Frantisek Grézl

Learn More
In recent years, probabilistic features became an integral part of state-of-the-are LVCSR systems. In this work, we are exploring the possibility of obtaining the features directly from neural net without the necessity of converting output probabilities to features suitable for subsequent GMM-HMM system. We experimented with 5-layer MLP with bottle-neck in(More)
This paper describes and discusses the "STBU" speaker recognition system, which performed well in the NIST Speaker Recognition Evaluation 2006 (SRE). STBU is a consortium of four partners: Spescom DataVoice (Stellenbosch, South Africa), TNO (Soesterberg, The Netherlands), BUT (Brno, Czech Republic), and the University of Stellenbosch (Stellenbosch, South(More)
Our feature extraction module for the Aurora task is based on a combination of a conventional noise supression technique (Wiener filtering) with our temporal processing technigues (linear discriminant RASTA filtering and nonlinear TempoRAl Pattern (TRAP) classifier). We observe better than 58% relative error improvement on the prescribed Aurora Digit Task,(More)
This work continues in development of the recently proposed bottle-neck features for ASR. A five-layers MLP used in bottleneck feature extraction allows to obtain arbitrary feature size without dimensionality reduction by transforms, independently on the MLP training targets. The MLP topology - number and sizes of layers, suitable training targets, the(More)
In this paper, we give an overview of the AMIDA systems for transcription of conference and lecture room meetings. The systems were developed for participation in the Rich Transcription evaluations conducted by the National Institute for Standards and Technology in the years 2007 and 2009 and can process close talking and far field microphone recordings.(More)
Recent results with phone-posterior acoustic features estimated by multilayer perceptrons (MLPs) have shown that such features can effectively improve the accuracy of state-of-the-art large vocabulary speech recognition systems. MLP features are trained discriminatively to perform phone classification and are therefore, like acoustic models, tuned to a(More)
The neural network based features became an inseparable part of state-of-the-art LVCSR systems. In order to perform well, the network has to be trained on a large amount of in-domain data. With the increasing emphasis on fast development of ASR system on limited resources, there is an effort to alleviate the need of in-domain data. To evaluate the(More)
This study is focused on the performance of Probabilistic and Bottle-Neck features on different language than they were trained for. It is shown, that such porting is possible and that the features are still competitive to PLP features. Further, several combination techniques are evaluated. The performance of combined features is close to the best(More)
This paper presents bootstrapping approach for neural network training. The neural networks serve as bottle-neck feature extractor for subsequent GMM-HMM recognizer. The recognizer is also used for transcription and confidence assignment of untranscribed data. Based on the confidence, segments are selected and mixed with supervised data and new NNs are(More)
We describe the development of our speech recognition system for the NIST Spring 2005 Meeting Rich Transcription (RT-05S) evaluation, highlighting improvements made since last year [1]. The system is based on the SRIICSI-UW RT-04F conversational telephone speech (CTS) recognition system, with meeting-adapted models and various audio preprocessing steps.(More)