Replacing hand-engineered pipelines with end-to-end deep learning systems has
enabled strong results in applications like speech and object recognition.
However, the causality and latency constraints of production systems put
end-to-end speech models back into the underfitting regime and expose biases in
the model that we show cannot be overcome by "scaling up", i.e., training
bigger models on more data. In this work we systematically identify and address
sources of bias, reducing error rates by up to 20% while remaining practical
for deployment. We achieve this by utilizing improved neural architectures for
streaming inference, solving optimization issues, and employing strategies that
increase audio and label modelling versatility.

本研究通过使用改进的神经网络结构、解决优化问题和应用增强的语音和标签建模策略来识别和解决深度学习中的偏差问题，成功应对了现有语音识别系统中固有的不足之处并实现了误差率的降低，为设备实际部署提供了可行性。

生产语音模型中减少偏差

Reducing Bias in Production Speech Models

We propose an end-to-end deep learning architecture for word-level visual
speech recognition. The system is a combination of spatiotemporal
convolutional, residual and bidirectional Long Short-Term Memory networks. We
train and evaluate it on the Lipreading In-The-Wild benchmark, a challenging
database of 500-size target-words consisting of 1.28sec video excerpts from BBC
TV broadcasts. The proposed network attains word accuracy equal to 83.0,
yielding 6.8 absolute improvement over the current state-of-the-art, without
using information about word boundaries during training or testing.

本文提出了一种端到端的深度学习架构用于字级视觉语音识别，该方法结合了时空卷积、残量和双向长短时记忆网络，该网络在 Lipreading In-The-Wild 基准上获得了 83.0 的字级准确率，相较于当前的最先进方法有 6.8 的绝对提升，且在训练和测试过程中均未使用有关单词边界的信息。

将 Residual Networks 与 LSTMs 组合用于唇语识别

Combining Residual Networks with LSTMs for Lipreading

We present a state-of-the-art speech recognition system developed using
end-to-end deep learning. Our architecture is significantly simpler than
traditional speech systems, which rely on laboriously engineered processing
pipelines; these traditional systems also tend to perform poorly when used in
noisy environments. In contrast, our system does not need hand-designed
components to model background noise, reverberation, or speaker variation, but
instead directly learns a function that is robust to such effects. We do not
need a phoneme dictionary, nor even the concept of a "phoneme." Key to our
approach is a well-optimized RNN training system that uses multiple GPUs, as
well as a set of novel data synthesis techniques that allow us to efficiently
obtain a large amount of varied data for training. Our system, called Deep
Speech, outperforms previously published results on the widely studied
Switchboard Hub5'00, achieving 16.0% error on the full test set. Deep Speech
also handles challenging noisy environments better than widely used,
state-of-the-art commercial speech systems.

使用端到端深度学习开发的演讲识别系统：不需要手工设计组件来模拟背景噪声、混响或者发言人差异，取而代之的是直接学习一个对这些影响具有鲁棒性的函数的方法，其关键是优化的 RNN 训练系统以及一组新的数据综合技术，该系统在 Switchboard Hub5'00 测试集上取得了 16.0% 的错误率，优于以前的成果，并且与广泛使用的最先进的商业演讲系统相比，Deep Speech 处理具有挑战性的嘈杂环境的能力更加出色。