Andrew Rosenberg

Acoustic/Prosodic and Lexical Correlates of Charismatic Speech

Charisma, the ability to command authority on the basis of personal qualities, is more difficult to define than to identify. How do charismatic leaders such as Fidel Castro or Pope John Paul II attract and retain their followers? We present results of an analysis of subjective ratings of charisma from a corpus of American political speech. We identify the associations between charisma ratings and ratings of other personal attributes. We also examine acoustic/prosodic and lexical features of this speech and correlate these with charisma ratings.

Charisma perception from text and speech

Charisma, the ability to attract and retain followers without benefit of formal authority, is more difficult to define than to identify. While we each seem able to identify charismatic individuals - and non-charismatic individuals - it is not clear what it is about an individual that influences our judgment. This paper describes the results of experiments designed to discover potential correlates of such judgments, in what speakers say and the way that they say it. We present results of two parallel experiments in which subjective judgments of charisma in spoken and in transcribed American political speech were analyzed with respect to the acoustic and prosodic (where applicable) and lexico-syntactic characteristics of the speech being assessed. While we find that there is considerable disagreement among subjects on how the speakers of each token are ranked, we also find that subjects appear to share a functional definition of charisma, in terms of other personal characteristics we asked them to rank speakers by. We also find certain acoustic, prosodic, and lexico-syntactic characteristics that correlate significantly with perceptions of charisma. Finally, by comparing the responses to spoken vs. transcribed stimuli, we attempt to distinguish between the contributions of what is said and how it is said with respect to charisma judgments.

Speech segmentation and spoken document processing

Progress in both speech and language processing has spurred efforts to support applications that rely on spoken rather than written language input. A key challenge in moving from text-based documents to such spoken documents is that spoken language lacks explicit punctuation and formatting, which can be crucial for good performance. This article describes different levels of speech segmentation, approaches to automatically recovering segment boundary locations, and experimental results demonstrating impact on several language processing tasks. The results also show a need for optimizing segmentation for the end task rather than independently.

Story Segmentation of Broadcast News in English, Mandarin and Arabic

In this paper, we present results from a Broadcast News story segmentation system developed for the SRI NIGHTINGALE system operating on English, Arabic and Mandarin news shows to provide input to subsequent question-answering processes. Using a rule-induction algorithm with automatically extracted acoustic and lexical features, we report success rates that are competitive with state-of-the-art systems on each input language. We further demonstrate that features useful for English and Mandarin are not discriminative for Arabic.

Detecting Pitch Accents at the Word, Syllable and Vowel Level

The automatic identification of prosodic events such as pitch accent in English has long been a topic of interest to speech researchers, with applications to a variety of spoken language processing tasks. However, much remains to be understood about the best methods for obtaining high accuracy detection. We describe experiments examining the optimal domain for accent analysis. Specifically, we compare pitch accent identification at the syllable, vowel or word level as domains for analysis of acoustic indicators of accent. Our results indicate that a word-based approach is superior to syllable- or vowel-based detection, achieving an accuracy of 84.2%.

Augmenting the kappa statistic to determine interannotator reliability for multiply labeled data points

This paper describes a method for evaluating interannotator reliability in an email corpus annotated for type (e.g., question, answer, social chat) when annotators are allowed to assign multiple labels to a message. An augmentation is proposed to Cohens kappa statistic which permits all data to be included in the reliability measure and which further permits the identification of more or less reliably annotated data points.

Detecting Pitch Accent Using Pitch-corrected Energy-based Predictors

Previous work has shown that the energy components of frequency subbands with a variety of frequencies and bandwidths predict pitch accent with various degrees of accuracy, and produce correct predictions for distinct subsets of data points. In this paper, we describe a series of experiments exploring techniques to leverage the predictive power of these energy components by including pitch and duration features – other known correlates to pitch accent. We perform these experiments on Standard American English read, spontaneous and broadcast news speech, each corpus containing at least four speakers. Using an approach by which we correct energy-based predictions using pitch and duration information prior to using a majority voting classifier, we were able to detect pitch accent in read, spontaneous and broadcast news speech at 84.0%, 88.3% and 88.5% accuracy, respectively. Human performance at pitch accent detection is generally taken to be between 85% and 90%. Index Terms: prosodic analysis, spectral emphasis

A cross-cultural comparison of American, Palestinian, and Swedish perception of charismatic speech

Perception of charisma, the ability to infuence others by virtue of ones personal qualities, appears to be infuenced to some extent by cultural factors. We compare results of five studies of chari ...

On the Correlation between Energy and Pitch Accent in Read English Speech

In this paper, we describe a set of experiments that examine the correlation between energy and pitch accent. We tested the discriminative power of the energy component of frequency subbands with a variety of frequencies and bandwidths on read speech spoken by four native speakers of Standard American English, using an analysis by classification approach. We found that the frequency region most robust to speaker differences is between 2 and 20 bark. Across all speakers, using only energy features we were able to predict pitch accent in read speech with accuracy of 81.9%.

Varying Input Segmentation for Story Boundary Detection in English, Arabic and Mandarin Broadcast News

Story segmentation of news broadcasts has been shown to improve the accuracy of the subsequent processes such as question answering and information retrieval. In previous work, a decision tree trained on automatically extracted lexical and acoustic features was trained to predict story boundaries, using hypothesized sentence boundaries to define potential story boundaries. In this paper, we empirically evaluate several alternatives to this choice of input segmentation on three languages: English, Mandarin and Arabic. Our results suggest that the best performance can be achieved by using 250ms pause-based segmentation or sentence boundaries determined using a very low confidence score threshold. Index Terms: story boundary detection, segmentation