Automatic Speech Recognition (ASR) has witnessed a profound research interest. Recent breakthroughs have given ASR systems different prospects such as faithfully transcribing spoken language, which is a pivotal advancement in building conversational agents. However, there is still an imminent challenge of accurately discerning context-dependent words and phrases. In this work, we propose a novel approach for enhancing contextual recognition within ASR systems via semantic lattice processing leveraging the power of deep learning models in accurately delivering spot-on transcriptions across a wide variety of vocabularies and speaking styles. Our solution consists of using Hidden Markov Models and Gaussian Mixture Models (HMM-GMM) along with Deep Neural Networks (DNN) models integrating both language and acoustic modeling for better accuracy. We infused our network with the use of a transformer-based model to properly rescore the word lattice achieving remarkable capabilities with a palpable reduction in Word Error Rate (WER). We demonstrate the effectiveness of our proposed framework on the LibriSpeech dataset with empirical analyses.

翻译：自动语音识别（ASR）已引起广泛的研究兴趣。近期的突破为ASR系统带来了不同前景，例如准确转录口语，这是构建对话智能体的关键进展。然而，准确辨别上下文相关词汇和短语仍是一项紧迫挑战。本研究提出了一种新方法，通过语义网格处理增强ASR系统中的上下文识别能力，利用深度学习模型在多种词汇和说话风格中准确提供精准转录的优势。我们的解决方案包括使用隐马尔可夫模型和高斯混合模型（HMM-GMM），并结合深度神经网络（DNN）模型，集成语言和声学建模以提高准确性。我们在网络中引入了基于Transformer的模型，对词语网格进行重评分，实现了显著能力，并明显降低了词错误率（WER）。通过在LibriSpeech数据集上的实证分析，我们展示了所提框架的有效性。