As human-machine voice interfaces provide easy access to increasingly
intelligent machines, many state-of-the-art automatic speech recognition (ASR)
systems are proposed. However, commercial ASR systems usually have poor
performance on domain-specific speech especially under low-resource settings.
The author works with pre-trained DeepSpeech2 and Wav2Vec2 acoustic models to
develop benefit-specific ASR systems. The domain-specific data are collected
using proposed semi-supervised learning annotation with little human
intervention. The best performance comes from a fine-tuned Wav2Vec2-Large-LV60
acoustic model with an external KenLM, which surpasses the Google and AWS ASR
systems on benefit-specific speech. The viability of using error prone ASR
transcriptions as part of spoken language understanding (SLU) is also
investigated. Results of a benefit-specific natural language understanding
(NLU) task show that the domain-specific fine-tuned ASR system can outperform
the commercial ASR systems even when its transcriptions have higher word error
rate (WER), and the results between fine-tuned ASR and human transcriptions are
similar.

使用预训练的 DeepSpeech2 和 Wav2Vec2 声学模型，提出了基于领域的语音自动识别系统，并通过半监督机器注释的方式收集领域特定的数据，研究结果表明，该系统即使在具有更高的字词错误率的情况下，性能仍优于商业自动语音识别系统，且在人工转录的结果上也呈现出类似的效果。同时，也探讨了使用自动语音识别文字转录来辅助口语理解的可行性。