Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2013, Pages 7349-7353

  Tuske, Zoltan ^a   Pinto, Joel ^b   Willett, Daniel ^b   Schluter, Ralf ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

^b NUANCE COMMUNICATIONS   (United States)

Author keywords

bottleneck; mismatched acoustical condition; MLP; multilingual

Indexed keywords

BOTTLENECK; LIMITED TRAINING DATA; LOW RESOURCE LANGUAGES; MISMATCHED ACOUSTICAL CONDITION; MLP; MULTI LAYER PERCEPTRON; MULTILINGUAL; MULTILINGUAL TRAININGS;

LEARNING ALGORITHMS; SPEECH RECOGNITION;

SIGNAL PROCESSING;

EID: 84890474441     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6639090     Document Type: Conference Paper

References (15)

1. M. Sundermeyer et al., "The RWTH 2010 QUAERO ASR Evaluation System for English, French, and German," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2011, pp. 2212-2215.
2. H. A. Bourlard and N. Morgan, Connectionist Speech Recognition: A Hybrid Approach. Norwell, MA, USA: Kluwer Academic Publishers, 1993.
3. H. Hermansky et al., "Tandem connectionist feature extraction for conventional HMM systems," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol. 3, 2000, pp. 1635-1638.
4. F. Grezl et al., "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2007, pp. 757-760.
5. A. Stolcke et al., "Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2006, pp. 321-324.
6. C. Plahl et al., "Cross-lingual Portability of Chinese and English Neural Network Features for French and German LVCSR," in Proc. of IEEE Automatic Speech Recognition and Understanding Workshop, 2011, pp. 371-376.
7. L. Toth et al., "Cross-lingual Portability of MLP-Based Tandem Features-A Case Study for English and Hungarian," in Proc. of Interspeech, 2008, pp. 2695-2698.
8. S. Thomas et al., "Cross-lingual and multistream posterior features for low resource LVCSR systems," in Proc. of Interspeech, 2010, pp. 877-880.
9. D. Imseng et al., "Towards mixed language speech recognition systems," in Proc. of Interspeech, 2010, pp. 278-281.
10. N. T. Vu et al., "An Investigation on Initialization Schemes for Multilayer Perceptron Training Using Multilingual Data and Their Effect on ASR Performance," in Proc. of Interspeech, 2012.
11. F. Grezl et al., "Study of probabilistic and bottle-neck features in multilingual environment," in Proc. of IEEE Automatic Speech Recognition and Understanding Workshop, 2011, pp. 359-364.
12. Y. Qian et al., "Strategies for using MLP based features with limited target-language training data," in Proc. of IEEE Automatic Speech Recognition and Understanding Workshop, 2011, pp. 354-358.
13. S. Scanzio et al., "On the Use of a Multilingual Neural Network Front-End," in Proc. of Interspeech, 2008, pp. 2711-2714.
14. S. Thomas et al., "Multilingual MLP features for low-resource LVCSR systems," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2012, pp. 4269-4272.
15. F. Valente et al., "Analysis and Comparison of Recent MLP Features for LVCSR Systems," in Proc. of Interspeech, 2011, pp. 1245-1248.