Abstract
In this paper we propose a new method of speaker diarization that employs a deep learning architecture to learn speaker embeddings. In contrast to the traditional approaches that build their speaker embeddings using manually hand-crafted spectral features, we propose to train for this purpose a recurrent convolutional neural network applied directly on magnitude spectrograms. To compare our approach with the state of the art, we collect and release for the public an additional dataset of over 6 h of fully annotated broadcast material. The results of our evaluation on the new dataset and three other benchmark datasets show that our proposed method significantly outperforms the competitors and reduces diarization error rate by a large margin of over 30% with respect to the baseline.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Miro, X.A., Bozonnet, S., Evans, N.W.D., Fredouille, C., Friedland, G., Vinyals, O.: Speaker diarization: a review of recent research. IEEE Trans. Audio Speech Lang. Process. 20(2), 356–370 (2012)
Gupta, V., Kenny, P., Ouellet, P., Stafylakis, T.: I-vector-based speaker adaptation of deep neural networks for French broadcast audio transcription. In: ICASSP (2014)
Liu, Y., Tian, Y., He, L., Liu, J.: Investigating various diarization algorithms for speaker in the wild (SITW) speaker recognition challenge. In: Interspeech (2016)
Le Lan, G., Meignier, S., Charlet, D., Deleglise, P.: Speaker diarization with unsupervised training framework. In: ICASSP (2016)
Woubie, A., Luque, J., Hernando, J.: Short-and long-term speech features for hybrid hmm-i-vector based speaker diarization system. In: Odyssey (2016)
Bredin, H., Gelly, G.: Improving speaker diarization of tv series using talking-face detection and clustering. In: ACM on Multimedia Conference (2016)
Xu, Y., McLoughlin, I., Song, Y., Wu, K.: Improved i-vector representation for speaker diarization. Circ. Syst. Sig. Process. 35(9), 3393–3404 (2016)
Ferras, M., Madikeri, S., Motlicek, P., Bourlard, H.: Systemfusion and speaker linking for longitudinal diarization of tv shows. In: ICASSP (2016)
Mermelstein, P.: Distance measures for speech recognition, psychological and instrumental. Pattern Recog. Artif. Intell. 116, 374–388 (1976)
Hermansky, H.: Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 87(4), 1738–1752 (1990)
Hermansky, H., Morgan, N.: Rasta processing of speech. IEEE Trans. Audio Speech Lang. Process. 2(4), 578–589 (1994)
Sainath, T.N., Kingsbury, B., Mohamed, A., Ramabhadran, B.: Learning filter banks within a deep neural network framework. In: Workshop on Automatic Speech Recognition and Understanding (2013)
Zhu, Z., Engel, J.H., Hannun, A.Y.: Learning multiscale features directly from waveforms. In: Interspeech (2016)
Hoshen, Y., Weiss, R.J., Wilson, K.W.: Speecha coustic modeling from raw multi channel waveforms. In: ICASSP (2015)
Palaz, D., Magimai-Doss, M., Collobert, R.: Analysis of CNN-based speech recognition system using raw speech as input. In: Interspeech (2015)
Lukic, Y., Vogt, C., Dürr, O., Stadelmann, T.: Speaker identification and clustering using convolutional neural networks. In: International Workshop on Machine Learning for Signal Processing (MLSP) (2016)
Zuo, Z., Shuai, B., Wang, G., Liu, X., Wang, X., Wang, B., Chen, Y.: Convolutional recurrent neural networks: learning spatial dependencies for image representation. In: CVPR (2015)
Cakir, E., Adavanne, S., Parascandolo, G., Drossos, K., Virtanen, T.: Convolutional recurrent neural networks for bird audio detection. In: ICASSP (2017)
Snyder, D., Ghahremani, P., Povey, D., Garcia-Romero, D., Carmiel, Y., Khudanpur, S.: Deep neural network-based speaker embeddings for end-to-end speaker verification. In: IEEE Spoken Language Technology Workshop (2016)
Yella, S.H.: Speaker diarization of spontaneous meeting room conversations. Ph.D. dissertation, Ecole Polytechnique Federale de Lausanne (2015)
Sell, G., Garcia-Romero, D.: Speaker diarization with plda i-vector scoring and unsupervised calibration. In: 2014 IEEE Spoken Language Technology Workshop (2014)
Vesnicer, B., Zganec-Gros, J., Dobrisek, S., Struc, V.: Incorporating duration information into i-vector-based speaker recognition systems. In: Odyssey: The Speaker and Language Recognition Workshop, pp. 241–248 (2014)
Mami, Y., Charlet, D.: Speaker identification by location in an optimal space of anchor models. In: Interspeech (2002)
Rouvier, M., Bousquet, P., Favre, B.: Speaker diarization through speaker embeddings. In: 23rd European Signal Process- ing Conference, EUSIPCO (2015)
Bredin, H.: Tristounet: triplet loss for speaker turn embedding. CoRR, abs/1609.04301 (2016)
Garcia-Romero, D., Snyder, D., Sell, G., Povey, D., McCree, A.: Speaker diarization using deep neural networks. In: ICASSP (2017)
Trigeorgis, G., Ringeval, F., Brueckner, R., Marchi, E., Nicolaou, M.A., Schuller, B., Zafeiriou, S.: Adieu features? end-to-end speech emotion recognition using a deep convolutional recurrent network. In: ICASSP (2016)
Tang, D., Qin, B., Liu, T.: Document modeling with gated recurrent neural network for sentiment classification. In: EMNLP (2015)
Choi, K., Fazekas, G., Sandler, M., Cho, K.: Convolutional recurrent neural networks for music classification. arXiv preprint arXiv:1609.04243 (2016)
Ghahremani, P., Manohar, V., Povey, D., Khudanpur, S.: Acoustic modelling from the signal domain using CNNs. In: Interspeech 2016 (2016)
Dieleman, S., Schrauwen, B.: End-to-end learning for music audio. In: ICASSP (2014)
Patterson, R., Nimmo-Smith, I., Holdsworth, J., Rice, P.: An efficient auditory filterbank based on the gammatone function. A meeting of the IOC Speech Group on Auditory Modelling at RSRE, vol. 2(7) (1987)
Brown, J.C.: Calculation of a constantq spectral transform. J. Acoust. Soc. Am. 89(1), 425–434 (1991)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR, abs/1502.03167 (2015)
Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR, abs/1412.3555 (2014)
Clevert, D., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). CoRR, abs/1511.07289 (2015)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors. CoRR, abs/1207.0580 (2012)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR, abs/1412.6980 (2014)
Carletta, J., Ashby, S., Bourban, S., Flynn, M., Guillemot, M., Hain, T., Kadlec, J., Karaiskos, V., Kraaij, W., Kronenthal, M., Lathoud, G., Lincoln, M., Lisowska, A., McCowan, I., Post, W., Reidsma, D., Wellner, P.: The ami meeting corpus: a pre-announcement. In: MLMI (2006)
Janin, A., Baron, D., Edwards, J., Ellis, D., Gelbart, D., Morgan, N., Peskin, B., Pfau, T., Shriberg, E., Stolcke, A., Wooters, C.: The ICSI meeting corpus, pp. 364–367 (2003)
Schmidt, L., Sharifi, M., Moreno, I.L.: Large-scale speaker identification. In ICASSP (2014)
Chollet, F.: Keras (2015). https://github.com/fchollet/keras
Al-Rfou, R., et. al.: Theano: a python framework for fast computation of mathematical expressions. CoRR, abs/1605.02688 (2016)
Meignier, S., Merlin, T.: Lium spkdiarization: an open source toolkit for diarization. In: CMU SPUD Workshop (2010)
Hershey, J.R., Chen, Z., Roux, J.L., Watanabe, S.: Deep clustering: discriminative embeddings for segmentation and separation. In: ICASSP (2016)
Acknowledgment
The authors would like to thank NowThisMedia Inc. for enabling this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Cyrta, P., Trzciński, T., Stokowiec, W. (2018). Speaker Diarization Using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings. In: Borzemski, L., Świątek, J., Wilimowska, Z. (eds) Information Systems Architecture and Technology: Proceedings of 38th International Conference on Information Systems Architecture and Technology – ISAT 2017. ISAT 2017. Advances in Intelligent Systems and Computing, vol 655. Springer, Cham. https://doi.org/10.1007/978-3-319-67220-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-67220-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67219-9
Online ISBN: 978-3-319-67220-5
eBook Packages: EngineeringEngineering (R0)