Abstract:
Using bottleneck features extracted from a deep neural network (DNN) trained to predict senone posteriors has resulted in new, state-of-the-art technology for language and speaker identification. For language identification, the features' dense phonetic information is believed to enable improved performance by better representing language-dependent phone distributions. For speaker recognition, the role of these features is less clear, given that a bottleneck layer near the DNN output layer is thought to contain limited speaker information. In this article, we analyze the role of bottleneck features in these identification tasks by varying the DNN layer from which they are extracted, under the hypothesis that speaker information is traded for dense phonetic information as the layer moves toward the DNN output layer. Experiments support this hypothesis under certain conditions, and highlight the benefit of using a bottleneck layer close to the DNN output layer when DNN training data is matched to the evaluation conditions, and a layer more central to the DNN otherwise. © 2016 IEEE.
Registro:
Documento: |
Conferencia
|
Título: | Exploring the role of phonetic bottleneck features for speaker and language recognition |
Autor: | McLaren, M.; Ferrer, L.; Lawson, A.; The Institute of Electrical and Electronics Engineers Signal Processing Society |
Filiación: | Speech Technology and Research Laboratory, SRI InternationalCA, United States Departamento de Computación, FCEN, Universidad de Buenos Aires and CONICET, Argentina
|
Palabras clave: | Bottleneck Features; Deep Neural Networks; Language Recognition; Speaker Recognition |
Año: | 2016
|
Volumen: | 2016-May
|
Página de inicio: | 5575
|
Página de fin: | 5579
|
DOI: |
http://dx.doi.org/10.1109/ICASSP.2016.7472744 |
Título revista: | 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
|
Título revista abreviado: | ICASSP IEEE Int Conf Acoust Speech Signal Process Proc
|
ISSN: | 15206149
|
CODEN: | IPROD
|
Registro: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_15206149_v2016-May_n_p5575_McLaren |
Referencias:
- Lei, Y., Scheffer, N., Ferrer, L., McLaren, M., A novel scheme for speaker recognition using a phonetically aware deep neural network (2014) Proc. ICASSP
- Ferrer, L., Lei, Y., McLaren, M., Study of senone-based deep neural network approaches for spoken language recognition (2015) Submitted to IEEE Trans. Audio Speech and Language Processing
- Richardson, F., Reynolds, D., Dehak, N., A unified deep neural network for speaker and language recognition (2015) Proc. Interspeech
- McLaren, M., Lei, Y., Ferrer, L., Advances in deep neural network approaches to speaker recognition (2015) Proc. IEEE ICASSP
- Ferrer, L., Lei, Y., McLaren, M., Scheffer, N., Language identification based on senone posteriors (2014) Proc. Interspeech
- Song, Y., Jiang, B., Bao, Y., Wei, S., Dai, L., I-Vector representation based on bottleneck features for language identification (2013) Electronics Letters, 49 (24), pp. 1569-1570
- Matejka, P., Zhang, L., Ng, T., Mallidi, S.H., Glembek, O., Ma, J., Zhang, B., Neural network bottleneck features for language identification (2014) Proc. Speaker Odyssey
- Lei, Y., Ferrer, L., Lawson, A., McLaren, M., Scheffer, N., Application of convolutional neural networks to language identification in noisy conditions (2014) Proc. Speaker Odyssey
- Matejka, P., Schwarz, P., Cernocky, J., Chytil, P., Phonotactic language identification using high-quality phoneme recognition (2005) Proc Interspeech
- Shen, W., Campbell, W., Gleason, T., Reynolds, D., Singer, E., Experiments with lattice-based PPRLM language identification (2006) Proc. Odyssey
- Stolcke, A., Akbacak, M., Ferrer, L., Kajarekar, S., Richey, C., Scheffer, N., Shriberg, E., Improving language recognition with multilingual phone recognition and speaker adaptation transforms (2010) Proc. Odyssey
- Fernando D'Haro Enŕquez, L., Glembek, O., Plchot, O., Matejka, P., Soufifar, M., De Córdoba Herralde, R., Ernockỳ, J.C., Phonotactic language recognition using i-vectors and phoneme posteriogram counts (2012) Proc. Interspeech
- Penagarikano, M., Varona, A., Diez, M., Rodriguez-Fuentes, L.J., Bordel, G., Study of different backends in a state-of-the-art language recognition system (2012) Proc. Interspeech
- 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
- Ferrer, L., Bratt, H., Burget, L., Cernocky, H., Glembek, O., Graciarena, M., Lawson, A., Scheffer, N., Promoting robustness for speaker modeling in the community: The PRISM evaluation set (2011) Proc. NIST 2011 Workshop
- Lei, Y., Burget, L., Ferrer, L., Graciarena, M., Scheffer, N., Towards noise-robust speaker recognition using probabilistic linear discriminant analysis (2012) Proc. ICASSP, pp. 4253-4256
- Larcher, A., Lee, K., Ma, B., Li, H., RSR2015: Database for text-dependent speaker verification using multiple pass-phrases (2012) Proc. Interspeech
- McLaren, M., Lawson, A., Ferrer, L., Scheffer, N., Lei, Trial-based calibration for speaker recognition in unseen conditions (2014) Odyssey 2014: The Speaker and Language Recognition Workshop
- (2009) The 2009 NIST Language Recognition Evaluation Plan, , http://www.itl.nist.gov/iad/mig/tests/lre/2009/
- Lawson, A., McLaren, M., Lei, Y., Mitra, V., Scheffer, N., Ferrer, L., Graciarena, M., Improving language identification robustness to highly channel-degraded speech through multiple system fusion (2013) Proc. Interspeech
- Walker, K., Strassel, S., The rats radio traffic collection system (2012) Proc. Odyssey
- Stafylakis, T., Kenny, P., Ouellet, P., Perez, J., Kockmann, M., Dumouchel, P., Text-dependent speaker recognition using PLDA with uncertainty propagation (2013) Proc. Interspeech, p. 36843688A4 - The Institute of Electrical and Electronics Engineers Signal Processing Society
Citas:
---------- APA ----------
McLaren, M., Ferrer, L., Lawson, A. & The Institute of Electrical and Electronics Engineers Signal Processing Society
(2016)
. Exploring the role of phonetic bottleneck features for speaker and language recognition. 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, 2016-May, 5575-5579.
http://dx.doi.org/10.1109/ICASSP.2016.7472744---------- CHICAGO ----------
McLaren, M., Ferrer, L., Lawson, A., The Institute of Electrical and Electronics Engineers Signal Processing Society
"Exploring the role of phonetic bottleneck features for speaker and language recognition"
. 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 2016-May
(2016) : 5575-5579.
http://dx.doi.org/10.1109/ICASSP.2016.7472744---------- MLA ----------
McLaren, M., Ferrer, L., Lawson, A., The Institute of Electrical and Electronics Engineers Signal Processing Society
"Exploring the role of phonetic bottleneck features for speaker and language recognition"
. 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, vol. 2016-May, 2016, pp. 5575-5579.
http://dx.doi.org/10.1109/ICASSP.2016.7472744---------- VANCOUVER ----------
McLaren, M., Ferrer, L., Lawson, A., The Institute of Electrical and Electronics Engineers Signal Processing Society Exploring the role of phonetic bottleneck features for speaker and language recognition. ICASSP IEEE Int Conf Acoust Speech Signal Process Proc. 2016;2016-May:5575-5579.
http://dx.doi.org/10.1109/ICASSP.2016.7472744