Publications

Refine Results

(Filters Applied) Clear All

Advances in cross-lingual and cross-source audio-visual speaker recognition: The JHU-MIT system for NIST SRE21

Summary

We present a condensed description of the joint effort of JHUCLSP/HLTCOE, MIT-LL and AGH for NIST SRE21. NIST SRE21 consisted of speaker detection over multilingual conversational telephone speech (CTS) and audio from video (AfV). Besides the regular audio track, the evaluation also contains visual (face recognition) and multi-modal tracks. This evaluation exposes new challenges, including cross-source–i.e., CTS vs. AfV– and cross-language trials. Each speaker can speak two or three languages among English, Mandarin and Cantonese. For the audio track, we evaluated embeddings based on Res2Net and ECAPA-TDNN, where the former performed the best. We used PLDA based back-ends trained on previous SRE and VoxCeleb and adapted to a subset of Mandarin/Cantonese speakers. Some novel contributions of this submission are: the use of neural bandwidth extension (BWE) to reduce the mismatch between the AFV and CTS conditions; and invariant representation learning (IRL) to make the embeddings from a given speaker invariant to language. Res2Net with neural BWE was the best monolithic system. We used a pre-trained RetinaFace face detector and ArcFace embeddings for the visual track, following our NIST SRE19 work. We also included a new system using a deep pyramid single shot face detector and face embeddings trained on Crystal loss and probabilistic triplet loss, which performed the best. The number of face embeddings in the test video was reduced by agglomerative clustering or weighting the embedding based on the face detection confidence. Cosine scoring was used to compare embeddings. For the multi-modal track, we just added the calibrated likelihood ratios of the audio and visual conditions, assuming independence between modalities. The multi-modal fusion improved Cprimary by 72% w.r.t. audio.
READ LESS

Summary

We present a condensed description of the joint effort of JHUCLSP/HLTCOE, MIT-LL and AGH for NIST SRE21. NIST SRE21 consisted of speaker detection over multilingual conversational telephone speech (CTS) and audio from video (AfV). Besides the regular audio track, the evaluation also contains visual (face recognition) and multi-modal tracks. This...

READ MORE

Advances in speaker recognition for multilingual conversational telephone speech: the JHU-MIT system for NIST SRE20 CTS challenge

Published in:
Speaker and Language Recognition Workshop, Odyssey 2022, pp. 338-345.

Summary

We present a condensed description of the joint effort of JHUCLSP/HLTCOE and MIT-LL for NIST SRE20. NIST SRE20 CTS consisted of multilingual conversational telephone speech. The set of languages included in the evaluation was not provided, encouraging the participants to develop systems robust to any language. We evaluated x-vector architectures based on ResNet, squeeze-excitation ResNets, Transformers and EfficientNets. Though squeeze-excitation ResNets and EfficientNets provide superior performance in in-domain tasks like VoxCeleb, regular ResNet34 was more robust in the challenge scenario. On the contrary, squeeze-excitation networks over-fitted to the training data, mostly in English. We also proposed a novel PLDA mixture and k-NN PLDA back-ends to handle the multilingual trials. The former clusters the x-vector space expecting that each cluster will correspond to a language family. The latter trains a PLDA model adapted to each enrollment speaker using the nearest speakers–i.e., those with similar language/channel. The k-NN back-end improved Act. Cprimary (Cp) by 68% in SRE16-19 and 22% in SRE20 Progress w.r.t. a single adapted PLDA back-end. Our best single system achieved Act. Cp=0.110 in SRE20 progress. Meanwhile, our best fusion obtained Act. Cp=0.110 in the progress–8% better than single– and Cp=0.087 in the eval set.
READ LESS

Summary

We present a condensed description of the joint effort of JHUCLSP/HLTCOE and MIT-LL for NIST SRE20. NIST SRE20 CTS consisted of multilingual conversational telephone speech. The set of languages included in the evaluation was not provided, encouraging the participants to develop systems robust to any language. We evaluated x-vector architectures...

READ MORE

Quantifying bias in face verification system

Summary

Machine learning models perform face verification (FV) for a variety of highly consequential applications, such as biometric authentication, face identification, and surveillance. Many state-of-the-art FV systems suffer from unequal performance across demographic groups, which is commonly overlooked by evaluation measures that do not assess population-specific performance. Deployed systems with bias may result in serious harm against individuals or groups who experience underperformance. We explore several fairness definitions and metrics, attempting to quantify bias in Google’s FaceNet model. In addition to statistical fairness metrics, we analyze clustered face embeddings produced by the FV model. We link well-clustered embeddings (well-defined, dense clusters) for a demographic group to biased model performance against that group. We present the intuition that FV systems underperform on protected demographic groups because they are less sensitive to differences between features within those groups, as evidenced by clustered embeddings. We show how this performance discrepancy results from a combination of representation and aggregation bias.
READ LESS

Summary

Machine learning models perform face verification (FV) for a variety of highly consequential applications, such as biometric authentication, face identification, and surveillance. Many state-of-the-art FV systems suffer from unequal performance across demographic groups, which is commonly overlooked by evaluation measures that do not assess population-specific performance. Deployed systems with bias...

READ MORE

Bayesian estimation of PLDA with noisy training labels, with applications to speaker verification

Published in:
2020 IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, ICASSP, 4-8 May 2020.

Summary

This paper proposes a method for Bayesian estimation of probabilistic linear discriminant analysis (PLDA) when training labels are noisy. Label errors can be expected during e.g. large or distributed data collections, or for crowd-sourced data labeling. By interpreting true labels as latent random variables, the observed labels are modeled as outputs of a discrete memoryless channel, and the maximum a posteriori (MAP) estimate of the PLDA model is derived via Variational Bayes. The proposed framework can be used for PLDA estimation, PLDA domain adaptation, or to infer the reliability of a PLDA training list. Although presented as a general method, the paper discusses specific applications for speaker verification. When applied to the Speakers in the Wild (SITW) Task, the proposed method achieves graceful performance degradation when label errors are introduced into the training or domain adaptation lists. When applied to the NIST 2018 Speaker Recognition Evaluation (SRE18) Task, which includes adaptation data with noisy speaker labels, the proposed technique provides performance improvements relative to unsupervised domain adaptation.
READ LESS

Summary

This paper proposes a method for Bayesian estimation of probabilistic linear discriminant analysis (PLDA) when training labels are noisy. Label errors can be expected during e.g. large or distributed data collections, or for crowd-sourced data labeling. By interpreting true labels as latent random variables, the observed labels are modeled as...

READ MORE

The JHU-MIT System Description for NIST SRE19 AV

Summary

This document represents the SRE19 AV submission by the team composed of JHU-CLSP, JHU-HLTCOE and MIT Lincoln Labs. All the developed systems for the audio and videoconditions consisted of Neural network embeddings with some flavor of PLDA/cosine back-end. Primary fusions obtained Actual DCF of 0.250 on SRE18 VAST eval, 0.183 on SRE19 AV dev audio, 0.140 on SRE19 AV dev video and 0.054 on SRE19AV multi-modal.
READ LESS

Summary

This document represents the SRE19 AV submission by the team composed of JHU-CLSP, JHU-HLTCOE and MIT Lincoln Labs. All the developed systems for the audio and videoconditions consisted of Neural network embeddings with some flavor of PLDA/cosine back-end. Primary fusions obtained Actual DCF of 0.250 on SRE18 VAST eval, 0.183...

READ MORE

State-of-the-art speaker recognition for telephone and video speech: the JHU-MIT submission for NIST SRE18

Summary

We present a condensed description of the joint effort of JHUCLSP, JHU-HLTCOE, MIT-LL., MIT CSAIL and LSE-EPITA for NIST SRE18. All the developed systems consisted of xvector/i-vector embeddings with some flavor of PLDA backend. Very deep x-vector architectures–Extended and Factorized TDNN, and ResNets– clearly outperformed shallower xvectors and i-vectors. The systems were tailored to the video (VAST) or to the telephone (CMN2) condition. The VAST data was challenging, yielding 4 times worse performance than other video based datasets like Speakers in the Wild. We were able to calibrate the VAST data with very few development trials by using careful adaptation and score normalization methods. The VAST primary fusion yielded EER=10.18% and Cprimary= 0.431. By improving calibration in post-eval, we reached Cprimary=0.369. In CMN2, we used unsupervised SPLDA adaptation based on agglomerative clustering and score normalization to correct the domain shift between English and Tunisian Arabic models. The CMN2 primary fusion yielded EER=4.5% and Cprimary=0.313. Extended TDNN x-vector was the best single system obtaining EER=11.1% and Cprimary=0.452 in VAST; and 4.95% and 0.354 in CMN2.
READ LESS

Summary

We present a condensed description of the joint effort of JHUCLSP, JHU-HLTCOE, MIT-LL., MIT CSAIL and LSE-EPITA for NIST SRE18. All the developed systems consisted of xvector/i-vector embeddings with some flavor of PLDA backend. Very deep x-vector architectures–Extended and Factorized TDNN, and ResNets– clearly outperformed shallower xvectors and i-vectors. The...

READ MORE

Approaches for language identification in mismatched environments

Summary

In this paper, we consider the task of language identification in the context of mismatch conditions. Specifically, we address the issue of using unlabeled data in the domain of interest to improve the performance of a state-of-the-art system. The evaluation is performed on a 9-language set that includes data in both conversational telephone speech and narrowband broadcast speech. Multiple experiments are conducted to assess the performance of the system in this condition and a number of alternatives to ameliorate the drop in performance. The best system evaluated is based on deep neural network (DNN) bottleneck features using i-vectors utilizing a combination of all the approaches proposed in this work. The resulting system improved baseline DNN system performance by 30%.
READ LESS

Summary

In this paper, we consider the task of language identification in the context of mismatch conditions. Specifically, we address the issue of using unlabeled data in the domain of interest to improve the performance of a state-of-the-art system. The evaluation is performed on a 9-language set that includes data in...

READ MORE

I-vector speaker and language recognition system on Android

Published in:
HPEC 2016: IEEE Conf. on High Performance Extreme Computing, 13-15 September 2016.

Summary

I-Vector based speaker and language identification provides state of the art performance. However, this comes as a more computationally complex solution, which can often lead to challenges in resource-limited devices, such as phones or tablets. We present the implementation of an I-Vector speaker and language recognition system on the Android platform in the form of a fully functional application that allows speaker enrollment and language/speaker scoring within mobile contexts. We include a detailed account of the challenges to port the system and its dependencies, which were necessary to optimize matrix operations in the I-Vector implementation. The system was benchmarked on a for a Google Nexus 6, showing a speed increase of 61.68% in scoring and 82.63% in enrollment operations with the implemented optimizations. The application was tested in mobile settings on a Nexus 7 tablet with forty participants, showing a rough accuracy of 84%. The optimized platform showed the capacity to perform near real-time recognition within a mobile setting and showcases the viability of I-Vector systems on resource-limited environments.
READ LESS

Summary

I-Vector based speaker and language identification provides state of the art performance. However, this comes as a more computationally complex solution, which can often lead to challenges in resource-limited devices, such as phones or tablets. We present the implementation of an I-Vector speaker and language recognition system on the Android...

READ MORE

Corpora for the evaluation of robust speaker recognition systems

Published in:
INTERSPEECH 2016: 16th Annual Conf. of the Int. Speech Communication Assoc., 8-12 September 2016.

Summary

The goal of this paper is to describe significant corpora available to support speaker recognition research and evaluation, along with details about the corpora collection and design. We describe the attributes of high-quality speaker recognition corpora. Considerations of the application, domain, and performance metrics are also discussed. Additionally, a literature survey of corpora used in speaker recognition research over the last 10 years is presented. Finally we show the most common corpora used in the research community and review them on their success in enabling meaningful speaker recognition research.
READ LESS

Summary

The goal of this paper is to describe significant corpora available to support speaker recognition research and evaluation, along with details about the corpora collection and design. We describe the attributes of high-quality speaker recognition corpora. Considerations of the application, domain, and performance metrics are also discussed. Additionally, a literature...

READ MORE

The MITLL NIST LRE 2015 Language Recognition System

Summary

In this paper we describe the most recent MIT Lincoln Laboratory language recognition system developed for the NIST 2015 Language Recognition Evaluation (LRE). The submission features a fusion of five core classifiers, with most systems developed in the context of an i-vector framework. The 2015 evaluation presented new paradigms. First, the evaluation included fixed training and open training tracks for the first time; second, language classification performance was measured across 6 language clusters using 20 language classes instead of an N-way language task; and third, performance was measured across a nominal 3-30 second range. Results are presented for the overall performance across the six language clusters for both the fixed and open training tasks. On the 6-cluster metric the Lincoln system achieved overall costs of 0.173 and 0.168 for the fixed and open tasks respectively.
READ LESS

Summary

In this paper we describe the most recent MIT Lincoln Laboratory language recognition system developed for the NIST 2015 Language Recognition Evaluation (LRE). The submission features a fusion of five core classifiers, with most systems developed in the context of an i-vector framework. The 2015 evaluation presented new paradigms. First...

READ MORE