Feature classification by means of deep belief networks for speaker recognition

Safari, Pooyan; Ghahabi, Omid; Hernando, Javier

doi:10.1109/eusipco.2015.7362758

Cited by 10 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, the adaptation step drives the URBM model in a speaker-specific direction. This kind of adaptation technique is successfully applied in References [25,[40][41][42]. The adaptation is also carried out by the CD-1 algorithm.…”

Section: Rbm Adaptationmentioning

confidence: 99%

Restricted Boltzmann Machine Vectors for Speaker Clustering and Tracking Tasks in TV Broadcast Shows

2019

Self Cite

View full text Add to dashboard Cite

Restricted Boltzmann Machines (RBMs) have shown success in both the front-end and backend of speaker verification systems. In this paper, we propose applying RBMs to the front-end for the tasks of speaker clustering and speaker tracking in TV broadcast shows. RBMs are trained to transform utterances into a vector based representation. Because of the lack of data for a test speaker, we propose RBM adaptation to a global model. First, the global model—which is referred to as universal RBM—is trained with all the available background data. Then an adapted RBM model is trained with the data of each test speaker. The visible to hidden weight matrices of the adapted models are concatenated along with the bias vectors and are whitened to generate the vector representation of speakers. These vectors, referred to as RBM vectors, were shown to preserve speaker-specific information and are used in the tasks of speaker clustering and speaker tracking. The evaluation was performed on the audio recordings of Catalan TV Broadcast shows. The experimental results show that our proposed speaker clustering system gained up to 12% relative improvement, in terms of Equal Impurity (EI), over the baseline system. On the other hand, in the task of speaker tracking, our system has a relative improvement of 11% and 7% compared to the baseline system using cosine and Probabilistic Linear Discriminant Analysis (PLDA) scoring, respectively.

show abstract

Section: Rbm Adaptationmentioning

confidence: 99%

Restricted Boltzmann Machine Vectors for Speaker Clustering and Tracking Tasks in TV Broadcast Shows

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…During adaptation the RBM model of the speaker segment is initialized with the parameters (weights and biases) of the URBM. This kind of adaptation technique is successfully applied in [18,19]. The adaptation is also carried out using CD-1 algorithm.…”

Section: Rbm Adaptationmentioning

confidence: 99%

Restricted Boltzmann Machine Vectors for Speaker Clustering

Khan¹,

Safari²,

Hernando³

2018

IberSPEECH 2018

Self Cite

View full text Add to dashboard Cite

Restricted Boltzmann Machines (RBMs) have been used both in the front-end and backend of speaker verification systems. In this work, we apply RBMs as a front-end in the context of speaker clustering. Speakers' utterances are transformed into a vector representation by means of RBMs. These vectors, referred to as RBM vectors, have shown to preserve speakerspecific information and are used for the task of speaker clustering. In this work, we perform the traditional bottom-up Agglomerative Hierarchical Clustering (AHC). Using the RBM vector representation of speakers, the performance of speaker clustering is improved. The evaluation has been performed on the audio recordings of Catalan TV Broadcast shows. The experimental results show that our proposed system outperforms the baseline i-vectors system in terms of Equal Impurity (EI). Using cosine scoring, a relative improvement of 11% and 12% are achieved for average and single linkage clustering algorithms respectively. Using PLDA scoring, the RBM vectors achieve a relative improvement of 11% compared to i-vectors for the single linkage algorithm.

show abstract

“…In other words, the URBM is adapted to the data of each speaker. The idea of this kind of adaptation has also shown success in [11,12,13,14] to initialize the parameters of DNNs for classification purposes. Figure 3 shows the weight matrices for URBM along with its adapted versions for two randomly selected speakers.…”

Section: Rbm Adaptationmentioning

confidence: 99%

“…From our experience in [14], it has been decided to work on the spectral features instead of Filter-Bank Energy (FBE) features. Frequency Filtering (FF) [27] features, have been used as spectral features in this work.…”

Section: Database and Setupmentioning

confidence: 99%

See 1 more Smart Citation

From Features to Speaker Vectors by means of Restricted Boltzmann Machine Adaptation

Safari¹,

Ghahabi²,

Hernando³

2016

The Speaker and Language Recognition Workshop (Odyssey 2016)

Self Cite

View full text Add to dashboard Cite

Restricted Boltzmann Machines (RBMs) have shown success in different stages of speaker recognition systems. In this paper, we propose a novel framework to produce a vector-based representation for each speaker, which will be referred to as RBMvector. This new approach maps the speaker spectral features to a single fixed-dimensional vector carrying speaker-specific information. In this work, a global model, referred to as Universal RBM (URBM), is trained taking advantage of RBM unsupervised learning capabilities. Then, this URBM is adapted to the data of each speaker in the development, enrolment and evaluation datasets. The network connection weights of the adapted RBMs are further concatenated and subject to a whitening with dimension reduction stage to build the speaker vectors. The evaluation is performed on the core test condition of the NIST SRE 2006 database, and it is shown that RBM-vectors achieve 15% relative improvement in terms of EER compared to i-vectors using cosine scoring. The score fusion with i-vector attains more than 24% relative improvement. The interest of this result for score fusion yields on the fact that both vectors are produced in an unsupervised fashion and can be used instead of i-vector/PLDA approach, when no data label is available. Results obtained for RBM-vector/PLDA framework is comparable with the ones from i-vector/PLDA. Their score fusion achieves 14% relative improvement compared to i-vector/PLDA.

show abstract

Feature classification by means of deep belief networks for speaker recognition

Cited by 10 publications

References 17 publications

Restricted Boltzmann Machine Vectors for Speaker Clustering and Tracking Tasks in TV Broadcast Shows

Restricted Boltzmann Machine Vectors for Speaker Clustering and Tracking Tasks in TV Broadcast Shows

Restricted Boltzmann Machine Vectors for Speaker Clustering

From Features to Speaker Vectors by means of Restricted Boltzmann Machine Adaptation

Contact Info

Product

Resources

About