A Speaker Pruning Algorithm for Real-Time Speaker Identification

Kinnunen, Tomi; Karpov, Evgeny; Fränti, Pasi

doi:10.1007/3-540-44887-x_75

Cited by 10 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speaker pruning [19], [22], [23] can be used to reduce the search space by dropping out unlikely speakers "on the fly" as more speech data arrives. We survey and compare several speaker pruning variants.…”

Section: Contributions Of This Studymentioning

confidence: 99%

See 1 more Smart Citation

Real-time speaker identification and verification

Kinnunen

Karpov

Fränti

2006

IEEE Trans. Audio Speech Lang. Process.

149

View full text Add to dashboard Cite

Abstract-In speaker identification, most of the computation originates from the distance or likelihood computations between the feature vectors of the unknown speaker and the models in the database. The identification time depends on the number of feature vectors, their dimensionality, the complexity of the speaker models and the number of speakers. In this paper, we concentrate on optimizing vector quantization (VQ) based speaker identification. We reduce the number of test vectors by pre-quantizing the test sequence prior to matching, and the number of speakers by pruning out unlikely speakers during the identification process. The best variants are then generalized to Gaussian mixture model (GMM) based modeling. We apply the algorithms also to efficient cohort set search for score normalization in speaker verification. We obtain a speed-up factor of 16:1 in the case of VQ-based modeling with minor degradation in the identification accuracy, and 34:1 in the case of GMM-based modeling. An equal error rate of 7 % can be reached in 0.84 seconds on average when the length of test utterance is 30.4 seconds.

show abstract

Section: Contributions Of This Studymentioning

confidence: 99%

“…We consider next the following simple pruning variants: static pruning [23], hierarchical pruning [22], and adaptive pruning [23]. We also propose a novel pruning variant called confidence-based pruning.…”

Section: Speaker Pruningmentioning

confidence: 99%

Real-time speaker identification and verification

Kinnunen

Karpov

Fränti

2006

IEEE Trans. Audio Speech Lang. Process.

149

View full text Add to dashboard Cite

show abstract

“…This subset can be selected randomly and also it can be the average of different frames features or the representative of a clustering method on the feature vector. Another technique is speaker pruning [6] which is a step by step method to identify the speaker. In each step, a small portion of the test utterance is used to prune the speaker set and at the last step a unique speaker is resulted.…”

Section: Introductionmentioning

confidence: 99%

A fast two-level Speaker Identification method employing sparse representation and GMM-based methods

Zeinali¹,

Sameti²,

Khaki

et al. 2012

2012 11th International Conference on Information Science, Signal Processing and Their Applications (ISSPA)

View full text Add to dashboard Cite

In large population Speaker Identification (SI), computation time has become one of the most important issues in recent real time systems. Test computation time depends on the cost of likelihood computation between test features and registered speaker models. For real time application of speaker identification, system must identify an unknown speaker quickly. Hence the conventional SI methods cannot be used. In this paper, we propose a twostep method that utilizes two different identification methods. In the first step we use Nearest Neighbor method to decrease the search space. In the second step we use GMM-based SI methods to specify the target speaker. We achieved 3.5× speed-ups without any loss of accuracy using the proposed method. If the number of best speaker is reduced, the Identification accuracy decreases. So, there is a trade-off between accuracy and speed-up.

show abstract