DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 27

1
Dawn of the transformer era in speech emotion recognition: closing the valence gap ...
BASE
Show details
2
Probing Speech Emotion Recognition Transformers for Linguistic Knowledge ...
Abstract: Large, pre-trained neural networks consisting of self-attention layers (transformers) have recently achieved state-of-the-art results on several speech emotion recognition (SER) datasets. These models are typically pre-trained in self-supervised manner with the goal to improve automatic speech recognition performance -- and thus, to understand linguistic information. In this work, we investigate the extent in which this information is exploited during SER fine-tuning. Using a reproducible methodology based on open-source tools, we synthesise prosodically neutral speech utterances while varying the sentiment of the text. Valence predictions of the transformer model are very reactive to positive and negative sentiment content, as well as negations, but not to intensifiers or reducers, while none of those linguistic features impact arousal or dominance. These findings show that transformers can successfully leverage linguistic information to improve their valence predictions, and that linguistic analysis should ... : This work has been submitted for publication to Interspeech 2022 ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
URL: https://dx.doi.org/10.48550/arxiv.2204.00400
https://arxiv.org/abs/2204.00400
BASE
Hide details
3
Infected phonemes: how a cold impairs speech on a phonetic level
BASE
Show details
4
The NoXi database: multimodal recordings of mediated novice-expert interactions
BASE
Show details
5
Ask Alice: an artificial retrieval of information agent
BASE
Show details
6
CABank Garfinkel Boston Seminar Corpus
BASE
Show details
7
SamtaleBank Sam4 Corpus
Wagner, Johannes; Gregersen, Frans. - : TalkBank, 2011
BASE
Show details
8
L2 Learning as Social Practice: Conversation-Analytic Perspectives ; Pragmatics & Interaction, Volume 2
Pallotti, Gabriele; Wagner, Johannes. - : National Foreign Language Resource Center, 2011
BASE
Show details
9
Whodunnit - Searching for the Most Important Feature Types Signalling Emotion-Related User States in Speech
In: ISSN: 0885-2308 ; EISSN: 1095-8363 ; Computer Speech and Language ; https://hal.archives-ouvertes.fr/hal-00661911 ; Computer Speech and Language, Elsevier, 2010, 25 (1), pp.4. ⟨10.1016/j.csl.2009.12.003⟩ (2010)
BASE
Show details
10
CABank Examples Corpus
Wagner, Johannes. - : TalkBank, 2010
BASE
Show details
11
SamtaleBank Dansk_som_Andetsprog Corpus
Wagner, Johannes. - : TalkBank, 2009
BASE
Show details
12
SamtaleBank Sam1 Corpus
Wagner, Johannes. - : TalkBank, 2009
BASE
Show details
13
SamtaleBank Radio Corpus
Wagner, Johannes. - : TalkBank, 2009
BASE
Show details
14
SamtaleBank Sam2 Corpus
Wagner, Johannes. - : TalkBank, 2009
BASE
Show details
15
SamtaleBank Natteravn Corpus
Wagner, Johannes. - : TalkBank, 2009
BASE
Show details
16
SamtaleBank Telefon Corpus
Wagner, Johannes. - : TalkBank, 2009
BASE
Show details
17
SamtaleBank Sam3 Corpus
Wagner, Johannes. - : TalkBank, 2009
BASE
Show details
18
Managing moral accountability in scholarly talk: The case of a conversation analysis data session
In: Text and Talk 28 (2008) 1, 1-30
IDS Bibliografie zur Gesprächsforschung
Show details
19
Bi-channel sensor fusion for automatic sign language recognition
BASE
Show details
20
Diversity and continuity in conversation analysis
In: Journal of Pragmatics 39 (2007) 3, 441-444
IDS Bibliografie zur Gesprächsforschung
Show details

Page: 1 2

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
3
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
23
0
1
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern