Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Jayadev Billa"'
Autor:
Jayadev Billa
Publikováno v:
Interspeech 2021.
Autor:
Jayadev Billa
Publikováno v:
INTERSPEECH
Autor:
Jayadev Billa
Publikováno v:
ICASSP
In this paper we examine dropout approaches in a Long Short Term Memory (LSTM) based automatic speech recognition (ASR) system trained with the Connectionist Temporal Classification (CTC) loss function. In particular, using an Eesen based LSTM-CTC sp
Autor:
Amro El-Jaroudi, Jayadev Billa
Publikováno v:
The Journal of the Acoustical Society of America. 103:2691-2705
Computational models of the peripheral auditory system have largely modeled basilar membrane (BM) mechanics as a linear filter-bank-like entity. Recent mathematical work on the nature of auditory system noise suppression allows us to analyze and argu
Autor:
Jayadev Billa, Amro El-Jaroudi
Publikováno v:
Engineering Applications of Artificial Intelligence. 9:205-208
Multi-Layer Neural Networks (MLNNs) have been known to be used to model the statistical properties of their training data. Several authors have shown that, depending on the objective function chosen, MLNNs estimate the posterior class probabilities o
Autor:
Fred Richardson, A. El-Jaroudi, G. Zavaliagkos, J. McDonough, Jayadev Billa, Kristine W. Ma, Herbert Gish, D. Miller, Man-Hung Siu
Publikováno v:
ICASSP
This paper presents the 1997 BBN Byblos large vocabulary speech recognition (LVCSR) system. We give an outline of the algorithms and procedures used to train the system, describe the recognizer configuration and present the major technological innova
Publikováno v:
ICASSP
This paper focuses on the optimization of model parameters for vocal tract length normalization (VTLN). For maximum likelihood (ML) based normalization techniques, the complexity of the VTL-models is a source of variation in system performance. An op
Autor:
R. Stone, John Makhoul, Amit Srivastava, M. Noamany, Daben Liu, J. Xu, Francis Kubala, Jayadev Billa
Publikováno v:
ICASSP
This paper describes the development of the BBN Audio Indexing System for broadcast news in Arabic. Key issues addressed in this work revolve around the three major components of the audio indexing system: automatic speech recognition, speaker identi
Publikováno v:
Proceedings of the second international conference on Human Language Technology Research.
This paper describes the introduction of Arabic speech and text into the TIDES OnTAP system. This includes the development of the BBN Audio Indexing System for broadcast news in Arabic, development and the introduction of an Arabic event tracker and