Design of speaker identification schemes for large number of speakers (A)

Design of speaker identification schemes for a small number of speakers (around 10) with a high degree of accuracy in controlled environment is a practical proposition today. When the number of speakers is large (say 50–100), many of these schemes cannot be directly extended, as both recognition error and computation time increase monotonically with population size. The feature selection problem is also complex for such schemes. Though there were earlier attempts to rank order features based on statistical distance measures, it has been observed only recently that the best two independent measurements are not the same as the combination in two's for pattern classification. We propose here a systematic approach to the problem using the decision tree or hierarchical classifier with the following objectives: (1) Design of optimal policy at each node of the tree given the tree structure i.e., the tree skeleton and the features to be used at each node. (2) Determination of the optimal feature measurement and decision policy given only the tree skeleton. Applicability of optimization procedures such as dynamic programming in the design of such trees is studied. The experimental results deal with the design of a 50 speaker identification scheme based on this approach.

Identification of Active Sources in Single-Channel Convolutive Mixtures Using Known Source Models

We address the problem of identifying the constituent sources in a single-sensor mixture signal consisting of contributions from multiple simultaneously active sources. We propose a generic framework for mixture signal analysis based on a latent variable approach. The basic idea of the approach is to detect known sources represented as stochastic models, in a single-channel mixture signal without performing signal separation. A given mixture signal is modeled as a convex combination of known source models and the weights of the models are estimated using the mixture signal. We show experimentally that these weights indicate the presence/absence of the respective sources. The performance of the proposed approach is illustrated through mixture speech data in a reverberant enclosure. For the task of identifying the constituent speakers using data from a single microphone, the proposed approach is able to identify the dominant source with up to 8 simultaneously active background sources in a room with RT60 = 250 ms, using models obtained from clean speech data for a Source to Interference Ratio (SIR) greater than 2 dB.

Online Estimation of Evolving Human Visual Interest

Regions in video streams attracting human interest contribute significantly to human understanding of the video. Being able to predict salient and informative Regions of Interest (ROIs) through a sequence of eye movements is a challenging problem. Applications such as content-aware retargeting of videos to different aspect ratios while preserving informative regions and smart insertion of dialog (closed-caption text) into the video stream can significantly be improved using the predicted ROIs. We propose an interactive human-in-the-loop framework to model eye movements and predict visual saliency into yet-unseen frames. Eye tracking and video content are used to model visual attention in a manner that accounts for important eye-gaze characteristics such as temporal discontinuities due to sudden eye movements, noise, and behavioral artifacts. A novel statistical-and algorithm-based method gaze buffering is proposed for eye-gaze analysis and its fusion with content-based features. Our robust saliency prediction is instantiated for two challenging and exciting applications. The first application alters video aspect ratios on-the-fly using content-aware video retargeting, thus making them suitable for a variety of display sizes. The second application dynamically localizes active speakers and places dialog captions on-the-fly in the video stream. Our method ensures that dialogs are faithful to active speaker locations and do not interfere with salient content in the video stream. Our framework naturally accommodates personalisation of the application to suit biases and preferences of individual users.

Real-time magnetic resonance imaging and electromagnetic articulography database for speech production research (TC)

USC-TIMIT is an extensive database of multimodal speech production data, developed to complement existing resources available to the speech research community and with the intention of being continuously refined and augmented. The database currently includes real-time magnetic resonance imaging data from five male and five female speakers of American English. Electromagnetic articulography data have also been presently collected from four of these speakers. The two modalities were recorded in two independent sessions while the subjects produced the same 460 sentence corpus used previously in the MOCHA-TIMIT database. In both cases the audio signal was recorded and synchronized with the articulatory data. The database and companion software are freely available to the research community. (C) 2014 Acoustical Society of America.

Improved subject-independent acoustic-to-articulatory inversion

In subject-independent acoustic-to-articulatory inversion, the articulatory kinematics of a test subject are estimated assuming that the training corpus does not include data from the test subject. The training corpus in subject-independent inversion (SII) is formed with acoustic and articulatory kinematics data and the acoustic mismatch between training and test subjects is then estimated by an acoustic normalization using acoustic data drawn from a large pool of speakers called generic acoustic space (GAS). In this work, we focus on improving the SII performance through better acoustic normalization and adaptation. We propose unsupervised and several supervised ways of clustering GAS for acoustic normalization. We perform an adaptation of acoustic models of GAS using the acoustic data of the training and test subjects in SII. It is found that SII performance significantly improves (similar to 25% relative on average) over the subject-dependent inversion when the acoustic clusters in GAS correspond to phonetic units (or states of 3-state phonetic HMMs) and when the acoustic model built on GAS is adapted to training and test subjects while optimizing the inversion criterion. (C) 2014 Elsevier B.V. All rights reserved.