Titlebook: Advances in Speech and Language Technologies for Iberian Languages; IberSPEECH 2014 Conf Juan Luis Navarro Mesa,Alfonso Ortega,Doroteo T. T

OMIT

https://doi.org/10.1007/978-3-319-48354-2across the AHC iterations is done using reference speaker ground-truth labels to select the purer clustering as input for the global framework. Experiments on the REPERE phase 1 test database show improvements of around 6% absolute DER compared to the baseline system output.

榨取

Systemic

Xiaobin Qiu,Hongqian Chen,Nan Zhoud. All processing is done locally on the phone, which is able to react in real-time to incoming keywords. In this paper we describe the application, review the matching algorithm we used and show experimentally that it successfully reacts to voice commands in a variety of acoustic conditions.

sparse

Global Speaker Clustering towards Optimal Stopping Criterion in Binary Key Speaker Diarizationacross the AHC iterations is done using reference speaker ground-truth labels to select the purer clustering as input for the global framework. Experiments on the REPERE phase 1 test database show improvements of around 6% absolute DER compared to the baseline system output.

saturated-fat

CVX-Optimized Beamforming and Vector Taylor Series Compensation with German ASR Employing Star-Shapedium-vocabulary German database for microphone array made of embedded clean signals contaminated with real room impulsive responses and mixed in a ‘natural’ way with real noises. We show that the proposed enhancement framework performs better than other related systems on the presented database.

blithe

Flexible Stand-Alone Keyword Recognition Application Using Dynamic Time Warpingd. All processing is done locally on the phone, which is able to react in real-time to incoming keywords. In this paper we describe the application, review the matching algorithm we used and show experimentally that it successfully reacts to voice commands in a variety of acoustic conditions.

教唆

Statistical Text-to-Speech Synthesis of Spanish Subtitlesthe best of our knowledge, this is the first time that a DNN-based TTS system has been implemented for the synthesis of Spanish. A comparative objective evaluation between both models has been carried out. Our results show that DNN-based systems can reconstruct speech waveforms more accurately.

兇殘

Unsupervised Training of PLDA with Variational Bayesre latent variables. We experimented on unlabeled NIST SRE data. The trained models were evaluated on NIST SRE10. Compared to cosine distance, unsupervised PLDA improved EER by 28% and minimum DCF by 36%.

Interferons

MODE