论文标题
使用最近的邻居对比学习的语音序列嵌入
Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning
论文作者
论文摘要
我们介绍了一个简单的神经编码器体系结构，可以使用无监督的对比学习目标对其进行训练，该目标从数据增强的K-Nearthiend邻居搜索中获取积极样本。我们表明，当建立在最近的自我监管的音频表示之上时，该方法可以迭代地应用，并在两个任务上评估竞争性SSE：逐个典型的语音序列和口语术语发现。在这两个任务上，我们的方法都通过5种不同语言的大幅度来推动最先进的余量。最后，我们在LibrisPeech数据集上的逐个示例任务上建立了一个基准测试，以监视该领域的未来改进。
We introduce a simple neural encoder architecture that can be trained using an unsupervised contrastive learning objective which gets its positive samples from data-augmented k-Nearest Neighbors search. We show that when built on top of recent self-supervised audio representations, this method can be applied iteratively and yield competitive SSE as evaluated on two tasks: query-by-example of random sequences of speech, and spoken term discovery. On both tasks our method pushes the state-of-the-art by a significant margin across 5 different languages. Finally, we establish a benchmark on a query-by-example task on the LibriSpeech dataset to monitor future improvements in the field.
