Castsearch - Context Based Spoken Document Retrieval

Mølgaard, Lasse Lohilahti; Jørgensen, Kasper Winther; Hansen, Lars Kai

doi:10.1109/icassp.2007.367171

Cited by 8 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Retrieval of broadcast news using ASR transcripts approaches the performance of text-based retrieval (Garofolo et al, 2000;Koumpis and Renals, 2005). Access to broadcast news content in the podosphere has attracted research attention (Mølgaard et al, 2007) and news and radio content remains an important application area of online audio search (e.g. www.audioclipping.de/).…”

Section: Spoken Content Retrievalmentioning

confidence: 99%

“…Due to the time consuming assessment process, carrying out spoken document retrieval experiments on sets containing significantly less data or with an alternative evaluation process that is system-specific or not yet widely used is also commonly used in the literature (cf. Mølgaard et al, 2007;Mizuno et al, 2008;Alberti et al, 2009). Our work is most closely related to investigations using audio collections containing spontaneous conversational speech that include both spoken content and metadata.…”

Section: Spoken Content Retrievalmentioning

confidence: 99%

See 1 more Smart Citation

Podcast search: user goals and retrieval technologies

Besser¹,

Larson

Hofmann³

2010

Online Information Review

View full text Add to dashboard Cite

Purpose -This research aims to identify users' goals and strategies when searching for podcasts and their impact on the design of podcast retrieval technology. In particular, the paper seeks to explore the potential to address user goals with indexing based on podcast metadata and automatic speech recognition (ASR) transcripts. Design/methodology/approach -The paper conducted a user study to obtain an overview of podcast search behaviour and goals, using a multi-method approach of an online survey, a diary study, and contextual interviews. In a subsequent podcast retrieval experiment, the paper investigated the retrieval performance of the two choices of indexing features for search goals identified during the study. Findings -The paper found that study participants used a variety of search strategies, partially influenced by available tools and their perceptions of these tools. Furthermore the experimental results revealed that retrieval using ASR transcripts performed significantly better than metadata-based searching. However, a detailed result analysis suggested that the efficacy of the indexing methods was search-goal dependent.Research limitations/implications -The research constitutes a step towards a future framework for investigating user needs and addressing them in an experimental set-up. It was primarily qualitative and exploratory in nature. Practical implications -Podcast search engines require evidence about suitable indexing methods in order to make an informed decision concerning whether it is worth the resources to generate speech recognition transcripts. Originality/value -Systematic studies of podcast searching have not previously been reported. Investigations of this kind hold the potential to optimise podcast retrieval in the long term.

show abstract

Section: Spoken Content Retrievalmentioning

confidence: 99%

Section: Spoken Content Retrievalmentioning

confidence: 99%

Podcast search: user goals and retrieval technologies

Besser¹,

Larson

Hofmann³

2010

Online Information Review

View full text Add to dashboard Cite

show abstract

“…This technique has been applied widely elsewhere to genetics [14] [32] [49], document retrieval [46], document clustering [68] and image classification [27] [39]. We apply it here to our multimodal data, including the demographic variables in our model.…”

Section: Introductionmentioning

confidence: 99%

Non-negative matrix factorization of multimodal MRI, fMRI and phenotypic data reveals differential changes in default mode subnetworks in ADHD

et al. 2014

View full text Add to dashboard Cite

In the multimodal neuroimaging framework, data on a single subject are collected from inherently different sources such as functional MRI, structural MRI, behavioral and/or phenotypic information. The information each source provides is not independent; a subset of features from each modality maps to one or more common latent dimensions, which can be interpreted using generative models. These latent dimensions, or “topics,” provide a sparse summary of the generative process behind the features for each individual. Topic modeling, an unsupervised generative model, has been used to map seemingly disparate features to a common domain. We use Non-Negative Matrix Factorization (NMF) to infer the latent structure of multimodal ADHD data containing fMRI, MRI, phenotypic and behavioral measurements. We compare four different NMF algorithms and find the sparsest decomposition is also the most differentiating between ADHD and healthy patients. We identify dimensions that map to interpretable, recognizable dimensions such as motion, default mode network activity, and other such features of the input data. For example, structural and functional graph theory features related to default mode subnetworks clustered with the ADHD inattentive diagnosis. Structural measurements of the default mode network (DMN) regions such as the posterior cingulate, precuneus, and parahippocampal regions were all related to the ADHD-Inattentive diagnosis. Ventral DMN subnetworks may have more functional connections in ADHD-I, while dorsal DMN may have less. We also find that ADHD topics may be dependent upon diagnostic site, raising the possibility of the diagnostic differences across geographic locations. We assess our findings in light of the ADHD-200 classification competition, and contrast our unsupervised, nominated topics with previously published supervised learning methods. Finally, we demonstrate the validity of these latent variables as biomarkers by using them for classification of ADHD in 730 patients. Cumulatively, this manuscript addresses how multi-modal data in ADHD can be interpreted by latent dimensions.

show abstract

“…A recent approach to query expansion using a parallel corpus is presented by [189]. This approach uses topics discovered by way of dimensionality reduction in order to enrich user queries.…”

Section: Expansion Techniquesmentioning

confidence: 99%

Automatic Summarization

Larson

2012

FNT in Information Retrieval

View full text Add to dashboard Cite

Castsearch - Context Based Spoken Document Retrieval

Cited by 8 publications

References 6 publications

Podcast search: user goals and retrieval technologies

Podcast search: user goals and retrieval technologies

Non-negative matrix factorization of multimodal MRI, fMRI and phenotypic data reveals differential changes in default mode subnetworks in ADHD

Automatic Summarization

Contact Info

Product

Resources

About