Paper ID | SPE-2.5 | ||
Paper Title | USING SYNTHETIC AUDIO TO IMPROVE THE RECOGNITION OF OUT-OF-VOCABULARY WORDS IN END-TO-END ASR SYSTEMS | ||
Authors | Xianrui Zheng, University of Cambridge, United Kingdom; Yulan Liu, Deniz Gunceler, Daniel Willett, Amazon, United Kingdom | ||
Session | SPE-2: Speech Recognition 2: Neural transducer Models 2 | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 13:00 - 13:45 | ||
Presentation Time: | Tuesday, 08 June, 13:00 - 13:45 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-LVCR] Large Vocabulary Continuous Recognition/Search | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Today, many state-of-the-art automatic speech recognition (ASR) systems apply all-neural models that map audio to word sequences trained end-to-end along one global optimisation criterion in a fully data driven fashion. These models allow high precision ASR for domains and words represented in the training material but have difficulties recognising words that are rarely or not at all represented during training, i.e. trending words and new named entities. In this paper, we use a text-to-speech (TTS) engine to provide synthetic audio for out-of-vocabulary (OOV) words. We aim to boost the recognition accuracy of a recurrent neural network transducer (RNN-T) on OOV words by using the extra audio-text pairs, while maintaining the performance on the non-OOV words. Different regularisation techniques are explored and the best performance is achieved by fine-tuning the RNN-T on both original training data and extra synthetic data with elastic weight consolidation (EWC) applied on the encoder. This yields a 57% relative word error rate (WER) reduction on utterances containing OOV words without any degradation on the whole test set. |