A unified deep neural network for speaker and language recognition

Keywords

Computer science, Speech recognition, NIST, Speaker recognition, Word error rate

References

• Bottleneck features for speaker recognitionSibel Yaman, Jason Pelecanos, Ruhi Sarikaya — 2012
• The Kaldi Speech Recognition ToolkitDaniel Povey — 2011
• Improving speaker recognition performance in the domain adaptation challenge using deep neural networksDaniel Garcia-Romero, Xiaohui Zhang, Alan McCree — 2014
• A novel scheme for speaker recognition using a phonetically-aware deep neural networkYun Lei, Nicolas Scheffer, Luciana Ferrer — 2014
• Automatic language identification using deep neural networksIgnacio López Moreno, Javier Gónzalez-Domínguez, Oldřich Plchot — 2014
• Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targetsTara N. Sainath, Brian Kingsbury, Vikas Sindhwani — 2013
• Inter dataset variability compensation for speaker recognitionHagai Aronowitz — 2014
• Convolutive Bottleneck Network features for LVCSRKarel Veselý, Martin Karafiát, František Grézl — 2011
• Domain adaptation via within-class covariance correction in I-vector based speaker recognition systemsOndřej Glembek, Jeff Ma, Pavel Matějka — 2014
• Extracting deep neural network bottleneck features using low-rank matrix factorizationYu Zhang, Ekapol Chuangsuwanich, James Glass — 2014
• New types of deep neural network learning for speech recognition and related applications: an overviewLi Deng, Geoffrey E. Hinton, Brian Kingsbury — 2013
• Combination of Cepstral and Phonetically Discriminative Features for Speaker VerificationAchintya Kumar Sarkar, Cong-Thanh Do, Viet-Bac Le — 2014
• Front-End Factor Analysis for Speaker VerificationNajim Dehak, Patrick Kenny, Réda Dehak — 2011
• i-vector representation based on bottleneck features for language identificationYan Song, Bing Jiang, Yebo Bao — 2013
• Tandem connectionist feature extraction for conventional HMM systemsHynek Heřmanský, Dan Ellis, Sanjay Sharma — 2000
• SWITCHBOARD: telephone speech corpus for research and developmentJ. Godfrey, E. Holliman, J. McDaniel — 1992
• i-Vector Modeling with Deep Belief Networks for Multi-Session Speaker RecognitionOmid Ghahabi, Javier Hernando — 2014
• Unsupervised Clustering Approaches for Domain Adaptation in Speaker Recognition SystemsAlan McCree, Stephen Shum, Douglas R. Reynolds — 2014
• Deep Neural Networks for extracting Baum-Welch statistics for Speaker RecognitionPatrick Kenny, Themos Stafylakis, Pierre Ouellet — 2014
• Application of Convolutional Neural Networks to Language Identification in Noisy ConditionsYun Lei, Luciana Ferrer, Aaron Lawson — 2014

Cited by

• Automatic Dialect Detection in Arabic Broadcast SpeechAhmed Ali, Najim Dehak, Patrick Cardinal — 2015
• Deep Learning Backend for Single and Multisession i-Vector Speaker RecognitionOmid Ghahabi, Javier Hernando — 2015
• The IBM Speaker Recognition System: Recent Advances and Error AnalysisSeyed Omid Sadjadi, Jason Pelecanos, Sriram Ganapathy — 2016
• On the use of deep feedforward neural networks for automatic language identificationIgnacio López Moreno, Javier Gónzalez-Domínguez, David Martínez — 2016
• A phonetically aware system for speech activity detectionLuciana Ferrer, Martin Graciarena, Vikramjit Mitra — 2016
• Advanced b-vector system based deep neural network as classifier for speaker verificationHee-Soo Heo, IL-Ho Yang, Myung-Jae Kim — 2016
• Cross-acoustic transfer learning for sound event classificationHyungjun Lim, Myung Jong Kim, Hoirin Kim — 2016
• Analysis of DNN approaches to speaker identificationPavel Matějka, Ondřej Glembek, Ondřej Novotný — 2016
• Exploring the role of phonetic bottleneck features for speaker and language recognitionMitchell McLaren, Luciana Ferrer, Aaron Lawson — 2016
• On the Use of Acoustic Unit Discovery for Language RecognitionStephen Shum, David Harwath, Najim Dehak — 2016
• Optimisation de la consommation énergétique d'une ligne de métro automatique prenant en compte les aléas de trafic à l'aide d'outils d'intelligence artificielleJonathan Lesel — 2016
• Domain compensation based on phonetically discriminative features for speaker verificationYanhua Long, Hong Ye, Jifeng Ni — 2017
• Spoofing Detection on the ASVspoof2015 Challenge Corpus Employing Deep Neural NetworksJahangir Alam, Patrick Kenny, Vishwa Gupta — 2016
• LID-senone Extraction via Deep Neural Networks for End-to-End Language IdentificationJin Ma, Yan Song, Ian McLoughlin — 2016
• Analysis and Optimization of Bottleneck Features for Speaker RecognitionAlicia Lozano-Díez, Anna Silnova, Pavel Matějka — 2016
• I-vector transformation and scaling for PLDA based speaker recognitionSandro Cumani, Pietro Laface — 2016
• Deep Language: a comprehensive deep learning approach to end-to-end language recognitionTrung Ngô Trọng, Ville Hautamäki, Kong Aik Lee — 2016
• Deep Neural Networks and Hidden Markov Models in i-vector-based Text-Dependent Speaker VerificationHossein Zeinali, Lukáš Burget, Hossein Sameti — 2016
• Identification of British English regional accents using fusion of i-vector and multi-accent phonotactic systemsMaryam Najafian, Saeid Safavi, Philip Weber — 2016
• Noise and Metadata Sensitive Bottleneck Features for Improving Speaker Recognition with Non-Native Speech InputYao Qian, Jidong Tao, David Suendermann‐Oeft — 2016

Related papers

• Front-End Factor Analysis for Speaker VerificationNajim Dehak, Patrick Kenny, Réda Dehak — 2011
• A novel scheme for speaker recognition using a phonetically-aware deep neural networkYun Lei, Nicolas Scheffer, Luciana Ferrer — 2014
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsGeoffrey E. Hinton, Li Deng, Dong Yu — 2012
• Deep Neural Networks for extracting Baum-Welch statistics for Speaker RecognitionPatrick Kenny, Themos Stafylakis, Pierre Ouellet — 2014
• Deep Neural Network Approaches to Speaker and Language RecognitionFred Richardson, Douglas A. Reynolds, Najim Dehak — 2015
• Deep neural networks for small footprint text-dependent speaker verificationEhsan Variani, Xin Lei, Erik McDermott — 2014
• The Kaldi Speech Recognition ToolkitDaniel Povey — 2011
• Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionGeorge E. Dahl, Dong Yu, Li Deng — 2012
• Automatic language identification using deep neural networksIgnacio López Moreno, Javier Gónzalez-Domínguez, Oldřich Plchot — 2014
• Speaker Verification Using Adapted Gaussian Mixture ModelsDouglas A. Reynolds, Thomas F. Quatieri, R.B. Dunn — 2000