1 |
Multilingual Language Model Adaptive Fine-Tuning: A Study on African Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Preventing author profiling through zero-shot multilingual back-translation
|
|
|
|
In: 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) ; https://hal.inria.fr/hal-03350906 ; 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2021, Punta Cana, Dominica (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
On the Correlation of Context-Aware Language Models With the Intelligibility of Polish Target Words to Czech Readers
|
|
|
|
In: Front Psychol (2021)
|
|
BASE
|
|
Show details
|
|
5 |
Transfer learning and distant supervision for multilingual Transformer models: A study on African languages
|
|
|
|
In: 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) ; https://hal.inria.fr/hal-03350901 ; 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020, Punta Cana, Dominica (2020)
|
|
BASE
|
|
Show details
|
|
6 |
Distant supervision and noisy label learning for low resource named entity recognition: A study on Hausa and Yorùbá
|
|
|
|
In: ICLR Workshops (AfricaNLP & PML4DC 2020) ; https://hal.archives-ouvertes.fr/hal-03359111 ; ICLR Workshops (AfricaNLP & PML4DC 2020), Apr 2020, Addis Ababa, Ethiopia (2020)
|
|
BASE
|
|
Show details
|
|
7 |
A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
The DBOX Corpus Collection of Spoken Human-Human and Human-Machine Dialogues
|
|
|
|
In: http://infoscience.epfl.ch/record/201766 (2014)
|
|
BASE
|
|
Show details
|
|
12 |
Dedicated Backing-Off Distributions for Language Model Based Passage
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Beamforming with a Maximum Negentropy Criterion
|
|
|
|
In: http://infoscience.epfl.ch/record/146100 (2010)
|
|
BASE
|
|
Show details
|
|
14 |
Adaptive Beamforming with a Maximum Negentropy Criterion
|
|
|
|
In: http://infoscience.epfl.ch/record/146440 (2010)
|
|
BASE
|
|
Show details
|
|
15 |
Adaptive Beamforming with a Maximum Negentropy Criterion
|
|
|
|
In: http://infoscience.epfl.ch/record/146101 (2010)
|
|
Abstract:
In this paper, we address an adaptive beamforming application in realistic acoustic conditions. After the position of a speaker is estimated by a speaker tracking system, we construct a subband-domain beamformer in generalized sidelobe canceller (GSC) configuration. In contrast to conventional practice, we then optimize the active weight vectors of the GSC so as to obtain an output signal with maximum negentropy (MN). This implies the beamformer output should be as non-Gaussian as possible. For calculating negentropy, we consider the Gamma and the generalized Gaussian (GG) pdfs. After MN beamforming, Zelinski post-filtering is performed to further enhance the speech by removing residual noise. Our beamforming algorithm can suppress noise and reverberation without the signal cancellation problems encountered in the conventional adaptive beamforming algorithms. We demonstrate the effectiveness of our proposed technique through a series of far-field automatic speech recognition experiments on the Multi-Channel Wall Street Journal Audio Visual Corpus (MC-WSJ-AV). On the MC-WSJ-AV evaluation data, the delay-and-sum beamformer with post-filtering achieved a word error rate (WER) of 16.5%. MN beamforming with the Gamma pdf achieved a 15.8% WER, which was further reduced to 13.2% with the GG pdf, whereas the simple delay-and-sum beamformer provided a WER of 17.8%.
|
|
URL: https://doi.org/10.1109/HSCMA.2008.4538716 https://infoscience.epfl.ch/record/146101/files/Kumatani_HSCMA_2008.pdf http://infoscience.epfl.ch/record/146101 http://publications.idiap.ch/downloads/papers/2008/Kumatani_HSCMA_2008.pdf http://publications.idiap.ch/index.php/publications/showcite/kumatani:rr08-06
|
|
BASE
|
|
Hide details
|
|
|
|