandarin speech corpus, called DiDiSpeech. It consists of about 800 hours of speech data at 48kHz sampling rate from…”
Get full text

Towards End-to-End Code-Switching Speech Recognition by Luo, Ne, Jiang, Dongwei, Zhao, Shuaijiang, Gong, Caixia, Zou, Wei, Li, Xiangang

“…Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue…”
Get full text