Search Results for author:
Found 8 papers, 0 papers with code
Scaling Instructable Agents Across Many Simulated Worlds
Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI.
Kernel Support Vector Machine Classifiers with the $\ell_0$-Norm Hinge Loss
In consideration of the nonconvexity and nonsmoothness of $\ell_0$-norm hinge loss, we first characterize the limiting subdifferential of the $\ell_0$-norm hinge loss and then derive the equivalent relationship among the proximal stationary point, the Karush-Kuhn-Tucker point, and the local optimal solution of $\ell_0$-KSVM.
Multi-turn RNN-T for streaming recognition of multi-party speech
Second, we propose a novel multi-turn RNN-T (MT-RNN-T) model with an overlap-based target arrangement strategy that generalizes to an arbitrary number of speakers without changes in the model architecture.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
SynthASR: Unlocking Synthetic Data for Speech Recognition
Our observations show that SynthASR holds great promise in training the state-of-the-art large-scale E2E ASR models for new applications while reducing the costs and dependency on production data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio
Bootstrapping speech recognition on limited data resources has been an area of active research for long.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Streaming Multi-speaker ASR with RNN-T
Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers.
Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systems
Different regularisation techniques are explored and the best performance is achieved by fine-tuning the RNN-T on both original training data and extra synthetic data with elastic weight consolidation (EWC) applied on the encoder.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Equivalent Lipschitz surrogates for zero-norm and rank optimization problems
Specifically, we reformulate these combinatorial problems as equivalent MPECs by the variational characterization of the zero-norm and rank function, show that their penalized problems, yielded by moving the equilibrium constraint into the objective, are the global exact penalization, and obtain the equivalent Lipschitz surrogates by eliminating the dual variable in the global exact penalty.
