The last year has seen astonishing progress in text-prompted image gener...
End-to-end models with large capacity have significantly improved
multil...
We propose a new two-pass E2E speech recognition model that improves ASR...
We introduce the Universal Speech Model (USM), a single large model that...
While large language models (LLM) have made impressive progress in natur...
Multilingual end-to-end automatic speech recognition models are attracti...
Text-only and semi-supervised training based on audio-only data has gain...
User historical behaviors are proved useful for Click Through Rate (CTR)...
We propose a streaming non-autoregressive (non-AR) decoding algorithm to...
Click-through rate(CTR) prediction is a core task in cost-per-click(CPC)...
Graph Neural Networks (GNNs) have become increasingly popular and achiev...
This paper proposes an artificial neural network to determine orientatio...
Click-through rate (CTR) prediction plays an important role in online
ad...
We study the problem of word-level confidence estimation in subword-base...
Interactive speech recognition systems must generate words quickly while...
The local feature detector and descriptor are essential in many computer...
In this paper, we propose Textual Echo Cancellation (TEC) - a framework ...
Nowadays air pollution becomes one of the biggest world issues in both
d...
Thus far, end-to-end (E2E) models have not been shown to outperform
stat...
End-to-end (E2E) models have made rapid progress in automatic speech
rec...
Contextual automatic speech recognition, i.e., biasing recognition towar...
Multilingual training has been shown to improve acoustic modeling perfor...
We reassess a recent study (Hassan et al., 2018) that claimed that machi...