Search

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.

We present a thorough analysis of the systems developed by the JHU-MIT consortium in the context of NIST speaker recognition evaluation 2018. In the previous NIST evaluation, in 2016, i-vectors were the speaker recognition state-of-the-art. However now, neural network embeddings (a.k.a. x-vectors) rise as the best performing approach. We show that in some conditions, x-vectors’ detection error reduces by 2 w.r.t. i-vectors. In this work, we experimented on the Speakers In The Wild evaluation (SITW), NIST SRE18 VAST (Video Annotation for Speech Technology), and SRE18 CMN2 (Call My Net 2, telephone Tunisian Arabic) to compare network architectures, pooling layers, training objectives, back-end adaptation methods, and calibration techniques. x-Vectors based on factorized and extended TDNN networks achieved performance without parallel on SITW and CMN2 data. However for VAST, performance was significantly worse than for SITW. We noted that the VAST audio quality was severely degraded compared to the SITW, even though they both consist of Internet videos. This degradation caused strong domain mismatch between training and VAST data. Due to this mismatch, large networks performed just slightly better than smaller networks. This also complicated VAST calibration. However, we managed to calibrate VAST by adapting SITW scores distribution to VAST, using a small amount of in-domain development data. Regarding pooling methods, learnable dictionary encoder performed the best. This suggests that representations learned by x-vector encoders are multi-modal. Maximum margin losses were better than cross-entropy for in-domain data but not in VAST mismatched data. We also analyzed back-end adaptation methods in CMN2. PLDA semi-supervised adaptation and adaptive score normalization (AS-Norm) yielded significant improvements. However, results were still worse than in English in-domain conditions like SITW. We conclude that x-vectors have become the new state-of-the-art in speaker recognition. However, their advantages reduce in cases of strong domain mismatch. We need to investigate domain adaptation and domain invariant training approaches to improve performance in all conditions. Also, speech enhancement techniques with a focus on improving the speaker recognition performance could be of great help.

Support vector machines (SVMs) have proven to be a powerful technique for pattern classification. SVMs map inputs into a high-dimensional space and then separate classes with a hyperplane. A critical aspect of using SVMs successfully is the design of the inner product, the kernel, induced by the high dimensional mapping. We consider the application of SVMs to speaker and language recognition. A key part of our approach is the use of a kernel that compares sequences of feature vectors and produces a measure of similarity. Our sequence kernel is based upon generalized linear discriminants. We show that this strategy has several important properties. First, the kernel uses an explicit expansion into SVM feature space—this property makes it possible to collapse all support vectors into a single model vector and have low computational complexity. Second, the SVM builds upon a simpler mean-squared error classifier to produce a more accurate system. Finally, the system is competitive and complimentary to other approaches, such as Gaussian mixture models (GMMs). We give results for the 2003 NIST speaker and language evaluations of the system and also show fusion with the traditional GMM approach.

Research in the speaker recognition community has continued to address methods of mitigating variational nuisances. Telephone and auxiliary-microphone recorded speech emphasize the need for a robust way of dealing with unwanted variation. The design of recent 2010 NIST-SRE Speaker Recognition Evaluation (SRE) reflects this research emphasis. In this paper, we present the MIT submission applied to the tasks of the 2010 NIST-SRE with two main goals—language-independent scalable modeling and robust nuisance mitigation. For modeling, exclusive use of inner product-based and cepstral systems produced a language-independent computationally-scalable system. For robustness, systems that captured spectral and prosodic information, modeled nuisance subspaces using multiple novel methods, and fused scores of multiple systems were implemented. The performance of the system is presented on a subset of the NIST SRE 2010 core tasks.

We propose an informative dialect recognition system that learns phonetic transformation rules, and uses them to identify dialects. A hidden Markov model is used to align reference phones with dialect-specific pronunciations to characterize when and how often substitutions, insertions, and deletions occur. Decision tree clustering is used to find context-dependent phonetic rules. We ran recognition tasks on 4 Arabic dialects. Not only do the proposed systems perform well on their own, but when fused with baselines they improve performance by 21–36% relative. In addition, our proposed decision-tree system beats the baseline monophone system in recovering phonetic rules by 21% relative. Pronunciation rules learned by our proposed system quantify the occurrence frequency of known rules, and suggest rule candidates for further linguistic studies.

This paper presents a description of the MIT Lincoln Laboratory language recognition system submitted to the NIST 2009 Language Recognition Evaluation (LRE). This system consists of a fusion of three core recognizers, two based on spectral similarity and one based on tokenization. The 2009 LRE differed from previous ones in that test data included narrowband segments from worldwide Voice of America broadcasts as well as conventional recorded conversational telephone speech. Results are presented for the 23-language closed-set and open-set detection tasks at the 30, 10, and 3 second durations along with a discussion of the language-pair task. On the 30 second 23-language closed set detection task, the system achieved a 1.64 average error rate.

The sections in this article are 1 Language-Identification Cues 2 Language Identification Systems 3 Evaluations 4 Conclusions 5 Acknowledgment Keywords: phone recognition; spectral similiarity; speech-to-text systems; speech recognition

The MIT Lincoln Laboratory submission for the 2004 NIST speaker recognition evaluation (SRE) was built upon seven core systems using speaker information from short-term acoustics, pitch and duration prosodic behavior, and phoneme and word usage. These different levels of information were modeled and classified using Gaussian mixture models, support vector machines and N-gram language models and were combined using a single layer perceptron fuser. The 2004 SRE used a new multi-lingual, multi-channel speech corpus that provided a challenging speaker detection task for the above systems. We describe the core systems used and provide an overview of their performance on the 2004 SRE detection tasks.

Audio diarization is the process of annotating an input audio channel with information that attributes (possibly overlapping) temporal regions of signal energy to their specific sources. These sources can include particular speakers, music, background noise sources, and other signal source/channel characteristics. Diarization has utility in making automatic transcripts more readable and in searching and indexing audio archives. In this paper, we provide an overview of current audio diarization approaches and discuss performance and potential applications. We outline the general framework of diarization systems and present the performance of current systems as measured in the DARPA EARS Rich Transcription Fall 2004 (RT-04F) speaker diarization evaluation. Lastly, we look at future challenges and directions for diarization research.

This paper presents a description of the MIT Lincoln Laboratory submissions to the 2005 NIST Language Recognition Evaluation (LRE05). As was true in 2003, the 2005 submissions were combinations of core cepstral and phonotactic recognizers whose outputs were fused to generate final scores. For the 2005 evaluation, Lincoln Laboratory had five submissions built upon fused combinations of six core systems. Major improvements included the generation of phone streams using lattices, SVM-based language models using lattice-derived phonotactics, and binary tree language models. In addition, a development corpus was assembled that was designed to test robustness to unseen languages and sources. Language recognition trends based on NIST evaluations conducted since 1996 show a steady improvement in language recognition performance.

The de facto international standard for the forensic exchange of data for biometric recognition is ANSI/NIST ITL-1/2, “Data Format for the Interchange of Fingerprint, Facial, and Other Biometric Information.” This format is used by law enforcement, intelligence, military, and homeland security organizations thoughout the world to exchange fingerprint, face, scar/mark/tatoo, iris, and palmprint data. To date, however, there is no provision within the standard for the exchange of audio data for the purpose of forensic speaker recognition. During the recent 5-year update process for ANSI/NIST ITL-1/2, a consensus decision was made to advance a voice data format type under the name “Type 11 record.” Creating such an exchange format type, however, is far from straight forward—the problem being not the encoding of the autio data, for which many accepted standards exist, but rather in reaching a consensus on the metadata needed to support the varied mission requirements across the stakeholder communities. In this talk, we'll discuss the progress that has been made to date, the questions that remain, and the requirements for additional input from the broader stakeholder communities.