Channel Factors Compensation in Model and Feature Domain for Speaker Recognition

Vair, Claudio; Colibro, Daniele; Castaldo, Fabio; Dalmasso, Emanuele; Laface, Pietro

doi:10.1109/odyssey.2006.248117

Cited by 64 publications

(29 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, HLDA is employed to decorrelate features and reduce the dimensionality from 52 to 39. Finally, a feature domain latent factor analysis (fLFA) (Vair et al, 2006) is applied to compensate the channel distortion. The performance measures are the same as NIST speaker recognition evaluation (NIST, 2010), using equal error rate (EER) and minimum detection cost function (DCF).…”

Section: Methodsmentioning

confidence: 99%

Discriminative Universal Background Model Training for Speaker Recognition

Zhang¹,

Lu²

2011

Speech and Language Technologies

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Discriminative Universal Background Model Training for Speaker Recognition

Zhang¹,

Lu²

2011

Speech and Language Technologies

View full text Add to dashboard Cite

“…Recently, in state-of-the-art language ID systems, a powerful technique called InterSession Compensation (ISC) has been proven to improve language ID performance dramatically [95]. For the perspective of language ID, inter-session variability can be defined as anything that makes one utterance in a particular language different from another.…”

Section: Inter-session Compensation (Isc)mentioning

confidence: 99%

Human and computer recognition of regional accents and ethnic groups from British English speech

Hanani

Russell

Carey

2013

Computer Speech & Language

View full text Add to dashboard Cite

Language Recognition Evaluation (LRE) tasks. This system is applied to the problems of regional accent recognition for British English, and ethnic group recognition within a particular accent. We compare the results with human performance and, for accent recognition, the 'text dependent' ACCDIST accent recognition measure. For the fourteen regional accents of British English in the ABI-1 corpus (good quality read speech), our language ID system achieves a recognition accuracy of 86.4%, compared with 95.18% for our best ACCDIST-based system and 58.24% for human listeners. The "Voices across Birmingham" corpus contains significant amounts of telephone conversational speech for the two largest ethnic groups in the city of Birmingham (UK), namely the 'Asian' and 'White' communities. Our language ID system distinguishes between these two groups with an accuracy of 94.3% compared with 90.24% for human listeners. Although direct comparison is difficult, it seems that our language ID system performs much better on the standard twelve class NIST 2003 Language Recognition Evaluation task or the two class ethnic group recognition task than on the fourteen class regional accent recognition task. We conclude that automatic accent recognition is a challenging task for speech technology, and that the use of natural conversational speech may be advantageous for these types of paralinguistic task.One issue with conventional approaches to language ID that use high-order Gaussian Mixture Models (GMMs) and high-dimensional feature vectors is the amount of computing power that they require. Currently, multi-core Graphics Processing Units (GPUs) provide a possible solution at very little cost. In this thesis we also explore the application of GPUs to speech signal and pattern processing, using language ID as a vehicle to demonstrate their benefits. Realisation of the full potential of GPUs requires both effective coding of predetermined algorithms, and, in cases where there is a choice, selection of the algorithm or technique for a specific function that is most able to exploit the properties of the GPU. We demonstrate these principles using the NIST LRE 2003 task, which involves processing over 600 hours of speech. We focus on two parts of the system, namely the acoustic classifier, which is based on a 2048 component GMM, and the acoustic feature extraction process. In the case of the latter we compare a conventional FFT-based analysis with an FIR filter bank, both in terms of their ability to exploit the GPU architecture and language ID performance. With no increase in error rate our GPU based system, with an FIR-based front-end, completes the full NIST LRE 2003 task in 16 hours, compared with 180 hours for the more conventional FFT-based system on a standard CPU (a speed up factor of more than 11).

show abstract

“…Factor analysis techniques Latent Factor Analysis (LFA) and Nuisance Attribute Projection (NAP), proposed by Vair et al in [15] are used to remove undesired variation coming from a lowdimensional source.…”

Section: Literacy Reviews Of Previous Researchmentioning

confidence: 99%

GMM based Language Identification using MFCC and SDC Features

Sarmah¹,

Bhattacharjee²

2014

IJCA

View full text Add to dashboard Cite

-Language Identification (LID) is one of the most popular areas of research in speech signal processing. Now a day's lots of approaches have been used to improve performance of LID system which includes Parallel Phone Recognition Language Modeling (PPRLM), Support Vector Machine (SVM) and general Gaussian Mixture Model (GMM) etc. The state-of-art LID system has been utilised lots of feature vectors like LPCC, MFCC, SDC and prosodic. Although fusion of prosodic features with MFCC features shows some improvement in the performance of the LID system. But still it is not sufficient. In this paper, a baseline system for the LID system in multilingual environments has been developed using GMM as a classifier and MFCC combined with Shifted-DeltaCepstral (SDC) as front end processing feature vectors. In this works, we used the Arunachali Language Speech Database (ALS-DB), a multilingual and multichannel speech corpus which was recently collected from the four local languages namely Adi, Apatani, Galo and Nyishi in Arunachal Pradesh including Hindi and English as secondary languages.The performance of the LID system has been improved by combing MFCC and SDC features than its individual performances. The minimum ERR rates for the features MFCC and SDC individually are 19.70% and 11.83% respectively while minimum ERR rate for the combined features both MFCC and SDC is 6.40%.Approximately 15.00% and 6.00% of performance of the LID system has been improved while using the combining features of MFCC with SDC over the baseline systems that using MFCC and SDC features in individual respectively.

show abstract

Channel Factors Compensation in Model and Feature Domain for Speaker Recognition

Cited by 64 publications

References 12 publications

Discriminative Universal Background Model Training for Speaker Recognition

Discriminative Universal Background Model Training for Speaker Recognition

Human and computer recognition of regional accents and ethnic groups from British English speech

GMM based Language Identification using MFCC and SDC Features

Contact Info

Product

Resources

About