CONF Wollmer_ICASSP_2009/IDIAP Robust Discriminative Keyword Spotting for Emotionally Colored Spontaneous Speech using Bidirectional LSTM Networks Wöllmer, Martin Eyben, Florian Keshet, Joseph Graves, Alex Schuller, Björn Rigoll, Gerhard EXTERNAL https://publications.idiap.ch/attachments/papers/2009/Wollmer_ICASSP_2009.pdf PUBLIC IEEE International Conference on Acoustic, Speech, and Signal Processing 2009 Taipei, Taiwan In this paper we propose a new technique for robust keyword spotting that uses bidirectional Long Short-Term Memory (BLSTM) recurrent neural nets to incorporate contextual information in speech decoding. Our approach overcomes the drawbacks of generative HMM modeling by applying a discriminative learning procedure that non-linearly maps speech features into an abstract vector space. By incorporating the outputs of a BLSTM network into the speech features, it is able to make use of past and future context for phoneme predictions. The robustness of the approach is evaluated on a keyword spotting task using the HUMAINE Sensitive Artificial Listener (SAL) database, which contains accented, spontaneous, and emotionally colored speech. The test is particularly stringent because the system is not trained on the SAL database, but only on the TIMIT corpus of read speech. We show that our method prevails over a discriminative keyword spotter without BLSTM-enhanced feature functions, which in turn has been proven to outperform HMM-based techniques.