RNN Transducer Models for Spoken Language Understanding

Abstract

We present a comprehensive study on building and adapting RNN transducer (RNN-T) models for spoken language understanding (SLU). These end-to-end (E2E) models are constructed in three practical settings: a case where verbatim transcripts are available, a constrained case where the only available annotations are SLU labels and their values, and a more restrictive case where transcripts are available but not corresponding audio. We show how RNN-T SLU models can be developed starting from pre-trained automatic speech recognition (ASR) systems, followed by an SLU adaptation step. In settings where real audio data is not available, artificially synthesized speech is used to successfully adapt various SLU models. When evaluated on two SLU data sets, the ATIS corpus and a customer call center data set, the proposed models closely track the performance of other E2E models and achieve state-of-the-art results.

A new data augmentation method for intent classification enhancement and its application on spoken conversation datasets

“…The graph clearly shows that additional data helps to improve the accuracy of the classifier. Our second dataset was composed of recordings from a call center with manual transcription and labeling [12][13][14]. There are in total about 30,000 samples split into test (5,600), train (21,900), and development (2,500) sets.…”