Emotions in Speech: Juristic Implications

Eriksson, Erik J.; Rodman, Robert D.; Hubal, Robert

doi:10.1007/978-3-540-74200-5_8

Cited by 3 publications

(2 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This kind of within-speaker variation stems from the incredible plasticity of our speech production mechanism. Some of the areas which have received considerable attention include various speech styles and the effect that they have on specific acoustic parameters (Jessen, 2009;McDougall & Duckworth, 2018;Ross et al, 2019), the impact of various affective or physiological states (Eriksson et al, 2007;Scherer, 2019), as well as phonetic accommodation to one's communication partner (see, e.g., Earnshaw, 2021;Šturm et al, 2021). In FVC, these are particularly important since the analyzed recordings tend to be mismatched in this respect.…”

Section: Introductionmentioning

confidence: 99%

The impact of mismatched recordings on an automatic-speaker-recognition system and human listeners

Nechanský¹,

Bořil²,

Houzar³

et al. 2023

Auc Philologica

View full text Add to dashboard Cite

The so-called ‘mismatch’ is a factor which experts in the forensic voice comparison field encounter regularly. Therefore, we decided to explore to what extent the automatic-speaker-recognition system’s and the earwitness’ ability to identify speakers is influenced when recordings are acquired in different languages and at different times. 100 voices in a database of 300 recordings (100 speakers recorded in three mutually mismatched sessions) were compared with an automatic-speaker-recognition software VOCALISE based on i-vectors and x-vectors, and by 39 respondents in simulated voice parades. Both the automatic and perceptual approach seem to have yielded similar results in that the less complex the mismatch type, the more successful the identification. The results point to the superiority of the x-vector approach, and also to varying identification abilities of listeners.

show abstract

Section: Introductionmentioning

confidence: 99%

The impact of mismatched recordings on an automatic-speaker-recognition system and human listeners

Nechanský¹,

Bořil²,

Houzar³

et al. 2023

Auc Philologica

View full text Add to dashboard Cite

show abstract

“…Furthermore, we did not discuss emerging applications for home parole, detection of deception, or fraud in the context of Law Enforcement, which are concerned with speaker's identity or emotion. An introduction to this field concerning the latter characteristic is given by Eriksson in this issue [38]. 3 What?…”

Section: Discussionmentioning

confidence: 99%

Speaker Characteristics

Schultz

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this chapter, we give a brief introduction to speech-driven applications in order to motivate why it is desirable to automatically recognize particular speaker characteristics from speech. Starting from these applications, we derive what kind of characteristics might be useful. After categorizing relevant speaker characteristics, we describe in more detail language, accent, dialect, idiolect, and sociolect. Next, we briefly summarize classification approaches to illustrate how these characteristics can be recognized automatically, and conclude with a practical example of a system implementation that performs well on the classification of various speaker characteristics.

show abstract

Real-time speech emotion recognition by minimum number of features

Savargiv

Bastanfard

2016

2016 Artificial Intelligence and Robotics (IRANOPEN)

View full text Add to dashboard Cite

Emotions in Speech: Juristic Implications

Cited by 3 publications

References 56 publications

The impact of mismatched recordings on an automatic-speaker-recognition system and human listeners

The impact of mismatched recordings on an automatic-speaker-recognition system and human listeners

Speaker Characteristics

Real-time speech emotion recognition by minimum number of features

Contact Info

Product

Resources

About