Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard

20 Jan 2020  ·  Zoltán Tüske, George Saon, Kartik Audhkhasi, Brian Kingsbury ·

It is generally believed that direct sequence-to-sequence (seq2seq) speech recognition models are competitive with hybrid models only when a large amount of data, at least a thousand hours, is available for training. In this paper, we show that state-of-the-art recognition performance can be achieved on the Switchboard-300 database using a single headed attention, LSTM based model. Using a cross-utterance language model, our single-pass speaker independent system reaches 6.4% and 12.5% word error rate (WER) on the Switchboard and CallHome subsets of Hub5'00, without a pronunciation lexicon. While careful regularization and data augmentation are crucial in achieving this level of performance, experiments on Switchboard-2000 show that nothing is more useful than more data. Overall, the combination of various regularizations and a simple but fairly large model results in a new state of the art, 4.7% and 7.8% WER on the Switchboard and CallHome sets, using SWB-2000 without any external data resources.

PDF Abstract


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Speech Recognition swb_hub_500 WER fullSWBCH IBM (LSTM encoder-decoder) Percentage error 7.8 # 2
Speech Recognition Switchboard + Hub500 IBM (LSTM encoder-decoder) Percentage error 4.7 # 2