Acoustic modeling with deep neural networks using raw time signal for LVCSR

@inproceedings{Tske2014AcousticMW,
  title={Acoustic modeling with deep neural networks using raw time signal for LVCSR},
  author={Zolt{\'a}n T{\"u}ske and Pavel Golik and Ralf Schl{\"u}ter and Hermann Ney},
  booktitle={INTERSPEECH},
  year={2014}
}
In this paper we investigate how much feature extraction is required by a deep neural network (DNN) based acoustic model for automatic speech recognition (ASR). We decompose the feature extraction pipeline of a state-of-the-art ASR system step by step and evaluate acoustic models trained on standard MFCC features, critical band energies (CRBE), FFT magnitude spectrum and even on the raw time signal. The focus is put on raw time signal as input features, i.e. as much as zero feature extraction… CONTINUE READING
Highly Cited
This paper has 110 citations. REVIEW CITATIONS
73 Citations
20 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 73 extracted citations

111 Citations

0204020142015201620172018
Citations per Year
Semantic Scholar estimates that this publication has 111 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 20 references

Similar Papers

Loading similar papers…