Should Deep Neural nets have ears? The role of auditory features in deep learning approaches

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2014, Pages 2435-2439

  Martinez, Angel Mario Castro ^a   Moritz, Niko ^a,b   Meyer, Bernd T ^a  

^a UNIVERSITY OF OLDENBURG   (Germany)

^b FRAUNHOFER IDMT   (Germany)

Author keywords

Amplitude modulation filter bank; Deep learning; Deep neural network; Gabor features; Speech recognition

Indexed keywords

AMPLITUDE MODULATION; ARTIFICIAL INTELLIGENCE; FILTER BANKS; GABOR FILTERS; LEARNING SYSTEMS; SIGNAL PROCESSING; SPEECH COMMUNICATION;

ACOUSTIC CONDITIONS; AUDITORY SIGNAL PROCESSING; AUTOMATIC SPEECH RECOGNITION; CONVENTIONAL FILTERS; DEEP LEARNING; DEEP NEURAL NETWORKS; GABOR FEATURE; MEL-FREQUENCY CEPSTRAL COEFFICIENTS;

SPEECH RECOGNITION;

EID: 84910029373     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (30)

1. R. Lippmann, "Speech recognition by machines and humans, " Speech Commun., vol. 22, no. 1, pp. 1-15, 1997.
2. O. Scharenborg, "Reaching over the gap: A review of efforts to link human and automatic speech recognition research, " Speech Commun., pp. 336-347, 2007.
3. B. Meyer and B. Kollmeier, "Robustness of spectro-temporal features against intrinsic and extrinsic variations in automatic speech recognition, " Speech Commun., vol. 53, pp. 753-767, 2011.
4. A. R. Mohamed, G. Hinton and G. Penn, "Understanding how deep belief networks perform acoustic modelling, " in Proc. ICASSP, 2012.
5. G. Dahl, D. Yu, L. Deng and A. Acero, "Context-dependent pretrained deep neural networks for large-vocabulary speech recognition. Audio, Speech, and Language Processing, " IEEE Transactions, vol. 20, no. 1, pp. 30-42, 2012.
6. A. R. Mohamed, T. N. Sainath, G. Dahl, B. Ramabhadran, G. E. Hinton and M. A. Picheny, "Deep belief networks using discriminative features for phone recognition, " in Proc. ICASSP, 2011.
7. T. N. Sainath, B. Kingsbury, B. Ramabhadran, P. Fousek, P. Novak and A. R. Mohamed, "Making deep belief networks effective for large vocabulary continuous speech recognition, " in IEEE Workshop ASRU, 2011.
8. H. Hermansky, D. Ellis and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems, " in Proc. Interspeech, 2000.
9. H. Hermansky, D. Ellis and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems, " in Proc. Interspeech, 2000.
10. C. Kim and R. M. Stern, "Feature extraction for robust speech recognition using a power-law nonlinearity and power-bias subtraction, " in Proc. Interspeech, 2009.
11. R. Patterson, K. Robinson, J. Holdsworth, D. McKeown, C. Zhang and M. Allerhand, "Complex sounds and auditory images, " in Auditory physiology and perception, Proc. 9th International Symposium on Hearing, 1992.
12. A. Qiu, C. Schreiner and M. Escabi, "Gabor analysis of auditory mid- brain receptive fields: Spectro-temporal and binaural composition, " Journal of Neurophysiology, vol. 90, pp. 456-476, 2003.
13. N. Mesgarani, D. Stephen and S. Shamma, "Representation of phonemes in primary auditory cortex: How the brain analyzes speech, " in Proc. ICASSP, 2007.
14. M. Kleinschmidt and D.Gelbart, "Improving word accuracy with Gabor feature extraction, " in Proc. Interspeech, 2002.
15. M. R. Schädler, B. Kollmeier and B. T. Meyer, "Spectrotemporal modulation subspace-spanning filter bank features for robust automatic speech recognition, " J. Acoust. Soc. Am., pp. 4134-4151, 2011.
16. B. Meyer, C. Spille, B. Kollmeier and N. Morgan, "Hooking up spectro-temporal filters with auditory-inspired representations for robust automatic speech recognition, " in Proc. Interspeech, 2012.
17. H. Lei, B. Meyer and N. Mirghafori, "Spectro-temporal Gabor features for speaker recognition, " in Proc. ICASSP, 2012.
18. G. Langner and C. Schreiner, "Periodicity coding in the inferior Colliculus of the cat. I. Neuronal mechanisms, " J. of Neurophysiology, vol. 60, pp. 1799-1822, 1988.
19. B. Kollmeier and R. Koch, "Speech enhancement based on physiological and psychoacoustical models of modulation perception and binaural interaction, " J. Acoust. Soc. Am., vol. 95, no. 3, pp. 1593-1602, 1994.
20. T. Dau, B. Kollmeier and A. Kohlrausch, "Modeling Auditory Processing of Amplitude Modulation. I. Detection and Masking with Narrow-Band Carriers, " J. Acoustic Soc. Am., vol. 102, no. 5, p. 2892-2905, 1997.
21. F. Xiong, N. Moritz, R. Rehr, J. Anemüller, B. Meyer, T. Gerkmann, S. Doclo and S. Goetze, "Robust ASR in Reverberant Environments Using Temporal Cepstrum Smoothing for Speech Enhancement and an Amplitude Modulation Filterbank for Feature Extraction, " in Proc. REVERB Workshop, 2014.
22. B. Meyer, T. Brand and B. Kollmeier, "Effect of speech-intrinsic variations on human and automatic recognition of spoken phonemes, " J. Acoust. Soc. Am., vol. 129, pp. 388-403, 2011.
23. N. Moritz, J. Anemüller and B. Kollmeier, "Amplitude Modulation Spectrogram based Features for Robust Speech Recognition in Noisy and Reverberant Environments, " in Proc. ICASSP, 2011.
24. N. Moritz, J. Anemüller and B. Kollmeier, "Amplitude Modulation Filters as Feature Sets for Robust ASR: Constant Absolute or Relative Bandwidth?, " in Proc. Interspeech, Portland, USA, 2012.
25. S. Davis and P. Mermelstein, "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences, " IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 28, no. 4, pp. 357-366., 1980.
26. S. Rath, D. Povey, K. Veselý and J. Cernocký, "Improved feature processing for deep neural networks, " in Interspeech, 2013.
27. K. Veselý, A. Ghoshal, L. Burget and D. Povey, "Sequencediscriminative training of deep neural networks, " in Proc. Interspeech, 2013.
28. G. Hinton, "A practical guide to training restricted Boltzmann machines, " Momentum, vol. 9, no. 1, p. 926, 2010.
29. D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel und K. Veselý, "The Kaldi speech recognition toolkit, " in Proc. ASRU, 2011.
30. N. Parihar and J. Picone, Aurora working group: DSR front end LVCSR evaluation AU/384/02, Inst. for Signal and Information Process, Mississippi State University, Technical Report, 2002.