Vikram Ramanarayanan

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.

An investigation of articulatory setting using real-time magnetic resonance imaging

This paper presents an automatic procedure to analyze articulatory setting in speech production using real-time magnetic resonance imaging of the moving human vocal tract. The procedure extracts frames corresponding to inter-speech pauses, speech-ready intervals and absolute rest intervals from magnetic resonance imaging sequences of read and spontaneous speech elicited from five healthy speakers of American English and uses automatically extracted image features to quantify vocal tract posture during these intervals. Statistical analyses show significant differences between vocal tract postures adopted during inter-speech pauses and those at absolute rest before speech; the latter also exhibits a greater variability in the adopted postures. In addition, the articulatory settings adopted during inter-speech pauses in read and spontaneous speech are distinct. The results suggest that adopted vocal tract postures differ on average during rest positions, ready positions and inter-speech pauses, and might, in that order, involve an increasing degree of active control by the cognitive speech planning mechanism.

Analysis of pausing behavior in spontaneous speech using real-time magnetic resonance imaging of articulation

It is hypothesized that pauses at major syntactic boundaries (i.e., grammatical pauses), but not ungrammatical (e.g., word search) pauses, are planned by a high-level cognitive mechanism that also controls the rate of articulation around these junctures. Real-time magnetic resonance imaging is used to analyze articulation at and around grammatical and ungrammatical pauses in spontaneous speech. Measures quantifying the speed of articulators were developed and applied during these pauses as well as during their immediate neighborhoods. Grammatical pauses were found to have an appreciable drop in speed at the pause itself as compared to ungrammatical pauses, which is consistent with our hypothesis that grammatical pauses are indeed choreographed by a central cognitive planner.

Evaluating Speech, Face, Emotion and Body Movement Time-series Features for Automated Multimodal Presentation Scoring

We analyze how fusing features obtained from different multimodal data streams such as speech, face, body movement and emotion tracks can be applied to the scoring of multimodal presentations. We compute both time-aggregated and time-series based features from these data streams--the former being statistical functionals and other cumulative features computed over the entire time series, while the latter, dubbed histograms of cooccurrences, capture how different prototypical body posture or facial configurations co-occur within different time-lags of each other over the evolution of the multimodal, multivariate time series. We examine the relative utility of these features, along with curated speech stream features in predicting human-rated scores of multiple aspects of presentation proficiency. We find that different modalities are useful in predicting different aspects, even outperforming a naive human inter-rater agreement baseline for a subset of the aspects analyzed.

Are Articulatory Settings Mechanically Advantageous for Speech Motor Control

We address the hypothesis that postures adopted during grammatical pauses in speech production are more “mechanically advantageous” than absolute rest positions for facilitating efficient postural motor control of vocal tract articulators. We quantify vocal tract posture corresponding to inter-speech pauses, absolute rest intervals as well as vowel and consonant intervals using automated analysis of video captured with real-time magnetic resonance imaging during production of read and spontaneous speech by 5 healthy speakers of American English. We then use locally-weighted linear regression to estimate the articulatory forward map from low-level articulator variables to high-level task/goal variables for these postures. We quantify the overall magnitude of the first derivative of the forward map as a measure of mechanical advantage. We find that postures assumed during grammatical pauses in speech as well as speech-ready postures are significantly more mechanically advantageous than postures assumed during absolute rest. Further, these postures represent empirical extremes of mechanical advantage, between which lie the postures assumed during various vowels and consonants. Relative mechanical advantage of different postures might be an important physical constraint influencing planning and control of speech production.

Assembling the Jigsaw: How Multiple Open Standards Are Synergistically Combined in the HALEF Multimodal Dialog System

As dialog systems become increasingly multimodal and distributed in nature with advances in technology and computing power, they become that much more complicated to design and implement. However, open industry and W3C standards provide a silver lining here, allowing the distributed design of different components that are nonetheless compliant with each other. In this chapter we examine how an open-source, modular, multimodal dialog system—HALEF—can be seamlessly assembled, much like a jigsaw puzzle, by putting together multiple distributed components that are compliant with the W3C recommendations or other open industry standards. We highlight the specific standards that HALEF currently uses along with a perspective on other useful standards that could be included in the future. HALEF has an open codebase to encourage progressive community contribution and a common standard testbed for multimodal dialog system development and benchmarking.

Multimodal HALEF: An Open-Source Modular Web-Based Multimodal Dialog Framework

We present an open-source web-based multimodal dialog framework, “Multimodal HALEF”, that integrates video conferencing and telephony abilities into the existing HALEF cloud-based dialog framework via the FreeSWITCH video telephony server. Due to its distributed and cloud-based architecture, Multimodal HALEF allows researchers to collect video and speech data from participants interacting with the dialog system outside of traditional lab settings, therefore largely reducing cost and labor incurred during the traditional audio-visual data collection process. The framework is equipped with a set of tools including a web-based user survey template, a speech transcription, an annotation and rating portal, a web visual processing server that performs head tracking, and a database that logs full-call audio and video recordings as well as other call-specific information. We present observations from an initial data collection based on an job interview application. Finally we report on some future plans for development of the framework.

Speaker verification based on the fusion of speech acoustics and inverted articulatory signals

We propose a practical, feature-level and score-level fusion approach by combining acoustic and estimated articulatory information for both text independent and text dependent speaker verification. From a practical point of view, we study how to improve speaker verification performance by combining dynamic articulatory information with the conventional acoustic features. On text independent speaker verification, we find that concatenating articulatory features obtained from measured speech production data with conventional Mel-frequency cepstral coefficients (MFCCs) improves the performance dramatically. However, since directly measuring articulatory data is not feasible in many real world applications, we also experiment with estimated articulatory features obtained through acoustic-to-articulatory inversion. We explore both feature level and score level fusion methods and find that the overall system performance is significantly enhanced even with estimated articulatory features. Such a performance boost could be due to the inter-speaker variation information embedded in the estimated articulatory features. Since the dynamics of articulation contain important information, we included inverted articulatory trajectories in text dependent speaker verification. We demonstrate that the articulatory constraints introduced by inverted articulatory features help to reject wrong password trials and improve the performance after score level fusion. We evaluate the proposed methods on the X-ray Microbeam database and the RSR 2015 database, respectively, for the aforementioned two tasks. Experimental results show that we achieve more than 15% relative equal error rate reduction for both speaker verification tasks.

Using bidirectional lstm recurrent neural networks to learn high-level abstractions of sequential features for automated scoring of non-native spontaneous speech

We introduce a new method to grade non-native spoken language tests automatically. Traditional automated response grading approaches use manually engineered time-aggregated features (such as mean length of pauses). We propose to incorporate general time-sequence features (such as pitch) which preserve more information than time-aggregated features and do not require human effort to design. We use a type of recurrent neural network to jointly optimize the learning of high level abstractions from time-sequence features with the time-aggregated features. We first automatically learn high level abstractions from time-sequence features with a Bidirectional Long Short Term Memory (BLSTM) and then combine the high level abstractions with time-aggregated features in a Multilayer Perceptron (MLP)/Linear Regression (LR). We optimize the BLSTM and the MLP/LR jointly. We find such models reach the best performance in terms of correlation with human raters. We also find that when there are limited time-aggregated features available, our model that incorporates time-sequence features improves performance drastically.

A distributed cloud-based dialog system for conversational application development

We have previously presented HALEF‐an open-source spoken dialog system‐that supports telephonic interfaces and has a distributed architecture. In this paper, we extend this infrastructure to be cloud-based, and thus truly distributed and scalable. This cloud-based spoken dialog system can be accessed both via telephone interfaces as well as through web clients with WebRTC/HTML5 integration, allowing in-browser access to potentially multimodal dialog applications. We demonstrate the versatility of the system with two conversation applications in the educational domain.