Recognizing long-form speech using streaming end-to-end models
This addresses a generalization issue in speech recognition for long-form applications like call centers, with incremental improvements over existing methods.
The paper tackled the problem of end-to-end speech recognition models failing to generalize from short utterances to long-form speech, proposing training on diverse acoustic data and LSTM state manipulation, which improved word error rates by up to 90% on synthesized data and 40-67% on real call-center data.
All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the ability of E2E models to generalize to unseen domains, where we find that models trained on short utterances fail to generalize to long-form speech. We propose two complementary solutions to address this: training on diverse acoustic data, and LSTM state manipulation to simulate long-form audio when training using short utterances. On a synthesized long-form test set, adding data diversity improves word error rate (WER) by 90% relative, while simulating long-form training improves it by 67% relative, though the combination doesn't improve over data diversity alone. On a real long-form call-center test set, adding data diversity improves WER by 40% relative. Simulating long-form training on top of data diversity improves performance by an additional 27% relative.