Page 28 - Winter Issue 2018
P. 28

Deep Language Learning
Brain Stimulation Chelba, C., and Ielinek, F. (2000). Structured language modeling. Computer
» - _ Speech and Language 14, 283-332.
Neurotechnology may play a role 1n foreign la.nguage cur chomwski’ L Bahdamu, D” Serdyuk DI, Kylmghylm’ C‘, and Bmgio, Y.
“C1113 of the future‘ A $12 mllhon DARPA grant to Johns (2015). Attention-based models for speech recognition. Proceedings of the
Hopkins University (Baltimore, MD) and collaborating 28th International Conference on Neural Information Processing Systems,
institutions explores whether the ability to learn a foreign M°m'e31- QC- C‘“13da»D5°"mb9‘” 7'12» 2015- V01 1» PP- 577535-
language can be enhanced through modulating the activa- Coll’ R‘ A" Flmly’ M" Noll’ M" and Llllldll’ T‘ 099.4)‘ Tlllpholll speech
. _ corpus development at CSLU. Proceedings of the Third International Con-
tlon of mleva-nt Parts of the audltory and speech areas of the ference on Spoken Language Processing (ICSLP1994), Yokohama, Iapan,
brain through electrical stimulation of the vagus nerve (e.g., September 18-22, 1994, pp. 1815-1818.
Engineer et al” 2015)_ Davis, S. B., and Mermelstein, P. (1980). Comparison of parametric rep.
resentations for monosyllabic word recognition in continuously spoken
Br-avg I\|gw Lap-gguag3_Laa|-nlng Vvarjd sentences. LEEE Transactions on Acoustics Speech and Signal Processing 28,
- - . 357-364.
DNN_ powered sllllellll llllllllllllllgy ls llllllly lll Play  llll Engineer, C. T., Engineer, N. D., Riley, I. R., Scale, I. D., and Kilgard, M. P.
Creasmgly Promlnent role 1“ 1anguage'1earnmg curnCu1a' (2015). Pairing speech sounds with vagus nerve stimulation drives stimu-
As computational power increases and costs diminish, sim— lus-specific cortical plasticity. Brain Stimulation 8, 637-644.
ulation technology will enable a student to inhabit a virtual Eskfnali» M- (13009)-A“ °V51'Vi¢W 0f 5P°k911 language ‘ECW101087 f°1' Cd“-
lllngullgll _wollld lllll hours on el_ld' This 15 likely the llullurll of F::il1l:<l1l,lIl;leuS1l1l£:lr::l:',llIl.l.l,lll{ldl1lrllo:,l l\/sll:2arl1l¢lill3ratt, H. (1999). Automatic de-
la-nguage mstructtonr for there 15 no better Way to learn 3 tor‘ tection of phone-level mispronunciation for language learning. Proceed-
eign tongue than to reside in a community where it is spo- ings of the 6th European Conference on Speech Communication and Tech-
ken. Will it matter that the language community exists only :g"§};iEUROsPEECHl99)’ B“daP"5t' H““$““'Y’ S“Pte"‘b" 5'9’ 1999= PP-
vullluauyl Vullual reahly gammg devices’ such as the Oculus Furui, S. (1986). On the role of spectral transition for speech perception.
Rift“. will only improve over time, enhancing their educa- The Journal ofthe Acoustical Society ofAmerica 30, 1015-1025.
tional potential. Indeed, language learning could become a Goodfellow. 1.. Courville, A., and Bengio. Y. (2016)- Deep Learning. MIT
cc - 2: - Press, Cambridge, MA.
llllllll app loll ellllcllllllllal Vlll Slay lllllelll Greenberg, S. (1999). Speaking in shorthand — A syllable-centric perspec-
tive for understanding pronunciation variation. Speech Communication
n9f9"9"“=93 29, 159-176.
  Greenberg, S., and Chang, S. (2000). Linguistic dissection of switchboard-
Ank, S. 0., Chrzanowski, M., Coates, A., Diamos, G., Gibiansky, A., Kang, corpus automatic speech recognition systems. International Speech Com-
Y., Li, X., Miller, I., Ng, A., Raiman, I., Sengupta, S., and Shoeybi, M. municatiun Association Workshop on Automatic Speech Recognition: Chal-
(2017). Deep voice: Real-time neural text—to-speech. Proceedings of Ma- lenges for the New Millennium, Paris, France, September 18-20, 2000, pp.
chine Learning Research, 34th International Conference on Machine Learn- 195-202.
ing, Sydney, Australia, August 6-11, 2017, vol. 70, pp. 195-204. Iames, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An Introduction
Bach, N., Eck, M., Charoenpornsawat, P., Kiihler, T., Stiiker, S., Nguyen, T., to Statistical Learning. Springer-Verlag, New York, p. 204.
Hsiao, R., Waibel, A., Vogel, S., Schultz, T., and Black, A. W. (2007) The Iollitfe I. T. (2002). Principal Component Analysis, 2nd ed. Springer—Verlag,
CMU TransTac 2007 eyes-free and hands-free two-way speech-to-speech New York.
translation system. Proceedings of the International Workshop on Spoken Kawahara,H., Masuda-Katsuse, I., and de Cheveigne, A. (1999). Restructur-
Lunguage Translation 7. ing speech representations using a pitch-adaptive time frequency smooth-
Baur, C., Chua, C., Gerlach, I., Rayner, M., Russell, M., Strik, H., and Wei, ing and an instantaneous-frequency-based tn extraction: Possible role of
X. (2017) Overview of the 2017 spoken call shared task. Proceedings of the a repetitive structure in sounds. Speech Communication 27, 187-207.
7th International Speech Communication Association Workshop on Speech Lee, A. (2016). Language-Independent Methods for Computer—Assisted Pro-
and Language Technology in Education, Stockholm, Sweden, August 25- nunciation Training. PhD Thesis, Massachusetts Institute of Technology,
26, 2017, pp. 71-78. hrl'ps:// Cambridge, MA.
Bax, S. (2003). CALL—Past, present and future. System 31, 13-28. Lee, A., and Glass, I. (2013). Pronunciation assessment via a comparison-
Bernstein, I., and Cheng, J. (2007). Logic and validation of fully automatic based system. Proceedings of Speech and Language Technology in Educa-
spoken English test. In Holland, M., and Fisher, F. P. (Eds.), The Path of tion (SLaTE 2013), Grenoble, France, August 30 to September 1, 2013, pp.
Speech Technologies in Computer Assisted Language Learning: From Re- 122-126.
search Toward Practice. Routledge, Florence, KY, pp. 174-194. Lee, A., and Glass, I. (2015). Mispronunciation detection without nonna-
Bishop, C. (2006). Pattern Recognition and Machine Learning. Sprir1ger- tive training data. Proceedings of the 16th Annual Conference of the Inter-
Verlag, New York. national Speech Communication Association (Interspeech 2015), Dresden,
Chang, S., Shastri, L., and Greenberg, S. (2000) Automatic phonetic tran- Germany, September 6-10, 2015, pp. 643-647.
scription of spontaneous speech (American English). Proceedings of the Li, I., Cheng, K., Wang, S., Morstatter, F., Trevino, R. P., Tang, I., and Huan,
6th International Conference on Spoken Language Processing, Beijing, Chi- L. (2018) Feature selection: A data perspective. Association for Computing
na, October 16-20, 2000, vol 4, pp. 330-333. Machinery Computing Surveys 50(6), 94.
Chapelle, C. A., and Sauro, S. (Eds.). (2017). The Handbook of Technology and Lion, C.-Y., Cheng, VV.-C., Liou, ].-W, and Lion, D.-R. (2014). Autoencoder
Second Language Teaching and Learning Wiley-Blackwell. Hoboken, N]. for words. Neurocomputing 139, 84-96.
23 | Acauet-.i|:e Thdey ] Winter 2018

   26   27   28   29   30