Guaranteeing privacy in released data is an important goal for data-producing agencies. There has been extensive research on developing suitable privacy mechanisms in recent years. Particularly notable is the idea of noise addition with the guarantee of differential privacy. There are, however, concerns about compromising data utility when very stringent privacy mechanisms are applied. Such compromises can be quite stark in correlated data, such as time series data. Adding white noise to a stochastic process may significantly change the correlation structure, a facet of the process that is essential to optimal prediction. We propose the use of all-pass filtering as a privacy mechanism for regularly sampled time series data, showing that this procedure preserves certain types of utility while also providing sufficient privacy guarantees to entity-level time series. Numerical studies explore the practical performance of the new method, and an empirical application to labor force data show the method's favorable utility properties in comparison to other competing privacy mechanisms.

Learner data from multiple instances of two introductory Python MOOCs, offered before and during the COVID-19 pandemic, were analyzed to see if and how learner behavior and overall learning outcomes changed during the pandemic. We found a surge in interest during the pandemic, but the certification rate fell short of the pre-pandemic average. Moreover, this drop in certification rate is more noticeable for the advanced course in the sequence, and is more pronounced in groups traditionally underrepresented in computer-science and coding communities. Additionally, we analyzed learners' interaction with one another on the course discussion forum, and performed a sentiment analysis of the forum comments using natural language processing, which revealed behavioral trends that differed significantly during the pandemic.

Online education, and MOOCs in particular, experienced a dramatic rise during the COVID-19 lockdown. Many had extra time to start learning new topics, while a significant fraction of the population experienced disruptions in areas such as healthcare, childcare, and potential loss of livelihood, among others. In this work we analyze learner data from multiple instances of two introductory Python MOOCs, offered before and during the COVID-19 pandemic, to understand how the pandemic affected learner progress and outcomes in these courses. We explore multiple measures of COVID-19 severity, and find a strong correlation between a measure of severity and relative change in certification rate. Specifically, we find that the change in certification rate relative to pre-pandemic baselines showed a negative correlation as COVID-19 severity increased.

Online learning platforms, such as edX, generate usage statistics data that can be valuable to educators. However, handling this raw data can prove challenging and time consuming for instructors and course designers. The raw data for the MIT courses running on the edX platform (MITx courses) are pre-processed and stored in a Google BigQuery database. We designed a tool based on Python and additional open-source Python packages such as Jupyter Notebook, to enable instructors to analyze their student data easily and securely. We expect that instructors would be encouraged to adopt more evidence-based teaching practices based on their interaction with the data.

This paper presents recent progress in developing speech-to-text (STT) and keyword spotting (KWS) systems for the 2014 IARPA-Babel evaluation. Systems have been developed for the limited language pack condition for four of the five de-velopment languages in this program phase: Assamese, Ben-gali, Haitian Creole and Zulu. The systems have several novel characteristics that support rapid development of KWS systems. On the STT side different acoustic units are explored based on phonemic or graphemic representations, and system combina-tion is used to improve STT performance. The acoustic models are trained on only 10 hours of speech data with manual tran-scriptions, completed with unsupervised training on additional untranscribed data. Both word and subword units (morphologi-cally decomposed, syllables, phonemes) are used for KWS. The KWS systems are based on the multi-hypotheses produced by a consensus network decoding or searching word lattices. The word error rates of the individual STT systems are on the or-der of 50-60%, and the KWS systems obtain Maximum Term Weighted Values ranging from 30-45 % for all keywords (in-vocabulary and out-of-vocabulary (OOV)). Sub-word units are shown to be successful at locating some of the OOV keywords, and system combination improves system performance. Index Terms: STT, KWS, semi-supervised training, lattice, consensus network, sub-word lexical units, Morfessor,

We address the problem of speaker identification in multimedia data, and TV series in particular. While speaker identification is traditionally a supervised machine-learning task, our first contribution is to significantly reduce the need for costly preliminary manual annotations through the use of automatically aligned (and potentially noisy) fan-generated transcripts and subtitles.

We present a framework for discovering acoustic units and generating an associated pronunciation lexicon from an initial grapheme-based recognition system. Our approach consists of two distinct contributions. First, context-dependent grapheme models are clustered using a spectral clustering approach to create a set of phone-like acoustic units. Next, we transform the pronunciation lexicon using a statistical machine translation-based approach. Pronunciation hypotheses generated from a decoding of the training set are used to create a phrase-based translation table. We propose a novel method for scoring the phrase-based rules that significantly improves the output of the transformation process. Results on an English language dataset demonstrate the combined methods provide a 13% relative reduction in word error rate compared to a baseline grapheme-based system. Our approach could potentially be applied to low-resource languages without existing lexicons, such as in the Babel project.

International audience

Speaker verification (SV) on portable devices like smartphones is gradually becoming popular. In this context, two issues need to be considered: 1) such devices have relatively limited computation resources, and 2) they are liable to be used everywhere, possibly in very noisy, uncontrolled environments. This work aims to address both these issues by proposing a computationally efficient yet robust SV system. This novel parts-based system draws inspiration from face and object detection systems in the computer vision domain. The system involves boosted ensembles of simple threshold-based classifiers. It uses a novel set of features extracted from speech spectra, called "slice features." The performance of the proposed system was evaluated through extensive studies involving a wide range of experimental conditions using the TIMIT, HTIMIT, and MOBIO corpus, against standard cepstral features and Gaussian Mixture Model-based SV systems.

In this paper, we propose a novel parts-based binary-valued feature for ASR. This feature is extracted using boosted ensembles of simple threshold-based classifiers. Each such classifier looks at a specific pair of time-frequency bins located on the spectro-temporal plane. These features termed as Boosted Binary Features (BBF) are integrated into standard HMM-based system by using multilayer perceptron (MLP) and single layer perceptron (SLP). Preliminary studies on TIMIT phoneme recognition task show that BBF yields similar or better performance compared to MFCC (67.8% accuracy for BBF vs. 66.3% accuracy for MFCC) using MLP, while it yields significantly better performance than MFCC (62.8% accuracy for BBF vs. 45.9% for MFCC) using SLP. This demonstrates the potential of the proposed feature for speech recognition.

In this work, we Investigate a novel computationally efficient speaker verification (SV) system involving boosted ensembles of simple threshold-based classifiers. The system is based on a novel set of features called "slice features". Both the system and the features were inspired by the recent success of pixel comparison-based ensemble approaches in the computer vision domain. The performance of the proposed system was evaluated through speaker verification experiments on the MOBIO corpus containing mo- bile phone speech, according to a challenging protocol. The system was found to perform reasonably well, compared to multiple state-of-the-art SV systems, with the benefit of significantly lower computational complexity. Its dual characteristics of good performance and computational efficiency could be important factors in the context of SV system implementation on portable devices like mobile phones.

The standard approach to speaker verification is to extract cepstral features from the speech spectrum and model them by generative or discriminative techniques. We propose a novel approach where a set of client-specific binary features carrying maximal discriminative information specific to the individual client are estimated from an ensemble of pair-wise comparisons of frequency components in magnitude spectra, using Adaboost algorithm. The final classifier is a simple linear combination of these selected features. Experiments on the XM2VTS database strictly according to a standard evaluation protocol have shown that although the proposed framework yields comparatively lower performance on clean speech, it significantly outperforms the state-of-the-art MFCC-GMM system in mismatched conditions with training on clean speech and testing on speech corrupted by four types of additive noise from the standard Noisex-92 database.

Person identification using audio (speech) and visual (facial appearance, static or dynamic) modalities, either independently or jointly, is a thoroughly investigated problem in pattern recognition. In this work, we explore a novel task : person identification in a cross-modal scenario, i.e., matching the speaker in an audio recording to the same speaker in a video recording, where the two recordings have been made during different sessions, using speaker specific information which is common to both the audio and video modalities. Several recent psychological studies have shown how humans can indeed perform this task with an accuracy significantly higher than chance. Here we propose two systems which can solve this task comparably well, using purely pattern recognition techniques. We hypothesize that such systems could be put to practical use in multimodal biometric and surveillance systems.

Face detection is the first step in many visual processing systems like face recognition, emotion recognition and lip reading. In this paper, we propose a novel feature called Haar Local Binary Pattern (HLBP) feature for fast and reliable face detection, particularly in adverse imaging conditions. This binary feature compares bin values of Local Binary Pattern histograms calculated over two adjacent image subregions. These subregions are similar to those in the Haar masks, hence the name of the feature. They capture the region-specific variations of local texture patterns and are boosted using AdaBoost in a framework similar to that proposed by Viola and Jones. Preliminary results obtained on several standard databases show that it competes well with other face detection systems, especially in adverse illumination conditions. 1

Knowing the statistical properties of a complex-valued signal is important in many signal processing applications by providing the necessary information for choosing the appropriate algorithm. In this paper, we provide generalized likelihood ratio tests (GLRT), based on the complex generalized Gaussian distribution (CGGD), for detecting two important signal properties: 1) the circularity of a complex random variable, not constrained to the Gaussian case and 2) whether a complex random variable is complex Gaussian. These tests can be combined to statistically determine if a complex random variable is, the often assumed, circular Gaussian. Simulations are used to quantify the performance of the detectors followed by application to communication signals and actual radar data.