A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
Speaker Diarization with Enhancing Speech for the First DIHARD Challenge
2018
Interspeech 2018
Preserved Fulltext
The enhanced speech can boost the performance for the subsequent SAD, segmentation and clustering. ...
To the best of our knowledge, this is the first time we show significant improvements of deep learning based single-channel speech enhancement over state-of-the-art diarization systems in highly mismatch ...
While state-of-the-art diarization systems perform remarkably well for some domains (e.g., conversational telephone speech such as CallHome), as was discovered at the 2017 JSALT Summer Workshop at CMU ...
doi:10.21437/interspeech.2018-1742
dblp:conf/interspeech/SunDJZHYL18
fatcat:vrnnolsq6vhmvidwetpk73dti4
The Second DIHARD Diarization Challenge: Dataset, Task, and Baselines
2019
Interspeech 2019
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We describe the task and metrics, challenge design, datasets, and baseline systems for speech enhancement, speech activity detection, and diarization. ...
, noise conditions, and conversational domain. ...
It is against this backdrop that the JSALT-2017 workshop [12] and DIHARD challenges 2 emerged. ...
doi:10.21437/interspeech.2019-1268
dblp:conf/interspeech/RyantCCCDGL19
fatcat:cxmnf46l6vc4bdr4ujm22n2bje
DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
For each module, we explore different techniques to enhance performance. ...
In this paper, we present the submitted system for the second DIHARD Speech Diarization Challenge from the DKULENOVO team. ...
However, the 2017 JSALT Summer Workshop at CMU found it hard to migrate the success to more challenging corpora including web videos, speech in the wild, child language recordings, etc [26] . ...
arXiv:2002.12761v2
fatcat:5te7enwf7fbkvhy5xjiyojmyje
The Nunavut Hansard Inuktitut-English Parallel Corpus 3.0 with Preliminary Machine Translation Results
2020
International Conference on Language Resources and Evaluation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This paper describes a newly released sentence-aligned Inuktitut-English corpus based on the proceedings of the Legislative Assembly of Nunavut, covering sessions from April 1999 to June 2017. ...
It is an official language of two territories, Nunavut and the Northwest Territories, and has recognition in additional regions. ...
We would also like to thank the 2019 Annual Jelinek Memorial Workshop on Speech and Language Technology (JSALT) for providing a venue for experiments and feedback on the beta version of this corpus. ...
dblp:conf/lrec/JoanisKKLLLSM20
fatcat:nyepziu5hrgntawpgebzvreplu
ALICE: An open-source tool for automatic measurement of phoneme, syllable, and word counts from child-centered daylong recordings
2020
Behavior Research Methods
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
A key measure to quantify from such data is the amount of speech present in children's home environments. ...
We discuss the advantages and disadvantages of measuring different units from theoretical and technical points of view. ...
Some of the daylong recordings in BER, and all recordings in TSE, YEL, MCD, and WAR, are available from HomeBank repository (VanDam et al., 2016) . ...
doi:10.3758/s13428-020-01460-x
pmid:32875399
fatcat:qbjvaxg4xba3vg5u55cihazpg4
DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team
2020
Odyssey 2020 The Speaker and Language Recognition Workshop
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
For each module, we explore different techniques to enhance performance. ...
In this paper, we present the submitted system for the second DIHARD Speech Diarization Challenge from the DKU-LENOVO team. ...
However, the 2017 JSALT Summer Workshop at CMU found it hard to migrate the success to more challenging corpora including web videos, speech in the wild, child language recordings, etc [26] . ...
doi:10.21437/odyssey.2020-15
fatcat:bpci45neejftppr6z5d7atfy2i
Benchmarking: Past, Present and Future
2021
Proceedings of the 1st Workshop on Benchmarking: Past, Present and Future
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Where have we been, and where are we going? It is easier to talk about the past than the future. These days, benchmarks evolve more bottom up (such as papers with code) ...
, speech coding, speech recognition, speech enhancement, artificial neural networks, human-machine interaction using voice, optical character recognition, machine translation, and cross-lingual information ...
Bio John Makhoul is a Chief Scientist at Raytheon BBN Technologies, Cambridge, MA, where he has been working on various aspects of speech and language processing, including speech analysis and synthesis ...
doi:10.18653/v1/2021.bppf-1.1
fatcat:ipnmbjgvqndjlhawhiximarfvy
Learning Representations of Social Media Users
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We apply several extensions of generalized canonical correlation analysis to learn these representations and evaluate them at three tasks: predicting future hashtag mentions, friending behavior, and demographic ...
and complicated as social media? ...
, and Pan, 2017) , speech and cognitive impairment features 4 , as well as to learn multimodal representations of video (Tsai and Kender, 2017) . ...
arXiv:1812.00436v1
fatcat:qp2hf6f6nfe7djyjakkns36epq