Search Results for author:
Found 20 papers, 2 papers with code
Towards Fast Inference: Exploring and Improving Blockwise Parallel Drafts
Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation.
Self-supervised Adaptive Weighting for Cooperative Perception in V2V Communications
The performance of cooperative perception is investigated in different system settings.
Cooperative Perception with Learning-Based V2V communications
A new late fusion scheme is proposed to leverage the robustness of intermediate features.
Large-scale Language Model Rescoring on Long-form Data
In this work, we study the impact of Large-scale Language Models (LLM) on Automated Speech Recognition (ASR) of YouTube videos, which we use as a source for long-form ASR.
LAST: Scalable Lattice-Based Speech Modelling in JAX
We introduce LAST, a LAttice-based Speech Transducer library in JAX.
Alignment Entropy Regularization
Existing training criteria in automatic speech recognition(ASR) permit the model to freely explore more than one time alignments between the feature and label sequences.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Global Normalization for Streaming Speech Recognition in a Modular Framework
We introduce the Globally Normalized Autoregressive Transducer (GNAT) for addressing the label bias problem in streaming speech recognition.
Learning discrete distributions: user vs item-level privacy
If each user has $m$ samples, we show that straightforward applications of Laplace or Gaussian mechanisms require the number of users to be $\mathcal{O}(k/(m\alpha^2) + k/\epsilon\alpha)$ to achieve an $\ell_1$ distance of $\alpha$ between the true and estimated distributions, with the privacy-induced penalty $k/\epsilon\alpha$ independent of the number of samples per user $m$.
Hybrid Autoregressive Transducer (hat)
This paper proposes and evaluates the hybrid autoregressive transducer (HAT) model, a time-synchronous encoderdecoder model that preserves the modularity of conventional automatic speech recognition systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Federated Learning of N-gram Language Models
The n-gram language models trained with federated learning are compared to n-grams trained with traditional server-based algorithms using A/B tests on tens of millions of users of virtual keyboard.
On the Compression of Lexicon Transducers
Indeed, a delicate balance between comprehensiveness, speed, and memory must be struck to conform to device requirements while providing a good user experience. In this paper, we describe a compression scheme for lexicons when represented as finite-state transducers.
Latin script keyboards for South Asian languages with finite-state normalization
The use of the Latin script for text entry of South Asian languages is common, even though there is no standard orthography for these languages in the script.
Distilling weighted finite automata from arbitrary probabilistic models
Weighted finite automata (WFA) are often used to represent probabilistic models, such as n-gram language models, since they are efficient for recognition tasks in time and space.
Approximating probabilistic models as weighted finite automata
Weighted finite automata (WFA) are often used to represent probabilistic models, such as $n$-gram language models, since they are efficient for recognition tasks in time and space.
Mobile Keyboard Input Decoding with Finite-State Transducers
We describe the general framework of what we call for short the keyboard "FST decoder" as well as the implementation details that are new compared to a speech FST decoder.
