Copingwith channel mismatch in Query-by-Example - But QUESST 2014

Szöke, Igor; Skácel, Miroslav; Burget, Lukáš; Černocký, Jaň

doi:10.1109/icassp.2015.7179091

Cited by 16 publications

(31 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feed forward networks have been traditionally used to obtain bottleneck features for speech related tasks [5,13,14]. Here, we describe the different architectures employed in this study as shown in Figure 1: The increased number of layers is intended at modeling the extra training data gained by adding languages.…”

Section: Feed Forward Networkmentioning

confidence: 99%

“…In this section, we report and analyze the QbE-STD performance using various bottleneck features estimated from our FFN and ResNet models. Previously, the best performance on QUESST 2014 database was obtained using monolingual bottleneck features estimated using FFNs [5]. We implemented those models to compare with multilingual features as well as corresponding ResNet based models.…”

Section: Experimental Analysismentioning

confidence: 99%

“…We evaluate the features estimated with these networks using QbE-STD as described in Section 5.3. Similar to [5], we did not employ any specific strategies to deal with different types of queries in QUESST 2014. The results are presented using C min nxe and M T W V metrics in Table 1.…”

Section: Monolingual Feature Performancementioning

confidence: 99%

“…The QbE-STD systems primarily involve the following two steps: (i) extract acoustic feature vectors from both the query and the audio document and (ii) employ those features to compute the likelihood of the query occurring somewhere in the audio document as a sub-sequence. Different types of acoustic features have been used for this task: spectral features [1,2], posterior features (posterior probability vector for phone or phone-like units) [3,4] as well as bottleneck features [5,6]. The matching likelihood is generally obtained by computing a frame-level similarity matrix between the query and each audio document using the corresponding feature The research is funded by the Swiss NSF project 'PHASER-QUAD', grant agreement number 200020-169398. vectors and employing a dynamic time warping (DTW) [4,5] or convolutional neural network (CNN) based matching technique [7].…”

Section: Introductionmentioning

confidence: 99%

“…Different types of acoustic features have been used for this task: spectral features [1,2], posterior features (posterior probability vector for phone or phone-like units) [3,4] as well as bottleneck features [5,6]. The matching likelihood is generally obtained by computing a frame-level similarity matrix between the query and each audio document using the corresponding feature The research is funded by the Swiss NSF project 'PHASER-QUAD', grant agreement number 200020-169398. vectors and employing a dynamic time warping (DTW) [4,5] or convolutional neural network (CNN) based matching technique [7]. Several variants of DTW have been used: Segmental DTW [1,3], Slope-constrained DTW [8], Sub-sequence DTW [9], Subspace-regularized DTW [10,11] etc.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Multilingual Bottleneck Features for Query by Example Spoken Term Detection

Ram

Miculicich

Bourlard

2019

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

View full text Add to dashboard Cite

State of the art solutions to query by example spoken term detection (QbE-STD) usually rely on bottleneck feature representation of the query and audio document to perform dynamic time warping (DTW) based template matching. Here, we present a study on QbE-STD performance using several monolingual as well as multilingual bottleneck features extracted from feed forward networks. Then, we propose to employ residual networks (ResNet) to estimate the bottleneck features and show significant improvements over the corresponding feed forward network based features. The neural networks are trained on GlobalPhone corpus and QbE-STD experiments are performed on a very challenging QUESST 2014 database.

show abstract

Section: Feed Forward Networkmentioning

confidence: 99%

Section: Experimental Analysismentioning

confidence: 99%

Section: Monolingual Feature Performancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multilingual Bottleneck Features for Query by Example Spoken Term Detection

Ram

Miculicich

Bourlard

2019

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

View full text Add to dashboard Cite

show abstract

Learning Acoustic Word Embeddings With Dynamic Time Warping Triplet Networks

et al. 2020

View full text Add to dashboard Cite

In the last years, acoustic word embeddings (AWEs) have gained significant interest in the research community. It applies specifically to the application of acoustic embeddings in the Query-by-Example Spoken Term Detection (QbE-STD) search and related word discrimination tasks. It has been shown that AWEs learned for the word or phone classification in one or several languages can outperform approaches that use dynamic time warping (DTW). In this paper, a new method of learning AWEs in the DTW framework is proposed. It employs a multitask triplet neural network to generate the AWEs. The triplet network learns acoustic representations of words through a comparison of DTW distances. In addition, a multitask objective, including a conventional word classification component, and a triplet loss component is proposed. The triplet loss component applies the DTW distance for the word discrimination task. The multitask objective ensures that the embeddings can be used with DTW directly. Experimental validation shows that the proposed approach is well-suited, but not necessarily restricted to the QbE-STD search. A comparison with several baseline methods shows that the new method leads to a significant improvement of the results on the word discrimination task. An evaluation of the word clustering in the learned embedding space is presented.

show abstract