Open-Source Speech Corpus and Initial Speech Recognition Experiments
Keywords:
speech corpus, E2E, USC, ASR, USC, DNN-HMM, WER
Abstract
We present a speech corpus and report preliminary results of automatic speech recognition (ASR) using a hidden deep neural network Markov model (DNNHMM) and an end-to-end (E2E) architecture.
References
1. Speechocean’s Uzbek speech corpus. http://en.speechocean.com/datacenter/details/1847.html, accessed: 2021-05-21
2. Uzbek language. https://en.wikipedia.org/wiki/Uzbek language, accessed: 2021-05-20
3. Voxforge. http://www.voxforge.org/, accessed: 2021-05-11 Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)
4. Abdel-Hamid, O., Mohamed, A., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional neural networks for speech recognition. IEEE ACM Trans. Audio Speech Lang. Process. 22(10), 1533–1545 (2014)
2. Uzbek language. https://en.wikipedia.org/wiki/Uzbek language, accessed: 2021-05-20
3. Voxforge. http://www.voxforge.org/, accessed: 2021-05-11 Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)
4. Abdel-Hamid, O., Mohamed, A., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional neural networks for speech recognition. IEEE ACM Trans. Audio Speech Lang. Process. 22(10), 1533–1545 (2014)
Published
2022-08-31
How to Cite
A.A. Rakhmanov. (2022). Open-Source Speech Corpus and Initial Speech Recognition Experiments. International Journal of Human Computing Studies, 4(8), 4-6. https://doi.org/10.31149/ijhcs.v4i8.3578
Section
Articles
3.png)
