Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Mahnoosh Mehrabani"'
Autor:
Shahab Jalalvand, Yeon-Jun Kim, Narendra K. Gupta, Minhua Chen, Ryan Price, Yanjie Zhao, Mahnoosh Mehrabani, Srinivas Bangalore
Publikováno v:
NAACL-HLT (Industry Papers)
Spoken language understanding (SLU) extracts the intended mean- ing from a user utterance and is a critical component of conversational virtual agents. In enterprise virtual agents (EVAs), language understanding is substantially challenging. First, t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::02aa4db6db13e7343b0fa780c252dec9
https://doi.org/10.18653/v1/2021.naacl-industry.9
https://doi.org/10.18653/v1/2021.naacl-industry.9
Publikováno v:
ICASSP
While human language provides a natural interface for humanmachine communication, there are several challenges concerning extracting the intents of a speaker when interacting with a virtual agent, especially when the speaker is in a noisy acoustic en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::38b66364dde055ef06168e31083ad348
https://doi.org/10.1109/icassp40776.2020.9054417
https://doi.org/10.1109/icassp40776.2020.9054417
Autor:
John H. L. Hansen, Mahnoosh Mehrabani
Publikováno v:
Speech Communication. 55:653-666
Highlights? Mixed style speech causes problems when training acoustic models for speech applications, such as speaker ID and ASR. ? This study is a first attempt for speaker clustering under mixed speaking styles which include reading and singing. ?
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af9fde152d3ff8f05ce7fb6e8360053b
https://doi.org/10.1016/j.specom.2012.11.001
https://doi.org/10.1016/j.specom.2012.11.001
Publikováno v:
WF-IoT
With the rapid increasing of smart devices, there has been a growing interest in the concept of Internet of Things (IoT). While as a network of connected objects, IoT is created by enabling machine to machine interactions, another important factor of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cdda19a6ce807ce62673763071aad4a3
https://doi.org/10.1109/wf-iot.2015.7389082
https://doi.org/10.1109/wf-iot.2015.7389082
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6cb40730c54a17afaa16dc5d0166593
https://doi.org/10.21437/interspeech.2015-327
https://doi.org/10.21437/interspeech.2015-327
Autor:
John H. L. Hansen, Mahnoosh Mehrabani
Publikováno v:
INTERSPEECH
In this study, we expand the question of ”what is the intrinsic dimensionality of speech?” to ”how does the intrinsic dimensionality of speech change from speaking to singing?”. Our focus is on dimensionality of the vowel space regarding spec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de5cb725528935a244535837ec0e5ecc
https://doi.org/10.21437/interspeech.2013-650
https://doi.org/10.21437/interspeech.2013-650
Publikováno v:
INTERSPEECH
We propose an unsupervised prominence prediction method for expressive speech synthesis. Prominence patterns are learned by statistical analysis of prosodic features extracted from speech data. The advantages of our unsupervised datadriven prominence
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a5c2b1ccfa776b5318d776b96e49c1ea
https://doi.org/10.21437/interspeech.2013-394
https://doi.org/10.21437/interspeech.2013-394
Autor:
Mahnoosh Mehrabani, John H. L. Hansen
Publikováno v:
Interspeech 2012.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e91d9ea96f848d8bf82345ffb41d790e
https://doi.org/10.21437/interspeech.2012-593
https://doi.org/10.21437/interspeech.2012-593
Publikováno v:
Interspeech 2012.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4aaafa46b6f03cf5281f4a24ba4f827
https://doi.org/10.21437/interspeech.2012-553
https://doi.org/10.21437/interspeech.2012-553
Publikováno v:
ICASSP
This study presents new advancements in our articulatory-based language identification (LID) system. Our LID system automatically identifies language-features (LFs) from a phonological features (PFs) based representation of speech. While our baseline
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::766215a0ac538f45f57f91527dd840b3
https://doi.org/10.1109/icassp.2011.5947329
https://doi.org/10.1109/icassp.2011.5947329