Developing a speaker identification system for the DARPA RATS project

Plchot, Oldřich; Matsoukas, Spyros; Matějka, Pavel; Dehak, Najim; Ma, Junxia; Cumani, Sandro; Glembek, Ondřej; Heřmanský, Hynek; Mallidi, Sri Harish; Mesgarani, Nima; Schwartz, Richard; Soufifar, Mehdi; Thomas, Samuel; Zhang, B.

doi:10.1109/icassp.2013.6638972

Cited by 31 publications

(28 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trial scoring was performed by the means of PLDA trained for full-rank speaker-and channelcovariance matrices. For a detailed description, see [18].…”

Section: System Descriptionmentioning

confidence: 99%

Domain adaptation via within-class covariance correction in I-vector based speaker recognition systems

Glembek

Jeff

Matějka

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

In this paper we propose a technique of Within-Class Covariance Correction (WCC) for Linear Discriminant Analysis (LDA) in Speaker Recognition to perform an unsupervised adaptation of LDA to an unseen data domain, and/or to compensate for speaker population difference among different portions of LDA training dataset. The paper follows on the study of source-normalization and interdatabase variability compensation techniques which deal with multimodal distribution of i-vectors. On the DARPA RATS (Robust Automatic Transcription of Speech) task, we show that, with two hours of unsupervised data, we improve the Equal-Error Rate (EER) by 17.5%, and 36% relative on the unmatched and semi-matched conditions, respectively. On the Domain Adaptation Challenge we show up to 70% relative EER reduction and we propose a data clustering procedure to identify the directions of the domain-based variability in the adaptation data.

show abstract

“…Trial scoring was performed by the means of PLDA trained for full-rank speaker-and channelcovariance matrices. For a detailed description, see [18].…”

Section: System Descriptionmentioning

confidence: 99%

Domain adaptation via within-class covariance correction in I-vector based speaker recognition systems

Glembek

Jeff

Matějka

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…[2]. In the later stages, various designs of robust features [3] are used in combination with normalization techniques such as cepstral mean and variance normalization or short-time gaussianization [4].…”

Section: Introductionmentioning

confidence: 99%

Audio enhancing with DNN autoencoder for speaker recognition

Plchot

Burget

Aronowitz

et al. 2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

In this paper we present a design of a DNN-based autoencoder for speech enhancement and its use for speaker recognition systems for distant microphones and noisy data. We started with augmenting the Fisher database with artificially noised and reverberated data and trained the autoencoder to map noisy and reverberated speech to its clean version. We use the autoencoder as a preprocessing step in the later stage of modelling in state-of-the-art text-dependent and text-independent speaker recognition systems. We report relative improvements up to 50% for the text-dependent system and up to 48% for the text-independent one. With text-independent system, we present a more detailed analysis on various conditions of NIST SRE 2010 and PRISM suggesting that the proposed preprocessig is a promising and efficient way to build a robust speaker recognition system for distant microphone and noisy data.

show abstract

“…In this application it is very important, that the robot knows who it is interacting with, such that the interaction can be made specifically to that person, thus increasing the likeliness of sustaining the interaction. The two most common modalities for person identification are audio ( [4], [5], [6]) and vision ( [7], [8], [9]). Both speaker recognition and face recognition perform well separately under ideal conditions, however in situations where both modalities are available, which is typically the case for robots, there is an improvement to gain by fusing the two modalities [10].…”

Section: Introductionmentioning

confidence: 99%

Improving the convergence of co-training for audio-visual person identification

Thomsen

Duan

Lindberg

et al. 2016

2016 First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE)

View full text Add to dashboard Cite

Person identification is a very important task for intelligent devices when communicating or interacting with humans. A potential problem in real applications is that the amount of enrollment data is insufficient. When multiple modalities are available, it is possible to re-train the system online by exploiting the conditional independence between the modalities and thus improving classification accuracy. This can be achieved by the well-known CO-training algorithm [1]. In this work we present a novel modification to the CO-training algorithm, which is concerned with how new observations/samples are chosen at each iteration to re-train the system in order to improve the classification accuracy faster, i.e., better convergence. In our method, the new data are chosen not only based on the score from the other modality but also the score from the self modality. We demonstrate our proposed method on a multimodal person identification task using the MOBIO database, and show that it outperforms the baseline method, in terms of convergency, by a large margin.

show abstract

Developing a speaker identification system for the DARPA RATS project

Cited by 31 publications

References 17 publications

Domain adaptation via within-class covariance correction in I-vector based speaker recognition systems

Domain adaptation via within-class covariance correction in I-vector based speaker recognition systems

Audio enhancing with DNN autoencoder for speaker recognition

Improving the convergence of co-training for audio-visual person identification

Contact Info

Product

Resources

About