Labeled audio data is insufficient to build satisfying speech recognition
systems for most of the languages in the world. There have been some
zero-resource methods trying to perform phoneme or word-level speech
recognition without labeled audio data of the target language, but the error
rate of these methods is usually too high to be applied in real-world
scenarios. Recently, the representation ability of self-supervise pre-trained
models has been found to be extremely beneficial in zero-resource phoneme
recognition. As far as we are concerned, this paper is the first attempt to
extend the use of pre-trained models into word-level zero-resource speech
recognition. This is done by fine-tuning the pre-trained models on IPA phoneme
transcriptions and decoding with a language model trained on extra texts.
Experiments on Wav2vec 2.0 and HuBERT models show that this method can achieve
less than 20% word error rate on some languages, and the average error rate on
8 languages is 33.77%.

本文研究使用预训练模型来解决无监督语音识别中的音素和单词级别的问题。通过在 IPA 音素转写上微调预训练模型并使用语言模型进行解码，实验结果表明该方法可在某些语言上实现低于 20% 的单词错误率，8 种语言的平均错误率为 33.77%。