Generative semi-supervised learning with a neural seq2seq noisy channel

We present a noisy channel generative model of two sequences, for example text and speech, which enables uncovering the associations between the two modalities when limited paired data is available. To address the intractability of the exact model under a realistic data set-up, we propose a variational inference approximation. To train this variational model with categorical data, we propose a KL encoder loss approach which has connections to the wake-sleep algorithm. Identifying the joint or conditional distributions by only observing unpaired samples from the marginals is only possible under certain structure in the data distribution and we discuss under what type of conditional independence assumptions that might be achieved, which guides the architecture designs. Experimental results show that even tiny amount of paired data is sufficient to learn to relate the two modalities (graphemes and phonemes here) when loads of unpaired data is available, paving the path to adopting this principled approach for ASR and TTS models in low resource data regimes.