Philip C. Woodland

Philip C. Woodland

Auto-generated profile, based on publicly available information

Philip C. Woodland

Department of Engineering, University of Cambridge, Cambridge, U.K.

Research Focus & Metrics

Academic Career Length

37Years (1990-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 1999 in Computer Speech & Language
Verified
Journal Article
Closed access
RDR.E. Donovan
R.E. Donovan
PWP.C. Woodland
P.C. Woodland

1 April 2007
Verified
Conference Paper
Closed access
KSK. C. Sim
K. C. Sim
WBW. J. Byrne
W. J. Byrne
MGM. J. F. Gales
M. J. F. Gales
HSH. Sahbi
H. Sahbi
PWP. C. Woodland
P. C. Woodland
This paper presents a simple and robust consensus decoding approach for combining multiple machine translation (MT) system outputs. A consensus network is constructed from an N-best list by aligning the hypotheses against an alignment reference, where the alignment is based on minimising the translation edit rate (TER). The minimum Bayes risk (MBR) decoding technique is investigated for the selection of an appropriate alignment reference. Several alternative decoding strategies proposed to retain coherent phrases in the original translations. Experimental results are presented primarily based on three-way combination of Chinese-English translation outputs, and also presents results for six-way system combination. It is shown that worthwhile improvements in translation performance can be obtained using the methods discussed.

14 November 2022 in IEEE Transactions on Affective Computing
Verified
Journal Article
Open access
WWWen Wu
Wen Wu
CZChao Zhang
Chao Zhang
XWXixin Wu
Xixin Wu
PWPhilip C. Woodland
Philip C. Woodland
Emotion recognition is a key attribute for artificial intelligence systems that need to naturally interact with humans. However, the task definition is still an open problem due to the inherent ambiguity of emotions. In this paper, a novel Bayesian training loss based on per-utterance Dirichlet prior distributions is proposed for verbal emotion recognition, which models the uncertainty in one-hot labels created when human annotators assign the same utterance to different emotion classes. An additional metric is used to evaluate the performance by detecting test utterances with high labelling uncertainty. This removes a major limitation that emotion classification systems only consider utterances with labels where the majority of annotators agree on the emotion class. Furthermore, a frequentist approach is studied to leverage the continuous-valued “soft” labels obtained by averaging the one-hot labels. We propose a two-branch model structure for emotion classification on a per-utterance basis, which achieves state-of-the-art classification results on the widely used IEMOCAP dataset. Based on this, uncertainty estimation experiments were performed. The best performance in terms of the area under the precision-recall curve when detecting utterances with high uncertainty was achieved by interpolating the Bayesian training loss with the Kullback-Leibler divergence training loss for the soft labels. The generality of the proposed approach was verified using the MSP-Podcast dataset which yielded the same pattern of results.

1 September 2021 in Neural Networks
Verified
Journal Article
Closed access
GSGuangzhi Sun
Guangzhi Sun
CZChao Zhang
Chao Zhang
PWPhilip C. Woodland
Philip C. Woodland

20 August 2023
Verified
Conference Paper
Open access
GSGuangzhi Sun
Guangzhi Sun
XZXianrui Zheng
Xianrui Zheng
CZChao Zhang
Chao Zhang
PWPhilip C. Woodland
Philip C. Woodland

1 April 2007
Verified
Conference Paper
Closed access
LWL. Wang
L. Wang
MGM.J.F. Gales
M.J.F. Gales
PWP.C. Woodland
P.C. Woodland
A significant cost in obtaining acoustic training data is the generation of accurate transcriptions. For some sources close-caption data is available. This allows the use of lightly-supervised training techniques. However, for some sources and languages close-caption is not available. In these cases unsupervised training techniques must be used. This paper examines the use of unsupervised techniques for discriminative training. In unsupervised training automatic transcriptions from a recognition system are used for training. As these transcriptions may be errorful data selection may be useful. Two forms of selection are described, one to remove non-target language shows, the other to remove segments with low confidence. Experiments were carried out on a Mandarin transcriptions task. Two types of test data were considered, broadcast news (BN) and broadcast conversations (BC). Results show that the gains from unsupervised discriminative training are highly dependent on the accuracy of the automatic transcriptions.