Zhifeng Chen
Zhifeng Chen has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
Anmol Gulati
Google, Inc., USA
1 shared publicationAren Jansen
Google, Inc., USA
1 shared publication- Bhuvana Ramabhadran
Google, New York, NY, USA
1 shared publication - Bo Li
State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication - Chris Sweeney
Waymo LLC, Mountain View, CA, USA
1 shared publication Chung-Cheng Chiu
Google, Inc., USA
1 shared publication
Latest Publications
- Top Cited Papers
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 16 (6) , 1519-1532
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio. We find that the combination of pre-training, self-training and scaling up model size greatly increases data efficiency, even for extremely large tasks with tens of thousands of hours of labeled data. In particular, on an ASR task with 34 k hours of labeled data, by fine-tuning an 8 billion parameter pre-trained Conformer model we can match state-of-the-art (SoTA) performance with only 3% of the training data and significantly improve SoTA with the full training set. We also report on the universal benefits gained from using big pre-trained and self-trained models for a large set of downstream tasks that cover a wide range of speech domains and span multiple orders of magnitudes of dataset sizes, including obtaining SoTA performance on many public benchmarks. In addition, we utilize the learned representation of pre-trained networks to achieve SoTA results on non-ASR tasks.
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 16 (6) , 1519-1532
Top Cited PapersBigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio. We find that the combination of pre-training, self-training and scaling up model size greatly increases data efficiency, even for extremely large tasks with tens of thousands of hours of labeled data. In particular, on an ASR task with 34 k hours of labeled data, by fine-tuning an 8 billion parameter pre-trained Conformer model we can match state-of-the-art (SoTA) performance with only 3% of the training data and significantly improve SoTA with the full training set. We also report on the universal benefits gained from using big pre-trained and self-trained models for a large set of downstream tasks that cover a wide range of speech domains and span multiple orders of magnitudes of dataset sizes, including obtaining SoTA performance on many public benchmarks. In addition, we utilize the learned representation of pre-trained networks to achieve SoTA results on non-ASR tasks.
- Open Access
- 31 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 1589-1596
Scalable Scene Flow From Point Clouds in the Real World
Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ 3D point cloud data from consecutive LiDAR scans, although such approaches have been limited by the small size of real-world, annotated LiDAR data. In this work, we introduce a new large-scale dataset for scene flow estimation derived from corresponding tracked 3D objects, which is $\sim 1,000\times$ larger than previous real-world datasets in terms of the number of annotated frames. We demonstrate how previous works were bounded by the amount of real LiDAR data available, suggesting that larger datasets are required to achieve state-of-the-art predictive performance. Furthermore, we show how previous heuristics such as down-sampling heavily degrade performance, motivating a new class of models that are tractable on the full point cloud. To address this issue, we introduce the FastFlow3D architecture which provides real time inference on the full point cloud. Additionally, we design human-interpretable metrics that better capture real world aspects by accounting for ego-motion and providing breakdowns per object type. We hope that this dataset may provide new opportunities for developing real world scene flow systems.
- 31 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 1589-1596
Open AccessScalable Scene Flow From Point Clouds in the Real World
Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ 3D point cloud data from consecutive LiDAR scans, although such approaches have been limited by the small size of real-world, annotated LiDAR data. In this work, we introduce a new large-scale dataset for scene flow estimation derived from corresponding tracked 3D objects, which is $\sim 1,000\times$ larger than previous real-world datasets in terms of the number of annotated frames. We demonstrate how previous works were bounded by the amount of real LiDAR data available, suggesting that larger datasets are required to achieve state-of-the-art predictive performance. Furthermore, we show how previous heuristics such as down-sampling heavily degrade performance, motivating a new class of models that are tractable on the full point cloud. To address this issue, we introduce the FastFlow3D architecture which provides real time inference on the full point cloud. Additionally, we design human-interpretable metrics that better capture real world aspects by accounting for ego-motion and providing breakdowns per object type. We hope that this dataset may provide new opportunities for developing real world scene flow systems.