Zhiyong Yan

机构：Xiaomi (China)

发表论文 25 篇 · 总被引 416 次 · h-index 9

代表论文

• GigaSpeech: An Evolving, Multi-Domain ASR Corpus with 10,000 Hours of Transcribed Audio (2021 · 被引 210)
• speechocean762: An Open-Source Non-Native English Speech Corpus for Pronunciation Assessment (2021 · 被引 62)
• CED: Consistent Ensemble Distillation for Audio Tagging (2024 · 被引 26)
• Av-Sepformer: Cross-Attention Sepformer for Audio-Visual Target Speaker Extraction (2023 · 被引 22)
• GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio (2021 · arXiv (Cornell University) · 被引 20)
• Scaling up masked audio encoder learning for general audio classification (2024 · 被引 19)