Abstract
In this paper we propose a pure “neural network” (NN) based keyword search system developed in the IARPA Babel program for conversational telephone speech. Using a common keyword search evaluation metric, “actual term weighted value” (ATWV), we demonstrate that our NN-keyword search system can achieve a performance similar to a comparible but more complex and slower “hybrid deep neural network - hidden markov model” (DNN-HMM Hybrid) based speech recognition system without using either an HMM decoder or a language model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., Bengio, Y.: Theano: A CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference (SciPy) (June 2010) Oral Presentation
Cui, J., Cui, X., Ramabhadran, B., Kim, J., Kingsbury, B., Mamou, J., Mangu, L., Picheny, M., Sainath, T.N., Sethy, A.: Developing speech recognition systems for corpus indexing under the iarpa babel program. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6753–6757. IEEE (2013)
Gehring, J., Lee, W., Kilgour, K., Lane, I., Miao, Y., Waibel, A., Campus, S.V.: Modular combination of deep neural networks for acoustic modeling. In: Proc. Interspeech, pp. 94–98 (2013)
Gehring, J., Miao, Y., Metze, F., Waibel, A.: Extracting deep bottleneck features using stacked auto-encoders. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3377–3381. IEEE (2013)
Goodman, J., Chen, S.: An empirical study of smoothing techniques for language modeling. Tech. rep., Technical Report TR-10-98, Harvard University (August 1998)
Heck, M., Mohr, C., Stüker, S., Müller, M., Kilgour, K., Gehring, J., Nguyen, Q.B., Van Nguyen, H., Waibel, A.: Segmentation of telephone speech based on speech and non-speech models. In: Železný, M., Habernal, I., Ronzhin, A. (eds.) SPECOM 2013. LNCS (LNAI), vol. 8113, pp. 286–293. Springer, Heidelberg (2013)
Hsiao, R., Ng, T., Grezl, F., Karakos, D., Tsakalidis, S., Nguyen, L., Schwartz, R.: Discriminative semi-supervised training for keyword search in low resource languages. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 440–445. IEEE (2013)
IARPA: Iarpa babel program - broad agency announcement, baa (2011), http://www.iarpa.gov/Programs/ia/Babel/solicitation_babel.html
Karakos, D., Schwartz, R., Tsakalidis, S., Zhang, L., Ranjan, S., Ng, T., Hsiao, R., Saikumar, G., Bulyko, I., Nguyen, L., et al.: Score normalization and system combination for improved keyword spotting. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 210–215. IEEE (2013)
Kingsbury, B., Cui, J., Cui, X., Gales, M.J., Knill, K., Mamou, J., Mangu, L., Nolden, D., Picheny, M., Ramabhadran, B., et al.: A high-performance cantonese keyword search system. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8277–8281. IEEE (2013)
Kolkhorst, H.: Strategies for Out-of-Vocabulary Words in Spoken Term Detection. Undergraduate thesis (2011)
Kurniawati, E., George, S.: Speaker dependent activation keyword detector based on gmm-ubm (2013)
Metze, F., Sheikh, Z.A., Waibel, A., Gehring, J., Kilgour, K., Nguyen, Q.B., Nguyen, V.H.: Models of tone for tonal and non-tonal languages. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 261–266. IEEE (2013)
Soltau, H., Metze, F., Fugen, C., Waibel, A.: A one-pass decoder based on polymorphic linguistic context assignment. In: IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001, pp. 214–217. IEEE (2001)
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. The Journal of Machine Learning Research 9999, 3371–3408 (2010)
Wang, Q., Zhang, X., Zhang, Y., Yi, Q.: Augem: Automatically generate high performance dense linear algebra kernels on x86 cpus. In: Proceedings of SC 2013: International Conference for High Performance Computing, Networking, Storage and Analysis, p. 25. ACM (2013)
Wang, Y.: An in-depth comparison of keyword specific thresholding and sum-to-one score normalization. Tech. rep., Technical Report, Carnegie Mellon University (2014)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kilgour, K., Waibel, A. (2014). A Neural Network Keyword Search System for Telephone Speech. In: Ronzhin, A., Potapova, R., Delic, V. (eds) Speech and Computer. SPECOM 2014. Lecture Notes in Computer Science(), vol 8773. Springer, Cham. https://doi.org/10.1007/978-3-319-11581-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-11581-8_7
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11580-1
Online ISBN: 978-3-319-11581-8
eBook Packages: Computer ScienceComputer Science (R0)