Objective measurement of fluency in natural language production: A dynamic systems approach

Hird, Kathryn; Kirsner, Kim

doi:10.1016/j.jneuroling.2010.03.001

Cited by 21 publications

(23 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FPS offers an automated way of reliably summarizing important temporal characteristics of natural speech. While manually analyzed studies have been able to demonstrate differences between groups on variables as diverse as reading speed (Demol et al, 2007), aphasia and neurogenic brain disorders (Hird & Kirsner, 2010;Rosen et al, 2003), and language type (Camione & Véronis, 2002, questions remain over the accuracy and reliability of manual analysis (see, e.g., Oehmen et al, 2010). A reliable and valid automatic method can provide an efficient means of studying differences between populations that vary in fluencies.…”

Section: Discussionmentioning

confidence: 99%

“…The logic behind the classification table is as follows: (1) Only low-energy segments with durations of 20 ms or longer and high-energy segments of 50 ms or longer are considered to be true pause or true speech segments, respectively. These assumptions are based on relevant precedents (e.g., Hird & Kirsner, 2010;Kirsner et al, 2002;Rosen et al, 2003) and on neurophysiological evidence identifying temporal constraints on speech perception and production (Schulze & Langner, 1997;Song et al, 2011). Any segments less than this cutoff length are combined with the adjacent segments.…”

Section: Energy Classificationmentioning

confidence: 99%

“…The addition of these measures allows for an analysis of the speech "content" within a speech segment, allowing for the calculation of the amount of information transmitted within a given period of time. These analyses would provide further information about the cognitive construction of language and potentially allow for the differentiation of clinical groups (e.g., in aphasia; Hird & Kirsner, 2010).…”

Section: Transcription and Final Statisticsmentioning

confidence: 99%

“…Both short and long pause duration distributions provide valuable information about fluency across different clinical populations and different social contexts. For instance, the mean of the long pause duration distribution, but not of the short pause distribution, is increased relative to controls in individuals with Broca's aphasia (Hird & Kirsner, 2010;Kirsner et al, 2005). Consequently, the parameters of the pause distributions can be used to assess multiple factors pertaining to cognitive workload, aphasia, breathing difficulties, arousal, and emotion that affect speech fluency.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Fluency Profiling System: An automated system for analyzing the temporal properties of speech

et al. 2012

Self Cite

View full text Add to dashboard Cite

The temporal characteristics of speech can be captured by examining the distributions of the durations of measurable speech components, namely speech segment durations and pause durations. However, several barriers prevent the easy analysis of pause durations: The first problem is that natural speech is noisy, and although recording contrived speech minimizes this problem, it also discards diagnostic information about cognitive processes inherent in the longer pauses associated with natural speech. The second issue concerns setting the distribution threshold, and consists of the problem of appropriately classifying pause segments as either short pauses reflecting articulation or long pauses reflecting cognitive processing, while minimizing the overall classification error rate. This article describes a fully automated system for determining the locations of speech-pause transitions and estimating the temporal parameters of both speech and pause distributions in natural speech. We use the properties of Gaussian mixture models at several stages of the analysis, in order to identify theoretical components of the data distributions, to classify speech components, to compute durations, and to calculate the relevant statistics.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Energy Classificationmentioning

confidence: 99%

Section: Transcription and Final Statisticsmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Fluency Profiling System: An automated system for analyzing the temporal properties of speech

et al. 2012

Self Cite

View full text Add to dashboard Cite

show abstract

“…The efficient understanding of natural language requires that computer program be able to resolve ambiguities at the syntactic level and recover that part of the meaning of its individual words taken in isolation. [7][8] The satisfaction of this requirement involves complex inference from a large database of worldknowledge, and this makes the designer of computer programs for NLU face the serious difficulty of algorithm processing. [9] The machine comprehension is embedded in the more general frame of interpersonal communication and is applied to the person-machine interaction task.…”

Section: Introductionmentioning

confidence: 99%

Predicting Garden Path Sentences Based on Natural Language Understanding System

Du¹,

Yu²

2012

IJACSA

View full text Add to dashboard Cite

Abstract-Natural language understanding (NLU) focusing on machine reading comprehension is a branch of natural language processing (NLP). The domain of the developing NLU system covers from sentence decoding to text understanding and the automatic decoding of GP sentence belongs to the domain of NLU system. GP sentence is a special linguistic phenomenon in which processing breakdown and backtracking are two key features. If the syntax-based system can present the special features of GP sentence and decode GP sentence completely and perfectly, NLU system can improve the effectiveness and develop the understanding skill greatly. On the one hand, by means of showing Octav Popescu's model of NLU system, we argue that the emphasis on the integration of syntactic, semantic and cognitive backgrounds in system is necessary. On the other hand, we focus on the programming skill of IF-THEN-ELSE statement used in N-S flowchart and highlight the function of context free grammar (CFG) created to decode GP sentence. On the basis of example-based analysis, we reach the conclusion that syntaxbased machine comprehension is technically feasible and semantically acceptable, and that N-S flowchart and CFG can help NLU system present the decoding procedure of GP sentence successfully. In short, syntax-based NLU system can bring a deeper understanding of GP sentence and thus paves the way for further development of syntax-based natural language processing and artificial intelligence.

show abstract

Constructing theoretically informed measures of pause duration in experimentally manipulated writing

2022

View full text Add to dashboard Cite

This paper argues that traditional threshold-based approaches to the analysis of pauses in writing fail to capture the complexity of the cognitive processes involved in text production. It proposes that, to capture these processes, pause analysis should focus on the transition times between linearly produced units of text. Following a review of some of the problematic features of traditional pause analysis, the paper is divided into two sections. These are designed to demonstrate: (i) how to isolate relevant transitions within a text and calculate their durations; and (ii) the use of mixture modelling to identify structure within the distributions of pauses at different locations. The paper uses a set of keystroke logs collected from 32 university students writing argumentative texts about current affairs topics to demonstrate these methods. In the first section, it defines how pauses are calculated using a reproducible framework, explains the distinction between linear and non-linear text transitions, and explains how relevant sections of text are identified. It provides Excel scripts for automatically identifying relevant pauses and calculating their duration. The second section applies mixture modelling to linear transitions at sentence, sub sentence, between-word and within-word boundaries for each participant. It concludes that these transitions cannot be characterised by a single distribution of “cognitive” pauses. It proposes, further, that transitions between words should be characterised by a three-component distribution reflecting lexical, supra-lexical and reflective processes, while transitions at other text locations can be modelled by two-component distributions distinguishing between fluent and less fluent or more reflective processing. The paper concludes by recommending that, rather than imposing fixed thresholds to distinguish processes, researchers should instead impose a common set of theoretically informed distributions on the data and estimate how the parameters of these distributions vary for different individuals and under different conditions.

show abstract

Objective measurement of fluency in natural language production: A dynamic systems approach

Cited by 21 publications

References 18 publications

Fluency Profiling System: An automated system for analyzing the temporal properties of speech

Fluency Profiling System: An automated system for analyzing the temporal properties of speech

Predicting Garden Path Sentences Based on Natural Language Understanding System

Constructing theoretically informed measures of pause duration in experimentally manipulated writing

Contact Info

Product

Resources

About