The VOiCES from a Distance Challenge 2019

Nandwana, Mahesh Kumar; Hout, Julien van; Richey, Colleen; McLaren, Mitchell; Barrios, María Auxiliadora; Lawson, Aaron

doi:10.21437/interspeech.2019-1837

Cited by 54 publications

(64 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use two subsets of this data corpus, the development portion of the VOiCES challenge data [24] referred to as V19-dev and the evaluation portion referred to as V19-eval. V19-dev is used for probing experiments as discussed in Section 4.2, as it contains annotations for 200 speaker labels, 12 microphone locations and 4 noise types (none, babble, television, music).…”

Section: Datasetsmentioning

confidence: 99%

“…The experimental setup for the controlled conditions is shown in Fig 2. As mentioned in Section 3, the green circles, numbered 1-12, represent microphones located at various distances from the main loudspeaker. In all experiments, the enrolment utterances were collected from source data used to playback from the loudspeaker, consistent with [24]. We choose a different set of test utterances depending on the experiment being performed.…”

Section: Setupmentioning

confidence: 99%

See 1 more Smart Citation

Robust Speaker Recognition Using Unsupervised Adversarial Invariance

Peri

Pal

Jati

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial invariance architecture to train a network that maps speaker embeddings extracted using a pretrained model onto two lower dimensional embedding spaces. The embedding spaces are learnt to disentangle speaker-discriminative information from all other information present in the audio recordings, without supervision about the acoustic conditions. We analyze the robustness of the proposed embeddings to various sources of variability present in the signal for speaker verification and unsupervised clustering tasks on a large-scale speaker recognition corpus. Our analyses show that the proposed system substantially outperforms the baseline in a variety of challenging acoustic scenarios. Furthermore, for the task of speaker diarization on a real-world meeting corpus, our system shows a relative improvement of 36% in the diarization error rate compared to the state-of-the-art baseline.

show abstract

Section: Datasetsmentioning

confidence: 99%

Section: Setupmentioning

confidence: 99%

Robust Speaker Recognition Using Unsupervised Adversarial Invariance

Peri

Pal

Jati

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Similar to mic-tel adaptation work we added noise to the target domain data (SITW dev rev) with the same procedure mentioned in section 3.2. For evaluation, we also used a recent far field VOiCES corpus [25,26]. We did not add noise to the evaluation corpora.…”

Section: Source and Target Domain Datasetsmentioning

confidence: 99%

Low-Resource Domain Adaptation for Speaker Recognition Using Cycle-Gans

Nidadavolu

Kataria

Villalba

et al. 2019

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

View full text Add to dashboard Cite

Current speaker recognition technology provides great performance with the x-vector approach. However, performance decreases when the evaluation domain is different from the training domain, an issue usually addressed with domain adaptation approaches. Recently, unsupervised domain adaptation using cycle-consistent Generative Adversarial Networks (CycleGAN) has received a lot of attention. Cycle-GAN learn mappings between features of two domains given non-parallel data. We investigate their effectiveness in low resource scenario i.e. when limited amount of target domain data is available for adaptation, a case unexplored in previous works. We experiment with two adaptation tasks: microphone to telephone and a novel reverberant to clean adaptation with the end goal of improving speaker recognition performance. Number of speakers present in source and target domains are 7000 and 191 respectively. By adding noise to the target domain during CycleGAN training, we were able to achieve better performance compared to the adaptation system whose CycleGAN was trained on a larger target data. On reverberant to clean adaptation task, our models improved EER by 18.3% relative on VOiCES dataset compared to a system trained on clean data. They also slightly improved over the state-of-the-art Weighted Prediction Error (WPE) de-reverberation algorithm.

show abstract

“…This makes the deployment of Speaker Verification (SV) systems challenging. To address this, several challenges were organized recently such as NIST Speaker Recognition Evaluation (SRE) 2019, VOiCES from a Distance Challenge [2], and VoxCeleb Speaker Recognition Challenge (VoxSRC) 2019. We consider acoustic feature enhancement as a solution to this problem.…”

Section: Introductionmentioning

confidence: 99%

Feature Enhancement with Deep Feature Losses for Speaker Verification

Kataria

Nidadavolu

Villalba

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Speaker Verification still suffers from the challenge of generalization to novel adverse environments. We leverage on the recent advancements made by deep learning based speech enhancement and propose a feature-domain supervised denoising based solution. We propose to use Deep Feature Loss which optimizes the enhancement network in the hidden activation space of a pre-trained auxiliary speaker embedding network. We experimentally verify the approach on simulated and real data. A simulated testing setup is created using various noise types at different SNR levels. For evaluation on real data, we choose BabyTrain corpus which consists of children recordings in uncontrolled environments. We observe consistent gains in every condition over the state-of-the-art augmented Factorized-TDNN x-vector system. On BabyTrain corpus, we observe relative gains of 10.38% and 12.40% in minDCF and EER respectively.

show abstract

The VOiCES from a Distance Challenge 2019

Cited by 54 publications

References 22 publications

Robust Speaker Recognition Using Unsupervised Adversarial Invariance

Robust Speaker Recognition Using Unsupervised Adversarial Invariance

Low-Resource Domain Adaptation for Speaker Recognition Using Cycle-Gans

Feature Enhancement with Deep Feature Losses for Speaker Verification

Contact Info

Product

Resources

About