F
Frederick V. Weber
Researcher at Amazon.com
Publications - 9
Citations - 341
Frederick V. Weber is an academic researcher from Amazon.com. The author has contributed to research in topics: Acoustic model & Speaker recognition. The author has an hindex of 7, co-authored 9 publications receiving 327 citations.
Papers
More filters
Patent
Discriminative language model pruning
TL;DR: In this article, a language model for speech recognition may be discriminatively pruned by computing a discriminative objective function value for one or more n-grams in the language model, and selecting ngrams to prune based on a threshold value.
Proceedings ArticleDOI
Using prosodic and lexical information for speaker identification
TL;DR: It is found that, with sufficient test and training data, suprasegmental information can significantly enhance the performance of traditional speaker ID systems.
Patent
Wake word evaluation
Stan Weidner Salvador,Jeffrey Paul Lilly,Frederick V. Weber,Jeffrey Penrod Adams,Ryan Paul Thomas +4 more
TL;DR: In this paper, a candidate word for evaluation as a wake word that activates a natural language control functionality of a computing device is provided, which may include one or more words or sounds.
Patent
Adaptive neural network speech recognition models
TL;DR: In this article, a neural network may be updated/retrained during run time by training the neural network based on the output of a speech recognition system or based on output of the neural networks themselves.
Patent
Automatic speaker identification using speech recognition features
TL;DR: In this paper, features are disclosed for automatically identifying a speaker, and scores are determined based on individual components of Gaussian mixture models (GMMs) that score best for frames of audio data of an utterance.