Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Woojay Jeon"'
Autor:
Hao Yen, Woojay Jeon
In embedding-matching acoustic-to-word (A2W) ASR, every word in the vocabulary is represented by a fixed-dimension embedding vector that can be added or removed independently of the rest of the system. The approach is potentially an elegant solution
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::efba3be0f7d20988229a177ee5bb0000
Publikováno v:
ICASSP
We propose a method to reduce false voice triggers of a speech-enabled personal assistant by post-processing the hypothesis lattice of a server-side large-vocabulary continuous speech recognizer (LVCSR) via a neural network. We first discuss how an e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0fec6a6b522e2ed64750cc0dfa652771
http://arxiv.org/abs/2003.00304
http://arxiv.org/abs/2003.00304
Publikováno v:
ICASSP
We present a new method for computing ASR word confidences that effectively mitigates the effect of ASR errors for diverse downstream applications, improves the word error rate of the 1-best result, and allows better comparison of scores across diffe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::beebdb5c04f29a3f99cf564a6a04145d
http://arxiv.org/abs/1907.09636
http://arxiv.org/abs/1907.09636
Publikováno v:
IEEE Transactions on Audio, Speech, and Language Processing. 20:2482-2491
We propose a novel method of measuring the similarity between two or more speech utterances for speaker clustering, based on probability theory and factor analysis. The similarity function is formulated as the probability that the utterances originat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8494ca2949ccf6831c68f89c9d370c28
https://doi.org/10.1109/tasl.2012.2204050
https://doi.org/10.1109/tasl.2012.2204050
Autor:
Biing-Hwang Juang, Woojay Jeon
Publikováno v:
IEEE Transactions on Audio, Speech, and Language Processing. 15:1802-1817
Recently, there is a significant increase in research interest in the area of biologically inspired systems, which, in the context of speech communications, attempt to learn from human's auditory perception and cognition capabilities so as to derive
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2943517b07482fa21e0af2fbe1e523b8
https://doi.org/10.1109/tasl.2007.900102
https://doi.org/10.1109/tasl.2007.900102
Autor:
Woojay Jeon, Yan-Ming Cheng
Publikováno v:
ICASSP
We propose a novel method of efficiently searching very large populations of speakers, tens of thousands or more, using an utterance comparison model proposed in a previous work. The model allows much more efficient comparison of utterances compared
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::06eb1fed9d517afc3b458c359038271b
https://doi.org/10.1109/icassp.2012.6288860
https://doi.org/10.1109/icassp.2012.6288860
Publikováno v:
ICASSP
We propose a novel utterance comparison model based on probability theory and factor analysis that computes the likelihood of two speech utterances originating from the same speaker. The model depends only on a set of statistics extracted from each u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aed36030145fd58d976b6f54ab638ce3
https://doi.org/10.1109/icassp.2011.5947361
https://doi.org/10.1109/icassp.2011.5947361
Efficient search of music pitch contours using wavelet transforms and segmented dynamic time warping
Autor:
Changxue Ma, Woojay Jeon
Publikováno v:
ICASSP
We propose a method of music melody matching based on their “continuous” (or “time-frame-based”) pitch contours. Most previous methods using frame-based contours either made limiting assumptions on the locations, musical scale, tempo, and/or
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0494a1dea622daa4d8c269c4b3fec98d
https://doi.org/10.1109/icassp.2011.5946943
https://doi.org/10.1109/icassp.2011.5946943
[TODO] Add abstract here.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10907a4d134d3d476235dca02588ef3b
Autor:
Woojay Jeon, Changxue Ma
Publikováno v:
ICASSP
In this paper, we present an efficient method of speech indexing and search using phoneme sequences called uniterms. In the indexing stage, a collection of uniterms and uniterm sequences is extracted from the target speech database by applying statis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8405edfce0b137de8d5ef2926f517c09
https://doi.org/10.1109/icassp.2009.4959829
https://doi.org/10.1109/icassp.2009.4959829