Qingming Tang


About Me

I'm a senior applied scientist in Alexa Perceptual Technologies (APT) of Alexa AI.

Selected Recent Publications

For a complete list of my publications, please see my Google Scholar or Semantics Scholar.

  1. Calibration-Aware Margin Loss: Pushing the Accuracy-Calibration Consistency Pareto Frontier for Deep Metric Learning, Preprint under submission
  2. On-device constrained self-supervised speech representation learning for keyword spotting via knowledge distillation, Interspeech 2023
  3. FedRPO: Federated relaxed Pareto optimization for acoustic event classification, ICASSP 2023
  4. Weight-sharing supernet for searching specialized acoustic event classification networks across device constraints, ICASSP 2023
  5. Wikitag: Wikipedia-based Knowledge Embedding Towards Improved Acoustic Event Classification, ICASSP 2022
  6. Improved Representation Learning for Acoustic Event Classification Using Tree-structured Ontology, ICASSP 2022
  7. Federated Self-supervised Learning for Acoustic Event Classification, ICASSP 2022
  8. Multi-task self-supervised pre-training for music classification, ICASSP 2021
  9. Unsupervised pre-training of bidirectional speech encoders via masked reconstruction, ICASSP 2020
  10. Controllable Paraphrase Generation with a Syntactic Exemplar, ACL 2019
  11. Hierarchical Residual-pyramidal Model for Large Context Based Media Presence Detection, ICASSP 2019
  12. A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations, NAACL 2019
  13. Variational Sequential Labelers for Semi-Supervised Learning, EMNLP 2018
  14. Acoustic Feature learning using cross-domain articulatory measurements, ICASSP 2018
  15. Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis, Interspeech 2017 [Paper] [Code] [Data]
  16. Learning Scale-Free Networks by Dynamic Node Specific Degree Prior, ICML 2015 [Pdf, Supplementary, Code]
  17. Exact Hybrid Covariance Thresholding for Joint Graphical Lasso, ECML/PKDD 2015 [Pdf, Proof, Figure, Code]

Professional Services

I'm serving as reviewers for most of the top-tier ML/Speech/NLP/Vision conferences:
ICLR (from 2018), NeulPS (from 2019), ASRU (from 2019), EMNLP (from 2019), Interspeech (from 2020), ICASSP (from 2020), ACL (from 2020), NAACL (from 2020), SLT (from 2021), ECCV (2021), CVPR (from 2022), ICML (from 2022) and DCASE (from 2021).

I'm serving as reviewers for the below journals:
Transactions on Machine Learning Research, Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Signal Processing, Knowledge-Based Systems, and The Journal of Artificial Intelligence Research and Neural Computation

I used to review below computational biology conferences and journals:
Annual International Conference on Research in Computational Molecular Biology (RECOMB), Pacific Symposium on Biocomputing (PSB), Interdisciplinary Sciences and IEEE/ACM Transactions on Computational Biology and Bioinformatics.

Recent Patents

Media Presence Detection
Qingming Tang , Ming Sun, Chieh-chi Kao, Chao Wang and Viktor Rozgic
US Patent 11,069,352, 2021

Acoustic event detection
Qingming Tang , Chieh-chi Kao, Qin Zhang, Ming Sun, Chao Wang and more
US Patent App. 17/547,644, 2023

Other nine confidential patents have been filed