On model quality and evaluation in speaker verification

Koolwaaij, Johan; Boves, L.W.J.; Jongebloed, Hans; Os, Els Den

doi:10.1109/icassp.2000.860220

Cited by 7 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another different approach [2] to check model quality introduces the distance Z between LLR scores from clients and from impostors for a given model:…”

Section: Theoretical Approachmentioning

confidence: 99%

See 1 more Smart Citation

A New On-Line Model Quality Evaluation Method for Speaker Verification

Saeta¹,

Hernando

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The accurate selection of the utterances is very important to obtain right estimated speaker models in speaker verification. In this sense, it is important to determine the quality of the utterances and to establish a mechanism to automatically discard or accept them. In real-time speaker verification applications, it is decisive to obtain on-line measures to ask the speaker for more data if necessary. In this paper, we introduce a new on-line quality method based on a male and a female Universal Background Model (UBM). These two models act as a reference for new incoming utterances in order to decide if they can be used to estimate the speaker model or not. Text-dependent experiments have been carried out by using a telephonic multi-session database in Spanish. The database has been recorded by the authors and has 184 speakers.

show abstract

“…Another different approach [2] to check model quality introduces the distance Z between LLR scores from clients and from impostors for a given model:…”

Section: Theoretical Approachmentioning

confidence: 99%

“…The 'leave-one-out' method [1] has the problem of an excessive computational cost. The Z method [2] uses impostor data. The method introduced by the authors in [3] overcomes these two problems but, as it happens with the first two methods, it needs the speaker model to evaluate quality.…”

Section: Introductionmentioning

confidence: 99%

A New On-Line Model Quality Evaluation Method for Speaker Verification

Saeta¹,

Hernando

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The fusion function is adapted to rely more on the biometric traits that are less prone to error in noisy conditions. Other studies concerned with quality estimations in the field of speaker recognition include: [7] in which model quality assessment methods are studied to adapt the model training process and [1] in which quality-based feature selection is proposed to improve the performance of speaker recognition systems.…”

Section: Introductionmentioning

confidence: 99%

Using quality measures for multilevel speaker recognition

Garcia‐Romero¹,

Fiérrez-Aguilar²,

González-Rodríguez³

et al. 2006

Computer Speech & Language

View full text Add to dashboard Cite

El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription Conventional user-independent multilevel Support Vector Machine (SVM) score fusion is also adapted for the inclusion of quality information in the fusion process.In particular, quality measures meeting three different goodness criteria: SN R, F 0 deviations and the IT U P.563 objective speech quality assessment are used in the speaker recognition process. Experiments carried out in the Switchboard-I database assess the benefits of the proposed quality-guided recognition approach for both the score computation and score fusion stages.

show abstract

“…The overall analysis of access calls showed that the false reject rate for individual clients were very high for a substantial pro portion of the callers [4], [5]. It turned out that these errors were related to the quality of the speaker models after enrolment [6]. This model quality is strongly dependent on consistent behav iour of the user during enrolment.…”

Section: Introductionmentioning

confidence: 99%

Speaker verification in operational environments - monitoring for improved service operation

Gu¹,

Jongebloed²,

Iskra³

et al. 2000

6th International Conference on Spoken Language Processing (ICSLP 2000)

View full text Add to dashboard Cite

There are very few, if any, published accounts of practical expe rience with Speaker Verification as a means to provide secure access to telematics services. Yet, there is no reason to expect that Speaker Verification is very different from speech recogni tion, for which many deployed services have shown the need for close and intensive on-line monitoring during the time when the service becomes operational. In this paper we present our expe rience with a monitoring scheme for Speaker Verification dur ing the field test of a financial investment game. Many of the issues that were monitored were suggested by our experience with a semi-operational service, viz. free access to Directory Assistance for visually impaired. A newly developed enrolment procedure, that can flag potentially weak speaker models, is an essential part of the monitoring procedure.

show abstract

On model quality and evaluation in speaker verification

Cited by 7 publications

References 6 publications

A New On-Line Model Quality Evaluation Method for Speaker Verification

A New On-Line Model Quality Evaluation Method for Speaker Verification

Using quality measures for multilevel speaker recognition

Speaker verification in operational environments - monitoring for improved service operation

Contact Info

Product

Resources

About