Automatic stress detection in emergency (telephone) calls

Lefter, Iulia; Rothkrantz, Léon J. M.; Leeuwen, David A. van; Wiggers, Pascal

doi:10.1504/ijidss.2011.039547

Cited by 41 publications

(28 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The numerical results that generated Table III are plotted on Figure 3. Now we can see that the more populated area is the trustable part (cases 1,2,3,5,6,7,10,11,14,16,17). The non-trustable area has four clear cases: 4, 9, 15 and 18.…”

Section:   mentioning

confidence: 85%

“…Most of them propose language independent systems by using just the speech sound and gender independent detection. The proposal of Lefter [2] separates neutral speech from emotional speech with a set of prosodicbased features at the utterance level and spectral features at the frame level. They use a database recorded with spontaneous emotions in a call centre.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of emotional stress in voice for deception detection

Rodellar

Palacios-Alonso

Nieto-Lluis

et al. 2015

2015 4th International Work Conference on Bioinspired Intelligence (IWOBI)

View full text Add to dashboard Cite

The current work gives a method to estimate alterations in speech caused by stress. This estimation is used as an indicator to detect deceptive speech. Truthful or neutral speech and deceptive speech were elicited by forcing to answer "hot questions" related with politics and society. Data were processed by using log-likelihood ratios and Fisher's linear discriminant analysis. Independent results for male and female are presented. The classification results are around 100% for neutral speech in both genders, while the best classification rate (67%) for stressed speech is achieved for females. In a first approach we have seen, that subjects tend to be more deceptive when the questions are related with gender issues, giving a politically correct answer instead of their true opinion.

show abstract

Section:   mentioning

confidence: 85%

Section: Introductionmentioning

confidence: 99%

Analysis of emotional stress in voice for deception detection

Rodellar

Palacios-Alonso

Nieto-Lluis

et al. 2015

2015 4th International Work Conference on Bioinspired Intelligence (IWOBI)

View full text Add to dashboard Cite

show abstract

“…In [11] we developed a model to extract special characteristics from speech, such as loudness, pitch, jitter, speech rate etc. Using these features we were able to detect stress in speech using a special database of speech recordings.…”

Section: Data Processingmentioning

confidence: 99%

Flood control of the smart city Prague

Rothkrantz

2016

2016 Smart Cities Symposium Prague (SCSP)

View full text Add to dashboard Cite

After heavy rainfall in the southern part of Germany and Czech country there is a serious risk of flooding of the river Moldau in the city of Prague. Flooding can cause many damage and victims. Prevention measures are building of removable dams and evacuation of people and animals. The raising of the water level can be predicted and a smart city has disaster plans. To train involved first responders in the execution of those plans many training hours are necessary. But to simulate realistic disasters is complicated or even impossible. Serious gaming is an alternative, especially to train involved people in communication, procedures and management. This paper is about the design of a serious game on flood control and a presentation of experiences from similar projects.

show abstract

“…By definition, paralinguistic communication includes “vocal, but extra-verbal aspects of communication properties, such as voice power (volume), the rate of speaking, variations, errors and other distortions of speech fluency, setting or level of voice, and its quality” [35]. Using paralinguistic communication to our advantage, research studies have shown that measures of paralinguistic speech features could be used to differentiate between older and younger speakers successfully [51] and to aid in the identification of a speaker’s emotional state [52, 53]. Lefter et al [52] also suggested if a caller’s stress could be measured, emergency call centres could allow computer operators to handle the less stressed callers, while the higher stressed individuals could be handled by a human operator.…”

Section: Introductionmentioning

confidence: 99%

Exploratory analysis of real personal emergency response call conversations: considerations for personal emergency response spoken dialogue systems

Young

Rochon

Mihailidis

2016

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

BackgroundThe purpose of this study was to derive data from real, recorded, personal emergency response call conversations to help improve the artificial intelligence and decision making capability of a spoken dialogue system in a smart personal emergency response system. The main study objectives were to: develop a model of personal emergency response; determine categories for the model’s features; identify and calculate measures from call conversations (verbal ability, conversational structure, timing); and examine conversational patterns and relationships between measures and model features applicable for improving the system’s ability to automatically identify call model categories and predict a target response.MethodsThis study was exploratory and used mixed methods. Personal emergency response calls were pre-classified according to call model categories identified qualitatively from response call transcripts. The relationships between six verbal ability measures, three conversational structure measures, two timing measures and three independent factors: caller type, risk level, and speaker type, were examined statistically.ResultsEmergency medical response services were the preferred response for the majority of medium and high risk calls for both caller types. Older adult callers mainly requested non-emergency medical service responders during medium risk situations. By measuring the number of spoken words-per-minute and turn-length-in-words for the first spoken utterance of a call, older adult and care provider callers could be identified with moderate accuracy. Average call taker response time was calculated using the number-of-speaker-turns and time-in-seconds measures. Care providers and older adults used different conversational strategies when responding to call takers. The words ‘ambulance’ and ‘paramedic’ may hold different latent connotations for different callers.ConclusionsThe data derived from the real personal emergency response recordings may help a spoken dialogue system classify incoming calls by caller type with moderate probability shortly after the initial caller utterance. Knowing the caller type, the target response for the call may be predicted with some degree of probability and the output dialogue could be tailored to this caller type. The average call taker response time measured from real calls may be used to limit the conversation length in a spoken dialogue system before defaulting to a live call taker.

show abstract

Automatic stress detection in emergency (telephone) calls

Cited by 41 publications

References 39 publications

Analysis of emotional stress in voice for deception detection

Analysis of emotional stress in voice for deception detection

Flood control of the smart city Prague

Exploratory analysis of real personal emergency response call conversations: considerations for personal emergency response spoken dialogue systems

Contact Info

Product

Resources

About