Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Monisankha Pal"'
Meta-Learning With Latent Space Clustering in Generative Adversarial Network for Speaker Diarization
Autor:
Somer L. Bishop, Manoj Kumar, Catherine Lord, Shrikanth S. Narayanan, Tae Jin Park, Monisankha Pal, So Hyun Kim, Raghuveer Peri
Publikováno v:
IEEE/ACM Trans Audio Speech Lang Process
The performance of most speaker diarization systems with x-vector embeddings is both vulnerable to noisy environments and lacks domain robustness. Earlier work on speaker diarization using generative adversarial network (GAN) with an encoder network
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b725b5e574652addf4d59cd32f2e6329
https://doi.org/10.1109/taslp.2021.3061885
https://doi.org/10.1109/taslp.2021.3061885
Publikováno v:
International Journal of Speech Technology
International Journal of Speech Technology, 2021, ⟨10.1007/s10772-020-09785-w⟩
International Journal of Speech Technology, Springer Verlag, 2021, ⟨10.1007/s10772-020-09785-w⟩
International Journal of Speech Technology, 2021, ⟨10.1007/s10772-020-09785-w⟩
International Journal of Speech Technology, Springer Verlag, 2021, ⟨10.1007/s10772-020-09785-w⟩
International audience; In this paper, we introduce a frame selection strategy for improved detection of spoofed speech. A countermeasure (CM) system typically uses a Gaussian mixture model (GMM) based classifier for computing the log-likelihood scor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5924ce1335b5dfca20009d8538edc661
https://hal.science/hal-03008912
https://hal.science/hal-03008912
Autor:
Arindam Jati, Shrikanth S. Narayanan, Monisankha Pal, Chin-Cheng Hsu, Raghuveer Peri, Wael AbdAlmageed
Publikováno v:
ICASSP
Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversarial attacks pose serious security threats to the speaker recognition s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20fcf9fe42fa8e72e770541d58635b84
Autor:
Chin-Cheng Hsu, Raghuveer Peri, Monisankha Pal, Wael AbdAlmageed, Shrikanth S. Narayanan, Arindam Jati
Publikováno v:
Computer Speech & Language. 68:101199
Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart speakers and personal agents that interact with an individual's voice c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de2061749ab8660b18a962c068f70cb9
https://doi.org/10.1016/j.csl.2021.101199
https://doi.org/10.1016/j.csl.2021.101199
Autor:
Goutam Saha, Monisankha Pal
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 25:2071-2084
In this paper, we propose a new voice conversion (VC) method using i-vectors which consider low-dimensional representation of speech utterances. An attempt is made to restrict the i-vector variability in the intermediate computation of total variabil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c349721cd3522194f719019081e15cb9
https://doi.org/10.1109/taslp.2017.2743620
https://doi.org/10.1109/taslp.2017.2743620
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 11:605-617
Recent advancements in voice conversion (VC) and speech synthesis research make speech-based biometric systems highly prone to spoofing attacks. This can provoke an increase in false acceptance rate in such systems and requires countermeasure to miti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4643b8096b2f53b5692d7c42903f4f3e
https://doi.org/10.1109/jstsp.2017.2684705
https://doi.org/10.1109/jstsp.2017.2684705
Autor:
Somer L. Bishop, Shrikanth S. Narayanan, Manoj Kumar, Tae Jin Park, Raghuveer Peri, So Hyun Kim, Catherine Lord, Monisankha Pal
Publikováno v:
ICASSP
In this work, we propose deep latent space clustering for speaker diarization using generative adversarial network (GAN) backprojection with the help of an encoder network. The proposed diarization system is trained jointly with GAN loss, latent vari
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::920eb4dc19bedaf0f215a8bc51c0a6d4
http://arxiv.org/abs/1910.11398
http://arxiv.org/abs/1910.11398
Autor:
Raghuveer Peri, Monisankha Pal, Tae Jin Park, Panayiotis G. Georgiou, Naveen Kumar, Shrikanth S. Narayanan, Ruchir Travadi, Arindam Jati
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::183d4b57a13dfb599785b27a577fa971
https://doi.org/10.21437/interspeech.2019-3010
https://doi.org/10.21437/interspeech.2019-3010
Autor:
Rimita Lahiri, Shrikanth S. Narayanan, Panayiotis G. Georgiou, Manoj Kumar, Monisankha Pal, Raghuveer Peri, Nikolaos Flemotomos, Tae Jin Park
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a733c603be287d9b5273446bb45d23e
https://doi.org/10.21437/interspeech.2019-1903
https://doi.org/10.21437/interspeech.2019-1903
Publikováno v:
ICASSP
In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial invariance arc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cb9576f216fc5c01054a563d945b0bb2