🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

This my my first tweet. I am so happy that my three papers are accepted to ICASSP2021. This is also my first pub in icassp. Thank all the reviewers for their dedicated work.

This is my espnet tutorial video youtu.be/2mRz3wH1vd0

I'm stoked to see all the progress in large ASR datasets. Several 10k hour+ datasets have recently (or will soon be) released. GigaSpeech (English): github.com/SpeechColab/Gi… WeNetSpeech (Mandarin): wenet-e2e.github.io/WenetSpeech/ People's Speech (multi-lingual): mlcommons.org/en/peoples-spe…

The research topic during my Ph.D. at UCLA is children's speech recognition. As this journey ended last week, I, over the weekend, summarized some resources about child speech (github.com/Diamondfan/Chi…). I hope the repo can help students who join the field.

We released Phi-4-mini (3.8B base in LLM), a new SLM excelling in language, vision, and audio through a mixture-of-LoRA, uniting three modalities in one model. I am so impressed with its new audio capability. I hope you can play with it and share with us your feedback. We also

Phi-4-Mini Technical Report Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs