Skip to content
Avatar

Achievements

Achievements

Block or Report

Block or report tan-xu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tan-xu/README.md

Research Work

Machine Learning and NLP

  • Research on Neural Machine Translation, Language Generation/Understanding, Seq2Seq Learning, etc.
  • Pubish 40+ papers on top conferences, multiple technologies transferred into Bing Search and Bing Translation.
  • Achieving human parity on Chinese-English news translation.
  • Winning champions in WMT Machine Translation Competition in 2019.

Pre-training for Language Understanding and Generation

  • Publish 8 papers on top conferences, pre-training model MASS deployed in Bing Ads for Ads content generation, and deployed in Bing Translation for low-resource languages.
  • MASS is one of the most impactful models in pre-training, with 400+ citations, top cited papers in ICML 2019. MPNet (NeurIPS 2020) adopted by Huggingface.

Speech Synthesis and Recognition

  • Publish 20+ papers on top conferences, multiple technologies (FastSpeech 1/2, LRSpeech, AdaSpeech 1/2/3, FastCorrect 1/2) deployed in Microsoft Azure TTS and ASR services.
  • FastSpeech 1/2 (NeurIPS 2019/ICLR 2021) are one of the most important techniques in TTS community, with totally 400+ citations, widely adopted in academia and industry. Integrated in some popular Github repos, such as ESPNet, NVIDIA Nemo, TensorFlowTTS, Baidu PaddlePaddle Parakeet. Demo by NVIDIA GTC 2020.
  • Survey, talks, and tutorials on TTS influence wide researchers and engineers in TTS community.

Music Understanding and Generation

  • Publish 10+ papers on top conferences, multiple techniques (SongMASS, StrcutMelody, DeepRapper, XiaoiceSing, and HiFiSinger) integrated in Microsoft Azure and Microsoft Xiaoice for AI music composition.
  • Systematic research on songwriting, accompaniment and arrangement, singing voice synthesis, music understanding, etc. Keynote speaker on AI music composition at GAITC 2021. Tutorial on AI music composition in ACM MM 2021.

Pinned

  1. Muzic: Music Understanding and Generation with Artificial Intelligence

    Python 1.2k 45

  2. MASS: Masked Sequence to Sequence Pre-training for Language Generation

    Python 1k 191

  3. MPNet: Masked and Permuted Pre-training for Language Understanding https://arxiv.org/pdf/2004.09297.pdf

    Python 176 21

  4. A Survey on Neural Speech Synthesis https://arxiv.org/pdf/2106.15561.pdf

    170 17

137 contributions in the last year

Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Mon Wed Fri

Contribution activity

Seeing something unexpected? Take a look at the GitHub profile guide.