We describe the Sogou neural machine translation systems for the WMT 2017 Chinese↔English news translation tasks. Our systems are based on a multilayer encoder-decoder architecture with attention mechanism. The best translation is obtained with ensemble and reranking techniques. We also propose an approach to improve the named entity translation problem. Our Chinese→English system achieved the highest cased BLEU among all 20 submitted systems, and our English→Chi-nese system ranked the third out of 16 submitted systems.

No abstract

We present an extended Parrotron model: a single, end-to-end network that enables voice conversion and recognition simultaneously. Input spectrograms are transformed to output spectrograms in the voice of a predetermined target speaker while also generating hypotheses in a target vocabulary. We study the performance of this novel architecture, which jointly predicts speech and text, on atypical (e.g. dysarthric) speech. We show that with as little as an hour of atypical speech, speaker adaptation can yield a 77% relative reduction in Word Error Rate (WER), measured by ASR performance on the converted speech. We also show that data augmentation using a customized synthesizer built on atypical speech can provide an additional 10% relative improvement over the best speaker-adapted model. Finally, we show how these methods generalize across 8 types of atypical speech for a range of speech impairment severities.

No abstract

No abstract