Technology Radar
Published : Oct 27, 2021
NOT ON THE CURRENT EDITION
This blip is not on the current edition of the Radar. If it was on one of the last few editions, it is likely that it is still relevant. If the blip is older, it might no longer be relevant and our assessment might be different today. Unfortunately, we simply don't have the bandwidth to continuously review blips from previous editions of the Radar.
Understand more
Oct 2021
Trial
Wav2Vec 2.0 是用于语音识别的自我监督学习框架。 在这个框架里，模型被分为两个阶段进行训练。 首先，它从使用未标记数据的自我监督模式开始，并尝试实现最佳的语音表达。 然后它进行有监督的微调整，在此期间，已被标记的数据指导模型去预测特定的单词或音素。使用 Wav2Vec 后，我们发现它的方法非常强大，即使有标记数据的可用性有限，它也可以为区域语言构建自动语音识别模型。
