ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023
DOI: 10.1109/icassp49357.2023.10096510
|View full text |Cite
|
Sign up to set email alerts
|

Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(1 citation statement)
references
References 21 publications
0
1
0
Order By: Relevance
“…Within the audio modality, spoken language understanding (SLU) models primarily focus on single-turn user commands by extracting relevant information to fulfill the intended actions [20,21]. Intent classification is another prominent research area that has been extensively explored across text [22], speech [23], and multi-modal environments [24]. While audio-based DST shares some similarities with these aforementioned tasks, it also exhibits notable distinctions; it addresses acoustic inputs that are comprised of multi-turn interactions between users and systems, and requires the prediction of comprehensive information that is beyond simple categorization of user intent.…”
Section: Related Workmentioning
confidence: 99%
“…Within the audio modality, spoken language understanding (SLU) models primarily focus on single-turn user commands by extracting relevant information to fulfill the intended actions [20,21]. Intent classification is another prominent research area that has been extensively explored across text [22], speech [23], and multi-modal environments [24]. While audio-based DST shares some similarities with these aforementioned tasks, it also exhibits notable distinctions; it addresses acoustic inputs that are comprised of multi-turn interactions between users and systems, and requires the prediction of comprehensive information that is beyond simple categorization of user intent.…”
Section: Related Workmentioning
confidence: 99%