2019

Multilingual Speech Recognition with Corpus Relatedness Sampling

Li, Xinjian, Dalmia, Siddharth, Black, Alan W. et al.

Understand

Multilingual acoustic models have been successfully applied to low-resource speech recognition.

Most existing works have combined many small corpora together and pretrained a multilingual model by sampling from each corpus uniformly.
The model is eventually fine-tuned on each target corpus.
This approach, however, fails to exploit the relatedness and similarity among corpora in the training set.

Built on

J. J. Godfrey, E. C. Holliman, and J. McDaniel, “SWITCHBOARD: Telephone speech corpus for research and development,” in
1992
Earlier work this paper cites.
T. Schultz and A. Waibel, “Language-independent and language-adaptive acoustic modeling for speech recognition,”
2001
Earlier work this paper cites.
C. Cieri, D. Miller, and K. Walker, “The fisher corpus: a resource for the next generations of speech-to-text.” in
2004
Earlier work this paper cites.
G. Riccardi and D. Hakkani-Tur, “Active learning: Theory and applications to automatic speech recognition,”
2005
Earlier work this paper cites.
A. Stolcke, F. Grezl, M.-Y. Hwang, X. Lei, N. Morgan, and D. Vergyri, “Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons,” in
2006
Earlier work this paper cites.
Y. Liu, P. Fung, Y. Yang, C. Cieri, S. Huang, and D. Graff, “Hkust/mts: A very large scale mandarin telephone speech corpus,” in
2006
Earlier work this paper cites.
A. Graves, S. Fernández, F. Gomez, and J. Schmidhuber, “Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,” in
2006
Earlier work this paper cites.
L. v. d. Maaten and G. Hinton, “Visualizing data using t-sne,”
2008
Earlier work this paper cites.
L. Burget, P. Schwarz, M. Agarwal, P. Akyazi, K. Feng, A. Ghoshal, O. Glembek, N. Goel, M. Karafiát, D. Povey
2010
Earlier work this paper cites.
K. Veselỳ, M. Karafiát, F. Grézl, M. Janda, and E. Egorova, “The language-independent bottleneck features,” in
2012
Earlier work this paper cites.
A. Rousseau, P. Deléglise, and Y. Esteve, “TED-LIUM: an automatic speech recognition dedicated corpus.” in
2012
Earlier work this paper cites.

Similar

M. Saraclar, “Turkish broadcast news speech and transcripts ldc2012s06,”
2012
Cited alongside, same era.
J.-T. Huang, J. Li, D. Yu, L. Deng, and Y. Gong, “Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers,” in
2013
Cited alongside, same era.
G. Heigold, V. Vanhoucke, A. Senior, P. Nguyen, M. Ranzato, M. Devin, and J. Dean, “Multilingual acoustic models using distributed deep neural networks,” in
2013
Cited alongside, same era.
N. T. Vu and T. Schultz, “Multilingual multilayer perceptron for rapid language adaptation between and across language families.” in
2013
Cited alongside, same era.
Q. Le and T. Mikolov, “Distributed representations of sentences and documents,” in
2014
Cited alongside, same era.
R. Kiros, Y. Zhu, R. R. Salakhutdinov, R. Zemel, R. Urtasun, A. Torralba, and S. Fidler, “Skip-thought vectors,” in
2015
Cited alongside, same era.
J. Cui, B. Kingsbury, B. Ramabhadran, A. Sethy, K. Audhkhasi, X. Cui, E. Kislal, L. Mangu, M. Nussbaum-Thom, M. Picheny
2015
Cited alongside, same era.
Z. Z. Dong Wang, Xuewei Zhang, “Thchs-30 : A free chinese speech corpus,” 2015. [Online]. Available:
Original
2015
Cited alongside, same era.
V. Panayotov, G. Chen, D. Povey, and S. Khudanpur, “Librispeech: an ASR corpus based on public domain audio books,” in
2015
Cited alongside, same era.
Y. Miao, M. Gowayyed, and F. Metze, “EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding,” in
2015
Cited alongside, same era.
D. Amodei, S. Ananthanarayanan, R. Anubhai, J. Bai, E. Battenberg, C. Case, J. Casper, B. Catanzaro, Q. Cheng, G. Chen
2016
Cited alongside, same era.

Then

W. Xiong, J. Droppo, X. Huang, F. Seide, M. Seltzer, A. Stolcke, D. Yu, and G. Zweig, “Achieving human parity in conversational speech recognition,”
Original
2016
Later among the works it cites.
Y. Kim, Y. Jernite, D. Sontag, and A. M. Rush, “Character-aware neural language models,” in
2016
Later among the works it cites.
S. Tong, P. N. Garner, and H. Bourlard, “An investigation of deep neural networks for multilingual speech recognition training and adaptation,” Tech. Rep., 2017
2017
Later among the works it cites.
P. Bojanowski, E. Grave, A. Joulin, and T. Mikolov, “Enriching word vectors with subword information,”
2017
Later among the works it cites.
M. Johnson, M. Schuster, Q. V. Le, M. Krikun, Y. Wu, Z. Chen, N. Thorat, F. Viégas, M. Wattenberg, G. Corrado
2017
Later among the works it cites.
S. Braun, D. Neil, and S.-C. Liu, “A curriculum learning method for improved noise robustness in automatic speech recognition,” in
2017
Later among the works it cites.
S. Dalmia, R. Sanabria, F. Metze, and A. W. Black, “Sequence-based multi-lingual low resource speech recognition,” in
2018
Later among the works it cites.
S. Dalmia, X. Li, F. Metze, and A. W. Black, “Domain robust feature extraction for rapid low resource asr development,” in
2018
Later among the works it cites.
B. Li, T. N. Sainath, K. C. Sim, M. Bacchiani, E. Weinstein, P. Nguyen, Z. Chen, Y. Wu, and K. Rao, “Multi-dialect speech recognition with a single sequence-to-sequence model,” in
2018
Later among the works it cites.
L. Primewords Information Technology Co., “Primewords chinese corpus set 1,” 2018,
2018
Later among the works it cites.
D. R. Mortensen, S. Dalmia, and P. Littell, “Epitran: Precision G2P for many languages.” in
2018
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…