Speaker recognition

About: Speaker recognition is a research topic. Over the lifetime, 14990 publications have been published within this topic receiving 310061 citations.

Data driven example based continuous speech recognition.

Abstract: The dominant acoustic modeling methodology based on Hidden Markov Models is known to have certain weaknesses Partial solutions to these flaws have been presented, but the fundamental problem remains: compression of the data to a compact HMM discards useful information such as time dependencies and speaker information In this paper, we look at pure example based recognition as a solution to this problem By replacing the HMM with the underlying examples, all information in the training data is retained We show how information about speaker and environment can be used, introducing a new interpretation of adaptation The basis for the recognizer is the wellknown DTW algorithm, which has often been used for small tasks However, large vocabulary speech recognition introduces new demands, resulting in an explosion of the search space We show how this problem can be tackled using a data driven approach which selects appropriate speech examples as candidates for DTW-alignment

Natural statistical models for automatic speech recognition

Abstract: The performance of state-of-the-art speech recognition systems is still far worse than that of humans. This is partly caused by the use of poor statistical models. In a general statistical pattern classification task, the probabilistic models should represent the statistical structure unique to and distinguishing those objects to be classified. In many cases, however, model families are selected without verification of their ability to represent vital discriminative properties. For example, Hidden Markov Models (HMMs) are frequently used in automatic speech recognition systems even though they possess conditional independence properties that might cause inaccuracies when modeling and classifying speech signals. In this work, a new method for automatic speech recognition is developed where the natural statistical properties of speech are used to determine the probabilistic model. Starting from an HMM, new models are created by adding dependencies only if they are not already well captured by the HMM, and only if they increase the model's ability to distinguish one object from another. Based on conditional mutual information, a new measure is developed and used for dependency selection. If dependencies are selected to maximize this measure, then the class posterior probability is better approximated leading to a lower Bayes classification error. The method can be seen as a general discriminative structure-learning procedure for Bayesian networks. In a large-vocabulary isolated-word speech recognition task, test results have shown that the new models can result in an appreciable word-error reduction relative to comparable HMM systems.

Selection of superwords based on criteria relevant to both speech recognition and understanding

Abstract: This invention is directed to the selection of superwords based on a criterion relevant to speech recognition and understanding. Superwords are used to refer to those word combinations which are so often spoken that they are recognized as units or should have models to reflect them in the language model. The selected superwords are placed in a lexicon along with selected meaningful phrases. The lexicon is then used by a speech recognizer to improve recognition of input speech utterances for the proper routing of a user's task objectives.

Filterbank Design for End-to-end Speech Separation

Abstract: Single-channel speech separation has recently made great progress thanks to learned filterbanks as used in ConvTasNet. In parallel, parameterized filterbanks have been proposed for speaker recognition where only center frequencies and bandwidths are learned. In this work, we extend real-valued learned and parameterized filterbanks into complex-valued analytic filterbanks and define a set of corresponding representations and masking strategies. We evaluate these filterbanks on a newly released noisy speech separation dataset (WHAM). The results show that the proposed analytic learned filterbank consistently outperforms the real-valued filterbank of ConvTasNet. Also, we validate the use of parameterized filterbanks and show that complex-valued representations and masks are beneficial in all conditions. Finally, we show that the STFT achieves its best performance for 2 ms windows.