AMIRAL: A Block-Segmental Multirecognizer Architecture for Automatic Speaker Recognition

Fredouille, Corinne; Bonastre, Jean-François; Merlin, Téva

doi:10.1006/dspr.1999.0367

Cited by 12 publications

(7 citation statements)

References 31 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Like in other pattern classification tasks, combining information from multiple sources of evidence -a technique called fusion -has been widely applied in speaker recognition [5,80,45,49,63,69,118,149,166,190,200,207]. Typically, a number of different feature sets are first extracted from the speech signal; then an individual classifier is used for each feature set; following that the sub-scores or decisions are combined.…”

Section: Fusionmentioning

confidence: 99%

An overview of text-independent speaker recognition: From features to supervectors

Kinnunen¹,

Li²

2010

Speech Communication

1,224

733

View full text Add to dashboard Cite

This paper gives an overview of automatic speaker recognition technology, with an emphasis on text-independent recognition. Speaker recognition has been studied actively for several decades. We give an overview of both the classical and the state-of-the-art methods. We start with the fundamentals of automatic speaker recognition, concerning feature extraction and speaker modeling. We elaborate advanced computational techniques to address robustness and session variability. The recent progress from vectors towards supervectors opens up a new area of exploration and represents a technology trend. We also provide an overview of this recent development and discuss the evaluation methodology of speaker recognition systems. We conclude the paper with discussion on future directions.

show abstract

Section: Fusionmentioning

confidence: 99%

An overview of text-independent speaker recognition: From features to supervectors

Kinnunen¹,

Li²

2010

Speech Communication

1,224

733

View full text Add to dashboard Cite

show abstract

“…-The LIA system computes the utterance score only from a subset of frames, taking into account the histogram of the frame-based likelihood values and performs short-term cepstral mean subtraction (using 3-s windows) in order to adapt this channel compensation technique to the fact that the two handsets have distinct transfer functions [4]; -The IRISA system uses ML estimates of the client models rather than MAP estimates, as was the case for the one-speaker task, and does not use z-normalization [20].…”

Section: Two-speaker Detectionmentioning

confidence: 99%

“…A decision is then made on the presence of the target speaker by comparing the average score of the selected blocks to a first threshold. If the target speaker is detected, a second pass is carried out to label each block as target or nontarget, by comparison of the score to a second threshold [4].…”

Section: Speaker Trackingmentioning

confidence: 99%

“…The results obtained at the official evaluation are then analyzed in Section 4. The systems are not described in full detail since most of them are presented in articles specific to each site, published in this volume, which will be refered to whenever necessary [4,6,10,14,15,20]. This article therefore concentrates on the contrastive comparison of the performances.…”

Section: Introductionmentioning

confidence: 97%

See 1 more Smart Citation

The ELISA Systems for the NIST'99 Evaluation in Speaker Detection and Tracking

Nedić¹,

Bimbot²,

Blouet³

et al. 2000

Digital Signal Processing

View full text Add to dashboard Cite

“…All the speaker segmentation systems were developed in the framework of the ELISA consortium using AMIRAL, the LIA Speaker Recognition System [2].…”

Section: Speaker Segmentation Systemsmentioning

confidence: 99%

The ELISA consortium approaches in broadcast news speaker segmentation during the NIST 2003 rich transcription evaluation

Moraru

Meignier

Fredouille

et al.

2004 IEEE International Conference on Acoustics, Speech, and Signal Processing

View full text Add to dashboard Cite

This paper presents the ELISA consortium activities in automatic speaker segmentation also known as speaker diarization during the NIST Rich Transcription (RT) 2003 evaluation. The experiments were conducted on real broadcast news data (HUB4). Two different approaches from CLIPS and LIA laboratories are presented and different possibilities of combining them are investigated, in the framework of ELISA consortium. The system submitted as ELISA primary system obtained the second lower segmentation error rate compared to the other RT03-participant primary systems. Another ELISA system submitted as secondary system outperformed the best primary system and obtained the lowest speaker segmentation error rate.

show abstract

AMIRAL: A Block-Segmental Multirecognizer Architecture for Automatic Speaker Recognition

Cited by 12 publications

References 31 publications

An overview of text-independent speaker recognition: From features to supervectors

An overview of text-independent speaker recognition: From features to supervectors

The ELISA Systems for the NIST'99 Evaluation in Speaker Detection and Tracking

The ELISA consortium approaches in broadcast news speaker segmentation during the NIST 2003 rich transcription evaluation

Contact Info

Product

Resources

About