The MIT-LL, JHU and LRDE NIST 2016 Speaker Recognition Evaluation System

Torres-Carrasquillo, Pedro A.; Richardson, F. S.; Nercessian, Shahan; Sturim, Douglas E.; Campbell, William M.; Gwon, Youngjune; Vattam, Swaroop; Dehak, Najim; Mallidi, Harish; Nidadavolu, Phani Sankar; Li, Ruizhi; Dehak, Réda

doi:10.21437/interspeech.2017-537

Cited by 14 publications

(11 citation statements)

References 11 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…x / A H z u c P e L G P r w = = < / l a t e x i t > < l a t e x i t s h a 1 _ b a s e 6 4 = " 9 D u 1 Y q W L w K K g y y 5 B 7 a v S X + H Y 1 F 8 = " > A A A B 7…”

Section: A D G Q 3 / H M / / G a N T Q C W T V L W 3 K 5 L 5 Y C K Z mentioning

confidence: 99%

“…The pitch period (the reciprocal of F0) determines the harmonic structure of voiced speech, while the pitch variation over different speech sounds leads to speech prosody. F0 estimation is an essential technique for speech analysis and generation, including speech synthesis [1], voice conversion [2], prosody analysis [3], speech coding [4], modelbased speech enhancement [5], [6] and speaker and language identification [7], [8]. Methods or devices that estimate F0 from short-time segments of speech are known as F0 trackers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Statistical Regression Models for Noise Robust F0 Estimation Using Recurrent Deep Neural Networks

Kato

Kinnunen

2019

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

The fundamental frequency (F0) in a speech signal, which corresponds to pitch, is one of the key features involved in a variety of speech processing tasks. Therefore, accurate F0 estimation has remained an important problem to be solved over decades. However, this problem is difficult, especially in low signal-to-noise ratio (SNR) conditions with unknown noise. In this work, we propose new approaches to noise-robust F0 estimation using recurrent neural networks (RNNs). Recent F0 estimation studies exploit deep neural networks (DNNs), including RNNs, to classify acoustic features into quantized frequency states. In contrast to these classification approaches, we put forward a regression method for F0 tracking, which is accomplished with RNNs. To this end, we propose two variants. Our first model predicts the (scalar) F0 value directly from a spectrum, while our second model predicts a target sinusoidal waveform (with the desired F0) from the raw speech waveform. Our experiments with the pitch tracking database from Graz University of Technology (PTDB-TUG), contaminated by additive noise (NOISEX-92), demonstrate the improvement of the proposed approaches in terms of the gross pitch error (GPE) and fine pitch error (FPE) rates by more than 35 % at SNRs between-10 dB and +10 dB against a well-known, noise-robust F0 tracker, PEFAC. Furthermore, our methods outperform state-of-the-art neural network-based approaches by more than 15 % in terms of both the FPE and GPE rates over the abovementioned SNR range.

show abstract

“…x / A H z u c P e L G P r w = = < / l a t e x i t > < l a t e x i t s h a 1 _ b a s e 6 4 = " 9 D u 1 Y q W L w K K g y y 5 B 7 a v S X + H Y 1 F 8 = " > A A A B 7…”

Section: A D G Q 3 / H M / / G a N T Q C W T V L W 3 K 5 L 5 Y C K Z mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Statistical Regression Models for Noise Robust F0 Estimation Using Recurrent Deep Neural Networks

Kato

Kinnunen

2019

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…We experimented using the setup, that we used in our participation in NIST SRE16 evaluation [19,20]. In this setup, the training set included two parts:…”

Section: Datasetsmentioning

confidence: 99%

An Investigation of Non-linear i-vectors for Speaker Verification

2018

Self Cite

View full text Add to dashboard Cite

Speaker verification becomes increasingly important due to the popularity of speech assistants and smart home. i-vectors are used broadly for this topic, which use factor analysis to model the shift of average parameter in Gaussian Mixture Models. Recently by the progress of deep learning, high-level non-linearity improves results in many areas. In this paper we proposed a new framework of i-vectors which uses stochastic gradient descent to solve the problem of i-vectors. From our preliminary results stochastic gradient descent can get same performance as expectation-maximization algorithm. However, by backpropagation the assumption can be more flexible, so both linear and non-linear assumption is possible in our framework. From our result, both maximum a posteriori estimation and maximum likelihood lead to slightly better result than conventional i-vectors and both linear and non-linear system has similar performance.

show abstract

“…Due to their good performance, DNN-based systems This work is supported by the Neuromorphic Computing Programme under the RIE2020 Advanced Manufacturing and Engineering Programmatic Grant A1687b0033 in Singapore. have been incorporated in most systems in the latest NIST SRE challenge [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Generative X-Vectors for Text-Independent Speaker Verification

Das

Yılmaz

et al. 2018

2018 IEEE Spoken Language Technology Workshop (SLT)

View full text Add to dashboard Cite

Speaker verification (SV) systems using deep neural network embeddings, so-called the x-vector systems, are becoming popular due to its good performance superior to the i-vector systems. The fusion of these systems provides improved performance benefiting both from the discriminatively trained x-vectors and generative i-vectors capturing distinct speaker characteristics. In this paper, we propose a novel method to include the complementary information of i-vector and x-vector, that is called generative x-vector. The generative x-vector utilizes a transformation model learned from the i-vector and x-vector representations of the background data. Canonical correlation analysis is applied to derive this transformation model, which is later used to transform the standard x-vectors of the enrollment and test segments to the corresponding generative x-vectors. The SV experiments performed on the NIST SRE 2010 dataset demonstrate that the system using generative x-vectors provides considerably better performance than the baseline i-vector and x-vector systems. Furthermore, the generative x-vectors outperform the fusion of i-vector and x-vector systems for long-duration utterances, while yielding comparable results for short-duration utterances.

show abstract

The MIT-LL, JHU and LRDE NIST 2016 Speaker Recognition Evaluation System

Cited by 14 publications

References 11 publications

Statistical Regression Models for Noise Robust F0 Estimation Using Recurrent Deep Neural Networks

Statistical Regression Models for Noise Robust F0 Estimation Using Recurrent Deep Neural Networks

An Investigation of Non-linear i-vectors for Speaker Verification

Generative X-Vectors for Text-Independent Speaker Verification

Contact Info

Product

Resources

About