Acoustic and Prosodic Correlates of Emotions in Urdu Speech

Urooj, Saba; Mumtaz, Benazir; Hussain, Sarmad; Haq, Ehsan Ul

doi:10.21437/interspeech.2021-910

Cited by 2 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many are available from the Linguistic Data Consortium (LDC), 1 which is an open consortium of universities, companies, and government research laboratories. We cite as examples, speech recognition corpus [13,18,19,37], speaker recognition corpus [12,24,33], emotion identification corpus [11,17,30,31,35], and those used for medical purposes [14,22,25,28].…”

Section: Introductionmentioning

confidence: 99%

The voice as a material clue: a new forensic Algerian Corpus

Zergat

Selouani

Amrouche

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

Dialects have received bigger interest in recent years as they are increasingly used on the web and social media. Because Algerian Arabic dialects suffer from a lack of appropriate speech corpora for speech recognition, a rich dialect corpus is needed to approach Algerian Accent recognition. The latter remains a key feature in the field of Forensic Voice Comparison (FVC) systems. This paper presents a new large-scale forensic Algerian speech corpus called Sawt El-Djazaïr. An important criterion in dealing with forensic corpora is the presence of session variability. For this purpose, we collected celebrity recordings in various regions of Algeria, from different social networks, in various scenarios, and at different times. In addition, we also recorded 87 participants using cellular calls and voice over IP (VoIP) applications including Viber, WhatsApp, and Google Meet. The corpus of approximately 50 hours covers various speech topics and is spoken in twelve Algerian sub-dialects. The design guidelines of the proposed corpus are described along with the grouping of dialects across different geographical locations. Sawt El-Djazaïr is available to the research community upon request.

show abstract

Section: Introductionmentioning

confidence: 99%

The voice as a material clue: a new forensic Algerian Corpus

Zergat

Selouani

Amrouche

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

Mirative Status of the Urdu Discourse Marker to

Sharif,

Hussain

2024

LLR

View full text Add to dashboard Cite

This study explicates the licensing conditions for the mirative behaviour of the Urdu discourse marker to, that is, how do declaratives become miratives in the presence of the discourse particle to? To explore the semantic contribution of this particle, the study uses Evans’ Lexical Concept and Cognitive Model (2009), since it combines linguistic and cognitive systems to account for a situated meaning. The study employs naturally occurring data, introspection, and Urdu Lughat to mitigate the limitations associated with an individual source when used in isolation. It finds that the discourse particle to contributes a non-propositional mirative meaning when it interacts with other lexical concepts undergoing the semantic compositional processes, namely selection, integration, and interpretation. The use of to and prosodic construction in declaratives remain in complementary distribution. The findings imply that both linguistic and non-linguistic factors account for form-meaning relation in Urdu language.

show abstract

Acoustic and Prosodic Correlates of Emotions in Urdu Speech

Cited by 2 publications

References 3 publications

The voice as a material clue: a new forensic Algerian Corpus

The voice as a material clue: a new forensic Algerian Corpus

Mirative Status of the Urdu Discourse Marker to

Contact Info

Product

Resources

About