This paper addresses the problem of improving speech recognition accuracy
with lattice rescoring in low-resource languages where the baseline language
model is insufficient for generating inclusive lattices. We minimally augment
the baseline language model with word unigram counts that are present in a
larger text corpus of the target language but absent in the baseline. The
lattices generated after decoding with such an augmented baseline language
model are more comprehensive. We obtain 21.8% (Telugu) and 41.8% (Kannada)
relative word error reduction with our proposed method. This reduction in word
error rate is comparable to 21.5% (Telugu) and 45.9% (Kannada) relative word
error reduction obtained by decoding with full Wikipedia text augmented
language mode while our approach consumes only 1/8th the memory. We demonstrate
that our method is comparable with various text selection-based language model
augmentation and also consistent for data sets of different sizes. Our approach
is applicable for training speech recognition systems under low resource
conditions where speech data and compute resources are insufficient, while
there is a large text corpus that is available in the target language. Our
research involves addressing the issue of out-of-vocabulary words of the
baseline in general and does not focus on resolving the absence of named
entities. Our proposed method is simple and yet computationally less expensive.

通过在低资源语言中使用栅格重采样来提高语音识别准确性的问题，本文通过最小限度地利用目标语言中大型文本语料库中存在但基线模型中缺失的单词一元计数来改进基线语言模型，从而生成更全面的栅格。我们的方法在泰卢固语和卡纳达语分别获得了 21.8% 和 41.8% 的相对词错误率降低，这个降低与使用全维基百科文本增强的语言模型解码所获得的 21.5%（泰卢固语）和 45.9%（卡纳达语）相对词错误率降低相当，而我们的方法仅消耗 1/8 的内存。我们证明了我们的方法与基于文本选择的语言模型增强方法相当，并且对于不同规模的数据集一致。我们的方法适用于在语音数据和计算资源不足的低资源条件下训练语音识别系统，并且目标语言中有大型文本语料库的情况。我们的研究涉及解决基线的未登录词问题，而不专注于解决命名实体的缺失问题。我们的方法简单且计算成本较低。

低资源语音识别中使用最小增强语言模型进行初始解码以提高格栅再评分

Initial Decoding with Minimally Augmented Language Model for Improved  Lattice Rescoring in Low Resource ASR

We investigate the effectiveness of using a large ensemble of advanced neural
language models (NLMs) for lattice rescoring on automatic speech recognition
(ASR) hypotheses. Previous studies have reported the effectiveness of combining
a small number of NLMs. In contrast, in this study, we combine up to eight
NLMs, i.e., forward/backward long short-term memory/Transformer-LMs that are
trained with two different random initialization seeds. We combine these NLMs
through iterative lattice generation. Since these NLMs work complementarily
with each other, by combining them one by one at each rescoring iteration,
language scores attached to given lattice arcs can be gradually refined.
Consequently, errors of the ASR hypotheses can be gradually reduced. We also
investigate the effectiveness of carrying over contextual information (previous
rescoring results) across a lattice sequence of a long speech such as a lecture
speech. In experiments using a lecture speech corpus, by combining the eight
NLMs and using context carry-over, we obtained a 24.4% relative word error rate
reduction from the ASR 1-best baseline. For further comparison, we performed
simultaneous (i.e., non-iterative) NLM combination and 100-best rescoring using
the large ensemble of NLMs, which confirmed the advantage of lattice rescoring
with iterative NLM combination.

我们研究了使用大规模先进神经语言模型（NLMs）对自动语音识别（ASR）假设进行格栅再评分的效果。通过将最多 8 个 NLMs 进行组合，通过迭代式格栅生成，逐步改进给定格栅弧上的语言评分，我们逐渐降低 ASR 假设的错误。此外，我们还研究了在长篇演讲等持续语音的格栅序列中传递上下文信息（先前的再评分结果）的有效性。在使用演讲语料库进行实验时，通过组合这八个 NLMs 并使用上下文传递，我们相较于 ASR 一流基准线获得了 24.4% 的相对词错误率降低。另外，我们还进行了非迭代式的 NLM 组合和使用大规模 NLMs 的 100 最佳再评分的同时比较，验证了迭代式 NLM 组合进行格栅再评分的优势。

基于大规模互补神经语言模型的格栅重新评分

Lattice Rescoring Based on Large Ensemble of Complementary Neural  Language Models

High-quality automatic speech recognition (ASR) is essential for virtual
assistants (VAs) to work well. However, ASR often performs poorly on VA
requests containing named entities. In this work, we start from the observation
that many ASR errors on named entities are inconsistent with real-world
knowledge. We extend previous discriminative n-gram language modeling
approaches to incorporate real-world knowledge from a Knowledge Graph (KG),
using features that capture entity type-entity and entity-entity relationships.
We apply our model through an efficient lattice rescoring process, achieving
relative sentence error rate reductions of more than 25% on some synthesized
test sets covering less popular entities, with minimal degradation on a
uniformly sampled VA test set.

本文研究提出了一种基于知识图谱的语言建模方法，通过有效的格栅重排过程，达到了相对句子错误率的降低，为虚拟助手 ASR 的精度提高提供了强有力的支持。