Conferencia
Abstract:
To date, automatic spoken language detection research has largely been based on a closed-set paradigm, in which the languages to be detected are known prior to system application. In actual practice, such systems may face previously unseen languages (out-of-set (OOS) languages) which should be rejected, a common problem that has received limited attention from the research community. In this paper, we focus on situations in which either (1) the system-modeled languages are not observed during use or (2) the test data contains OOS languages that are unseen during modeling or calibration. In these situations, the common multi-class objective function for calibration of language-detection scores is problematic. We describe how the assumptions of multi-class calibration are not always fulfilled in a practical sense and explore applying global and language-dependent binary objective functions to relax system constraints. We contrast the benefits and sensitivities of the calibration approaches on practical scenarios by presenting results using both LRE09 data and 14 languages from the BABEL dataset. We show that the global binary approach is less sensitive to the characteristics of the training data and that OOS modeling with individual detectors is the best option when OOS test languages are not known to the system. Copyright © 2017 ISCA.
Registro:
| Documento: | Conferencia |
| Título: | Calibration approaches for language detection |
| Autor: | McLaren, M.; Ferrer, L.; Castan, D.; Lawson, A.; Lacerda F.; Strombergsson S.; Wlodarczak M.; Heldner M.; Gustafson J.; House D. |
| Filiación: | Speech Technology and Research (STAR) Laboratory, SRI International, Menlo Park, United States Instituto de Investigación en Ciencias de la Computación (ICC), CONICET-UBA, Argentina |
| Palabras clave: | Bins; Calibration; Speech communication; Speech recognition; Language detection; Limited attentions; Objective functions; Research communities; Spoken languages; System applications; System constraints; Training data; Modeling languages |
| Año: | 2017 |
| Volumen: | 2017-August |
| Página de inicio: | 2804 |
| Página de fin: | 2808 |
| DOI: | http://dx.doi.org/10.21437/Interspeech.2017-530 |
| Título revista: | 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 |
| Título revista abreviado: | Proc. Annu. Conf. Int. Speech. Commun. Assoc., INTERSPEECH |
| ISSN: | 2308457X |
| Registro: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_2308457X_v2017-August_n_p2804_McLaren |
Referencias:
- Robust Automatic Transcription of Speech (RATS), , http://www.darpa.mil/program/robust-atuomatic-transcription-of-speech
- Brummer, N., Van Leeuwen, D., On calibration of language recognition scores (2006) Odyssey: Speaker and Language Recognition Workshop, pp. 1-8
- Matejka, P., Zhang, L., Ng, T., Mallidi, S., Glembek, O., Ma, J., Zhang, B., Neural network bottleneck features for language identification (2014) Proc. Speaker Odyssey
- Ferrer, L., Lei, Y., McLaren, M., Scheffer, N., Study of senone-based deep neural network approaches for spoken language recognition (2015) IEEE Transactions on Acoustics Speech and Signal Processing, , accepted for publication
- Fér, R., Matějka, P., Grézl, F., Plchot, O., Černockỳ, J., Multilingual bottleneck features for language recognition (2015) Sixteenth Annual Conference of the International Speech Communication Association
- McLaren, M., Ferrer, L., Lawson, A., Exploring the role of phonetic bottleneck features for speaker and language recognition (2016) Proc. ICASSP
- Richardson, F., Reynolds, D., Dehak, N., A unified deep neural network for speaker and language recognition (2015) Proc. Interspeech
- Brümmer, N., Du Preez, J., Application-independent evaluation of speaker detection (2006) Computer Speech & Language, 20 (2), pp. 230-275
- (2009) The 2009 NIST Language Recognition Evaluation Plan, , http://www.itl.nist.gov/iad/mig/tests/lre/2009
- (2015) The 2015 NIST Language Recognition Evaluation Plan, , http://www.nist.gov/itl/iad/mig/upload/LRE15EvalPlanv23.pdf
- Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P., Front-end factor analysis for speaker verification (2011) IEEE Trans. on Speech and Audio Processing, 19, pp. 788-798
- Singer, E., Torres-Carrasquillo, P.A., Gleason, T.P., Campbell, W.M., Reynolds, D.A., Acoustic, phonetic, and discriminative approaches to automatic language identification (2003) Proc. Interspeech
- McLaren, M., Lawson, A., Lei, Y., Scheffer, N., Adaptive Gaussian backend for robust language identification (2013) Proc. Interspeech, pp. 84-88
- Brummer, N., Burget, L., Glembek, O., Hubeika, V., Jancik, Z., Karafiát, M., Matejka, P., Strasheim, A., But-agnitio system description for nist language recognition evaluation 2009 (2009) Proceedings NIST 2009 Language Recognition Evaluation Workshop, pp. 1-7
- (2016) The NIST Year 2016 Speaker Recognition Evaluation Plan, , https://www.nist.gov/sites/default/files/documents/2016/10/07/sre16evalplanv1.3.pdfA4 - Amazon Alexa; Apple; DiDi; et al.; Furhat Robotics; Microsoft
Citas:
---------- APA ----------
McLaren, M., Ferrer, L., Castan, D., Lawson, A., Lacerda F., Strombergsson S., Wlodarczak M.,..., House D. (2017) . Calibration approaches for language detection. 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017, 2017-August, 2804-2808.http://dx.doi.org/10.21437/Interspeech.2017-530
---------- CHICAGO ----------
McLaren, M., Ferrer, L., Castan, D., Lawson, A., Lacerda F., Strombergsson S., et al. "Calibration approaches for language detection" . 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 2017-August (2017) : 2804-2808.http://dx.doi.org/10.21437/Interspeech.2017-530
---------- MLA ----------
McLaren, M., Ferrer, L., Castan, D., Lawson, A., Lacerda F., Strombergsson S., et al. "Calibration approaches for language detection" . 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017, vol. 2017-August, 2017, pp. 2804-2808.http://dx.doi.org/10.21437/Interspeech.2017-530
---------- VANCOUVER ----------
McLaren, M., Ferrer, L., Castan, D., Lawson, A., Lacerda F., Strombergsson S., et al. Calibration approaches for language detection. Proc. Annu. Conf. Int. Speech. Commun. Assoc., INTERSPEECH. 2017;2017-August:2804-2808.http://dx.doi.org/10.21437/Interspeech.2017-530
