An audio indexing system for election video material

Alberti, Christopher; Bacchiani, Michiel; Bezman, A.; Chelba, Ciprian; Drofa, Anastassia; Liao, Hank; Moreno, Pedro J.; Power, Ted; Sahuguet, Arnaud; Shugrina, Maria; Siohan, Olivier

doi:10.1109/icassp.2009.4960723

Cited by 52 publications

(40 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Search of this less well-planned content has formed the basis of more recent work in SCR. Examples include search of meetings, [23,150], call center recordings [176], collections of interviews [33,61], historical archives [100], lectures [86], podcasts [207], and political speeches [2].…”

Section: Use Scenariosmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Summarization

Larson

2012

FNT in Information Retrieval

View full text Add to dashboard Cite

Section: Use Scenariosmentioning

confidence: 99%

“…The Google election gadget [2], which offered search functionality for political speeches during the 2008 US elections, also displayed hints for users. It provided information about the scope and the functionality of the system by prompting users with the question "What did the candidates say?"…”

Section: Query Entrymentioning

confidence: 99%

Automatic Summarization

Larson

2012

FNT in Information Retrieval

View full text Add to dashboard Cite

“…The software tools used for acoustic modeling and runtime Viterbi decoding were those developed at Google for large-vocabulary speech recognition applications [20]. The algorithms for constructing the finitestate transducer representation of the song database were implemented in the OpenFst toolkit [21].…”

Section: Methodsmentioning

confidence: 99%

Efficient and Robust Music Identification With Weighted Finite-State Transducers

Mohri

Moreno

Weinstein

2010

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-We present an approach to music identification based on weighted finite-state transducers and Gaussian mixture models, inspired by techniques used in large-vocabulary speech recognition. Our modeling approach is based on learning a set of elementary music sounds in a fully unsupervised manner. While the space of possible music sound sequences is very large, our method enables the construction of a compact and efficient representation for the song collection using finite-state transducers.This paper gives a novel and substantially faster algorithm for the construction of factor transducers, the key representation of song snippets supporting our music identification technique. The complexity of our algorithm is linear with respect to the size of the suffix automaton constructed. Our experiments further show that it helps speed up the construction of the weighted suffix automaton in our task by a factor of 17 with respect to our previous method using the intermediate steps of determinization and minimization. We show that, using these techniques, a large-scale music identification system can be constructed for a database of over 15 000 songs while achieving an identification accuracy of 99.4% on undistorted test data, and performing robustly in the presence of noise and distortions.

show abstract

“…Recent work which has focused on the automatic transcription or indexing of multi-genre broadcast data has included work on the automatic transcription of podcasts and other web audio [1], automatic transcription of YouTube [2,3], the MediaEval rich speech retrieval evaluation which used blip.tv semi-professional user created content [4], and the automatic tagging of a large radio archive [5]. This paper concerns the automatic transcription of multigenre content from the BBC archive.…”

Section: Introductionmentioning

confidence: 99%

Transcription of multi-genre media archives using out-of-domain data

Bell

Gales

Lanchantin

et al. 2012

2012 IEEE Spoken Language Technology Workshop (SLT)

View full text Add to dashboard Cite

We describe our work on developing a speech recognition system for multi-genre media archives. The high diversity of the data makes this a challenging recognition task, which may benefit from systems trained on a combination of in-domain and out-of-domain data. Working with tandem HMMs, we present Multi-level Adaptive Networks (MLAN), a novel technique for incorporating information from out-of-domain posterior features using deep neural networks. We show that it provides a substantial reduction in WER over other systems, with relative WER reductions of 15% over a PLP baseline, 9% over in-domain tandem features and 8% over the best out-of-domain tandem features.

show abstract

An audio indexing system for election video material

Cited by 52 publications

References 8 publications

Automatic Summarization

Automatic Summarization

Efficient and Robust Music Identification With Weighted Finite-State Transducers

Transcription of multi-genre media archives using out-of-domain data

Contact Info

Product

Resources

About