Abstract
We proposed an automatic speech recognition (ASR) error correction method using hybrid word sequence matching and recurrent neural network for dialog system applications. Basically, the ASR errors are corrected by the word sequence matching whereas the remaining OOV (out of vocabulary) errors are corrected by the secondary method which uses a recurrent neural network based syllable prediction. We evaluated our method on a test parallel corpus (Korean) including ASR results and their correct transcriptions. Overall result indicates that the method effectively decreases the word error rate of the ASR results. The proposed method can correct ASR errors only with a text corpus without their speech recognition results, which means that the method is independent to the ASR engine. The method is general and can be applied to any speech based application such as spoken dialog systems.
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
Similar content being viewed by others
Notes
- 1.
In some cases, the syllable prediction length is longer than the number of syllables of the detected erroneous word. Then, to predict a syllable, the method must predict a phoneme first.
- 2.
The number of syllables and phonemes is constant for Korean.
References
Brandow, R.L., Strzalkowski, T.: Improving speech recognition through text-based linguistic post-processing. US Patent 6,064,957, 16 May 2000
Choi, J., Kim, K., Lee, S., Kim, S., Lee, D., Lee, I., Lee, G.G.: Seamless error correction interface for voice word processor. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4973–4976. IEEE (2012)
Choi, J., Lee, D., Ryu, S., Lee, K., Kim, K., Noh, H., Lee, G.G.: Engine-independent asr error management for dialog systems. In: Intenational Workshop Series on Spoken Dialogue Systems Technology (IWSDS) (2014)
Evermann, G., Woodland, P.: Posterior probability decoding, confidence estimation and system combination (2000)
Fiscus, J.G.: A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (rover). In: Proceedings of the 1997 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 347–354. IEEE (1997)
Han, D., Choi, K.: A study on error correction using phoneme similarity in post-processing of speech recognition. J. Korea Inst. Intel. Transp. Syst. 6(3), 77–86 (2007). The Korean Institute of Intelligent Transport Systems (Korean ITS)
Jeong, M., Jung, S., Lee, G.G.: Speech recognition error correction using maximum entropy language model. In: Proceedings of INTERSPEECH, pp. 2137–2140 (2004)
Mikolov, T., Karafiát, M., Burget, L., Cernockỳ, J., Khudanpur, S.: Recurrent neural network based language model. In: INTERSPEECH, pp. 1045–1048 (2010)
Mikolov, T., Kombrink, S., Burget, L., Cernocky, J., Khudanpur, S.: Extensions of recurrent neural network language model. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5528–5531. IEEE (2011)
Ringger, E.K., Allen, J.F.: A fertility channel model for post-correction of continuous speech recognition. In: Proceedings of the Fourth International Conference on Spoken Language, 1996. ICSLP 1996, vol. 2, pp. 897–900. IEEE (1996)
Acknowledgements
This work was partly supported by the ICT R&D program of MSIP/IITP [14-824-09-014, Basic Software Research in Human-level Lifelong Machine Learning (Machine Learning Center)] and by the National Research Foundation of Korea (NRF) [NRF-2014R1A2A1A01003041].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Choi, J. et al. (2015). ASR Independent Hybrid Recurrent Neural Network Based Error Correction for Dialog System Applications. In: Böck, R., Bonin, F., Campbell, N., Poppe, R. (eds) Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction. MA3HMI 2014. Lecture Notes in Computer Science(), vol 8757. Springer, Cham. https://doi.org/10.1007/978-3-319-15557-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-15557-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-15556-2
Online ISBN: 978-3-319-15557-9
eBook Packages: Computer ScienceComputer Science (R0)