Publications

Refine Results

(Filters Applied) Clear All

Channel compensation for speaker recognition using MAP adapted PLDA and denoising DNNs

June 21, 2016
  |
Conference Paper
Author:
Frederick S. Richardson
…
Published in:
Odyssey 2016, The Speaker and Language Recognition Workshop, 21-24 June 2016.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

Over several decades, speaker recognition performance has steadily improved for applications using telephone speech. A big part of this improvement has been the availability of large quantities of speaker-labeled data from telephone recordings. For new data applications, such as audio from room microphones, we would like to effectively use existing telephone data to build systems with high accuracy while maintaining good performance on existing telephone tasks. In this paper we compare and combine approaches to compensate models parameters and features for this purpose. For model adaptation we explore MAP adaptation of hyper-parameters and for feature compensation we examine the use of denoising DNNs. On a multi-room, multi-microphone speaker recognition experiment we show a reduction of 61% in EER with a combination of these approaches while slightly improving performance on telephone data.
READ LESS

Summary

Over several decades, speaker recognition performance has steadily improved for applications using telephone speech. A big part of this improvement has been the availability of large quantities of speaker-labeled data from telephone recordings. For new data applications, such as audio from room microphones, we would like to effectively use existing...

READ MORE
Channel compensation for speaker recognition using MAP adapted PLDA and denoising DNNs

The MITLL NIST LRE 2015 Language Recognition System

June 21, 2016
  |
Conference Paper
Author:
Pedro A. Torres-Carrasquillo
…
Published in:
Odyssey 2016, 21-24 June 2016, pp. 196-203.
Topic:
language recognition
R&D area:
R&D group:

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
The MITLL NIST LRE 2015 Language Recognition System

A vocal modulation model with application to predicting depression severity

June 14, 2016
  |
Conference Paper
Author:
Rachelle Horwitz-Martin
…
Published in:
13th IEEE Int. Conf. on Wearable and Implantable Body Sensor Networks, BSN 2016, 14-17 June 2016.
Topic:
biometrics
R&D area:
R&D group:

Summary

Speech provides a potential simple and noninvasive "on-body" means to identify and monitor neurological diseases. Here we develop a model for a class of vocal biomarkers exploiting modulations in speech, focusing on Major Depressive Disorder (MDD) as an application area. Two model components contribute to the envelope of the speech waveform: amplitude modulation (AM) from respiratory muscles, and AM from interaction between vocal tract resonances (formants) and frequency modulation in vocal fold harmonics. Based on the model framework, we test three methods to extract envelopes capturing these modulations of the third formant for synthesized sustained vowels. Using subsequent modulation features derived from the model, we predict MDD severity scores with a Gaussian Mixture Model. Performing global optimization over classifier parameters and number of principal components, we evaluate performance of the features by examining the root-mean-squared error (RMSE), mean absolute error (MAE), and Spearman correlation between the actual and predicted MDD scores. We achieved RMSE and MAE values 10.32 and 8.46, respectively (Spearman correlation=0.487, p<0.001), relative to a baseline RMSE of 11.86 and MAE of 10.05, obtained by predicting the mean MDD severity score. Ultimately, our model provides a framework for detecting and monitoring vocal modulations that could also be applied to other neurological diseases.
READ LESS

Summary

Speech provides a potential simple and noninvasive "on-body" means to identify and monitor neurological diseases. Here we develop a model for a class of vocal biomarkers exploiting modulations in speech, focusing on Major Depressive Disorder (MDD) as an application area. Two model components contribute to the envelope of the speech...

READ MORE
A vocal modulation model with application to predicting depression severity

Broadband Optical Switch Based on Liquid Crystal Dynamic Scattering

June 13, 2016
  |
Journal Article
Author:
Michael W. Geis
…
Published in:
Optics Express, vol. 24, no. 13
Topic:
optics
R&D area:
R&D group:

Summary

This work demonstrates a novel broadband optical switch, based on dynamic-scattering effect in liquid crystals (LCs). Dynamic-scattering-mode technology was developed for display applications over four decades ago, but was displaced in favor of the twisted-nematic LCs. However, with the recent development of more stable LCs, dynamic scattering provides advantages over other technologies for optical switching. We demonstrate broadband polarization-insensitive attenuation of light directly passing thought the cell by 4 to 5 orders of magnitude at 633 nm. The attenuation is accomplished by light scattering to higher angles. Switching times of 150 μs to 10% transmission have been demonstrated. No degradation of devices is found after hundreds of switching cycles. The light-rejection mechanism is due to scattering, induced by disruption of LC director orientation with dopant ion motion with an applied electric field. Angular dependence of scattering is characterized as a function of bias voltage.
READ LESS

Summary

This work demonstrates a novel broadband optical switch, based on dynamic-scattering effect in liquid crystals (LCs). Dynamic-scattering-mode technology was developed for display applications over four decades ago, but was displaced in favor of the twisted-nematic LCs. However, with the recent development of more stable LCs, dynamic scattering provides advantages over...

READ MORE
Broadband Optical Switch Based on Liquid Crystal Dynamic Scattering

BubbleNet: A Cyber Security Dashboard for Visualizing Patterns

June 6, 2016
  |
Conference Paper
Author:
Sean P. McKenna
…
Published in:
Proceeding of 2016 Eurographics Conference on Visualization (EuroVis)
Topic:
visualization
R&D area:
R&D group:

Summary

The field of cyber security is faced with ever-expanding amounts of data and a constant barrage of cyber attacks. Within this space, we have designed BubbleNet as a cyber security dashboard to help network analysts identify and summarize patterns within the data.
READ LESS

Summary

The field of cyber security is faced with ever-expanding amounts of data and a constant barrage of cyber attacks. Within this space, we have designed BubbleNet as a cyber security dashboard to help network analysts identify and summarize patterns within the data.

READ MORE
BubbleNet: A Cyber Security Dashboard for Visualizing Patterns

Single-photon-sensitive solid-state image sensors for flash lidar

June 5, 2016
  |
Conference Paper
Author:
Brian F. Aull
Published in:
CLEO 2016, Laser Science to Photonic Applications, 5-10 June 2016.
Topic:
photonics
R&D area:
R&D group:

Summary

MIT Lincoln Laboratory has developed lidar systems based on Geiger-mode avalanche photodiodes using both silicon and InGaAs. This technology has enabled terrain mapping and foliage penetration systems with exquisite sensitivity and high area coverage rate.
READ LESS

Summary

MIT Lincoln Laboratory has developed lidar systems based on Geiger-mode avalanche photodiodes using both silicon and InGaAs. This technology has enabled terrain mapping and foliage penetration systems with exquisite sensitivity and high area coverage rate.

READ MORE
Single-photon-sensitive solid-state image sensors for flash lidar

Multitap RF canceller for in-band full-duplex wireless communications

June 1, 2016
  |
Journal Article
Author:
Kenneth E. Kolodziej
…
Published in:
IEEE Wirel. Commun., Vol. 15, No. 6, June 2016, pp. 4321-34.
Topic:
wireless
R&D area:
R&D group:

Summary

In-band full-duplex wireless communications are challenging because they require the mitigation of self-interference caused by the co-located transmitter to operate effectively. This paper presents a novel tapped delay line RF canceller architecture with multiple non-uniform pre-weighted taps to improve system isolation by cancelling both the direct antenna coupling as well as multipath effects that comprise a typical interference channel. A four-tap canceller prototype was measured over several different operating conditions, and was found to provide an average of 30 dB signal cancellation over a 30 MHz bandwidth centered at 2.45 GHz in isolated scenarios. When combined with an omni-directional high-isolation antenna, the canceller improved the overall analog isolation to 90 dB for these cases. In an indoor setting, the canceller suppressed a +30 dBm OFDM signal by 22 dB over a 20 MHz bandwidth centered at 2.45 GHz, and produced 78 dB of total analog isolation. This complete evaluation demonstrates not only the performance limitations of an optimized multitap RF canceller, but also establishes the amount of analog interference suppression that can be expected for the different environments considered.
READ LESS

Summary

In-band full-duplex wireless communications are challenging because they require the mitigation of self-interference caused by the co-located transmitter to operate effectively. This paper presents a novel tapped delay line RF canceller architecture with multiple non-uniform pre-weighted taps to improve system isolation by cancelling both the direct antenna coupling as well...

READ MORE
Multitap RF canceller for in-band full-duplex wireless communications

A scalable fabrication process for liquid crystal-based uncooled thermal imagers

June 1, 2016
  |
Journal Article
Author:
Shaun R. Berry
…
Published in:
J. Microelectromech. Syst., Vol. 25, No. 3. June 2016, pp. 479-88.
Topic:
microelectronics
R&D area:
R&D group:

Summary

A novel sensor is being developed for a new uncooled imager technology that is scalable to large formats (tens of megapixels), which is greater than what is achieved by commercial microbolometer arrays. In this novel sensor, a liquid-crystal transducer is used to change a long-wavelength infrared scene into a visible image that can be detected using a conventional visible imager. This approach has the potential for making a more flexible thermal sensor that can be optimized for a variety of applications. In this paper, we describe the microfabrication processes required to create an array of sealed thermally isolated micro-cavities filled with liquid crystals to be used for an uncooled thermal imager. Experimental results from the fabricated arrays will also be discussed.
READ LESS

Summary

A novel sensor is being developed for a new uncooled imager technology that is scalable to large formats (tens of megapixels), which is greater than what is achieved by commercial microbolometer arrays. In this novel sensor, a liquid-crystal transducer is used to change a long-wavelength infrared scene into a visible...

READ MORE
A scalable fabrication process for liquid crystal-based uncooled thermal imagers

Operational assessment of keyword search on oral history

May 23, 2016
  |
Conference Paper
Author:
Elizabeth E. Salesky
…
Published in:
10th Language Resources and Evaluation Conf., LREC 2016, 23-8 May 2016.
Topic:
human language technology
R&D area:
R&D group:

Summary

This project assesses the resources necessary to make oral history searchable by means of automatic speech recognition (ASR). There are many inherent challenges in applying ASR to conversational speech: smaller training set sizes and varying demographics, among others. We assess the impact of dataset size, word error rate and term-weighted value on human search capability through an information retrieval task on Mechanical Turk. We use English oral history data collected by StoryCorps, a national organization that provides all people with the opportunity to record, share and preserve their stories, and control for a variety of demographics including age, gender, birthplace, and dialect on four different training set sizes. We show comparable search performance using a standard speech recognition system as with hand-transcribed data, which is promising for increased accessibility of conversational speech and oral history archives.
READ LESS

Summary

This project assesses the resources necessary to make oral history searchable by means of automatic speech recognition (ASR). There are many inherent challenges in applying ASR to conversational speech: smaller training set sizes and varying demographics, among others. We assess the impact of dataset size, word error rate and term-weighted...

READ MORE
Operational assessment of keyword search on oral history

Enforced sparse non-negative matrix factorization

May 23, 2016
  |
Conference Paper
Author:
Brendan E. Gavin
…
Published in:
30th IEEE Int. Parallel and Distributed Processing Symp., IPDPS 2016, 23-27 May 2016.
Topic:
supercomputing
R&D area:
R&D group:

Summary

Non-negative matrix factorization (NMF) is a dimensionality reduction algorithm for data that can be represented as an undirected bipartite graph. It has become a common method for generating topic models of text data because it is known to produce good results, despite its relative simplicity of implementation and ease of computation. One challenge with applying the NMF to large datasets is that intermediate matrix products often become dense, thus stressing the memory and compute elements of the underlying system. In this article, we investigate a simple but powerful modification of the alternating least squares method of determining the NMF of a sparse matrix that enforces the generation of sparse intermediate and output matrices. This method enables the application of NMF to large datasets through improved memory and compute performance. Further, we demonstrate, empirically, that this method of enforcing sparsity in the NMF either preserves or improves both the accuracy of the resulting topic model and the convergence rate of the underlying algorithm.
READ LESS

Summary

Non-negative matrix factorization (NMF) is a dimensionality reduction algorithm for data that can be represented as an undirected bipartite graph. It has become a common method for generating topic models of text data because it is known to produce good results, despite its relative simplicity of implementation and ease of...

READ MORE
Enforced sparse non-negative matrix factorization
481-490 of 2315