In this paper we investigate the use of deep neural networks (DNNs) for a small footprint text-dependent speaker verification task. At development stage, a DNN is trained to classify speakers at the frame-level. During speaker enrollment, the trained DNN is used to extract speaker specific features from the last hidden layer. The average of these speaker features, or d-vector, is taken as the speaker model. At evaluation stage, a d-vector is extracted for each utterance and compared to the enrolled speaker model to make a verification decision. Experimental results show the DNN based speaker verification system achieves good performance compared to a popular i-vector system on a small footprint text-dependent speaker verification task. In addition, the DNN based system is more robust to additive noise and outperforms the i-vector system at low False Rejection operating points. Finally the combined system outperforms the i-vector system by 14% and 25% relative in equal error rate (EER) for clean and noisy conditions respectively.

/pdf/deep-neural-networks-for-small-footprint-text-dependent-1otxqwx3q4.pdf

Deep neural networks for small footprint text-dependent speaker verification

http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Schuller11-RRE.pdf

Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge

Today's mobile phones represent a rich and powerful computing platform, given their sensing, processing and communication capabilities. Phones are also part of the everyday life of billions of people, and therefore represent an exceptionally suitable tool for conducting social and psychological experiments in an unobtrusive way.de the ability of sensing individual emotions as well as activities, verbal and proximity interactions among members of social groups. Moreover, the system is programmable by means of a declarative language that can be used to express adaptive rules to improve power saving. We evaluate a system prototype on Nokia Symbian phones by means of several small-scale experiments aimed at testing performance in terms of accuracy and power consumption. Finally, we present the results of real deployment where we study participants emotions and interactions. We cross-validate our measurements with the results obtained through questionnaires filled by the users, and the results presented in social psychological studies using traditional methods. In particular, we show how speakers and participants' emotions can be automatically detected by means of classifiers running locally on off-the-shelf mobile phones, and how speaking and interactions can be correlated with activity and location measures.

/pdf/emotionsense-a-mobile-phones-based-adaptive-platform-for-2ke6rn4ppf.pdf

EmotionSense: a mobile phones based adaptive platform for experimental social psychology research

The ASVspoof initiative was created to promote the development of countermeasures which aim to protect automatic speaker verification (ASV) from spoofing attacks. The first community-led, common evaluation held in 2015 focused on countermeasures for speech synthesis and voice conversion spoofing attacks. Arguably, however, it is replay attacks which pose the greatest threat. Such attacks involve the replay of recordings collected from enrolled speakers in order to provoke false alarms and can be mounted with greater ease using everyday consumer devices. ASVspoof 2017, the second in the series, hence focused on the development of replay attack countermeasures. This paper describes the database, protocols and initial findings. The evaluation entailed highly heterogeneous acoustic recording and replay conditions which increased the equal error rate (EER) of a baseline ASV system from 1.76% to 31.46%. Submissions were received from 49 research teams, 20 of which improved upon a baseline replay spoofing detector EER of 24.77%, in terms of replay/non-replay discrimination. While largely successful, the evaluation indicates that the quest for countermeasures which are resilient in the face of variable replay attacks remains very much alive.

The ASVspoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection

http://cs.uef.fi/pages/tkinnu/webpage/pdf/spoofingsurvey2014_SPCOM.pdf

Spoofing and countermeasures for speaker verification

This paper describes data collection efforts conducted as part of the RedDots project which is dedicated to the study of speaker recognition under conditions where test utterances are of short duration and of variable phonetic content. At the current stage, we focus on English speakers, both native and non-native, recruited worldwide. This is made possible through the use of a recording front-end consisting of an application running on mobile devices communicating with a centralized web server at the back-end. Speech recordings are collected by having speakers read text prompts displayed on the screen of the mobile devices. We aim to collect a large number of sessions from each speaker over a long time span, typically one session per week over a one year period. The corpus is expected to include rich inter-speaker and intra-speaker variations, both intrinsic and extrinsic (that is, due to recording channel and acoustic environment).

https://hal.archives-ouvertes.fr/hal-01818427/document

The RedDots Data Collection for Speaker Recognition

In this paper, we apply and enhance the i-vector-PLDA paradigm to text-dependent speaker recognition. Due to its origin in text-independent speaker recognition, this paradigm does not make use of the phonetic content of each utterance. Moreover, the uncertainty in the i-vector estimates should be taken into account in the PLDA model, due to the short duration of the utterances. To bridge this gap, a phrase-dependent PLDA model with uncertainty propagation is introduced. We examined it on the RSR-2015 dataset and we show that despite its low channel variability, improved results over the GMM-UBM model are attained.

Text-dependent speaker recognition using PLDA with uncertainty propagation

This paper describes Brno University of Technology (BUT) system for the Interspeech 2009 Emotion Challenge. Our submitted system for the Open Performance Sub-Challenge uses acoustic frame based features as a front-end and Gaussian Mixture Models as a back-end. Different feature types and modeling approaches successfully applied in speakerand language recognition are investigated and we can achieve an 16% and 9% relative improvement over the best dynamic and static baseline system on the 5-class task, respectively.

http://noel.feld.cvut.cz/gacr0811/publ/KOC09.pdf

Brno University of Technology system for Interspeech 2009 emotion challenge.

http://noel.feld.cvut.cz/gacr0811/publ/KOC11.pdf

Application of speaker- and language identification state-of-the-art techniques for emotion recognition

This paper addresses a novel technique for representation and processing of n-gram counts in phonotactic language recognition (LRE): subspace multinomial modelling represents the vectors of n-gram counts by low dimensional vectors of coordinates in total variability subspace, called iVector Two techniques for iVector scoring are tested: support vector machines (SVM), and logistic regression (LR) Using standard NIST LRE 2009 task as our evaluation set, the latter scoring approach was shown to outperform phonotactic LRE system based on direct SVM classification of n-gram count vectors The proposed iVector paradigm also shows comparable results to previously proposed PCA-based phonotactic feature extraction Index Terms: language recognition, subspace modeling, multinomial distribution

/pdf/ivector-approach-to-phonotactic-language-recognition-3y8fwvkkpp.pdf

Marcel Kockmann

Papers

The RedDots Data Collection for Speaker Recognition

Text-dependent speaker recognition using PLDA with uncertainty propagation

Brno University of Technology system for Interspeech 2009 emotion challenge.

Application of speaker- and language identification state-of-the-art techniques for emotion recognition

iVector Approach to Phonotactic Language Recognition