Jort F. Gemmeke

Learn More
This paper proposes to use exemplar-based sparse representations for noise robust automatic speech recognition. First, we describe how speech can be modeled as a linear combination of a small number of exemplars from a large speech exemplar dictionary. The exemplars are time-frequency patches of real speech, each spanning multiple time frames. We then(More)
An effective way to increase the noise robustness of automatic speech recognition is to label noisy speech features as either reliable or unreliable (missing), and to replace (impute) the missing ones by clean speech estimates. Conventional imputation techniques employ parametric models and impute the missing features on a frame-by-frame basis. At low(More)
This paper proposes a computationally efficient algorithm for estimating the non-negative weights of linear combinations of the atoms of large-scale audio dictionaries, so that the generalized Kullback-Leibler divergence between an audio observation and the model is minimized. This linear model has been found useful in many audio signal processing tasks,(More)
Noise robustness of automatic speech recognition benefits from using missing data imputation: Prior to recognition the parts of the spectrogram dominated by noise are replaced by clean speech estimates. Especially at low SNRs each frame contains at best only a few uncorrupted coefficients. This makes frame-by-frame restoration of corrupted feature vectors(More)
Audio event recognition, the human-like ability to identify and relate sounds from audio, is a nascent problem in machine perception. Comparable problems such as object detection in images have reaped enormous benefits from comprehensive datasets - principally ImageNet. This paper describes the creation of Audio Set, a large-scale dataset of(More)
An effective way to increase the noise robustness of automatic speech recognition is to label noisy speech features as either reliable or unreliable (missing) prior to decoding, and to replace the missing ones by clean speech estimates. We present a novel method based on techniques from the field of Compressive Sensing to obtain these clean speech(More)
This paper proposes a noise robust exemplar-based speech recognition system where noisy speech is modeled as a linear combination of a set of speech and noise exemplars. The method works by finding a small number of labeled exemplars in a very large collection of speech and noise exemplars that jointly approximate the observed speech signal. We represent(More)
Solving real-world classification and recognition problems requires a principled way of modeling the physical phenomena generating the observed data and the uncertainty in it. The uncertainty originates from the fact that many data generation aspects are influenced by nondirectly measurable variables or are too complex to model and hence are treated as(More)
This paper introduces a novel approach to exemplar-based connected digit recognition. The approach is tested for different sizes of the exemplar collection (from 250 to 16,000), different length of the exemplars (from 1 to 50 time frames) and state-labeled versus word-labeled decoding. In addition, we compare the novel method for selecting exemplars, based(More)
In this work an exemplar-based technique for speech enhancement of noisy speech is proposed. The technique works by finding a sparse representation of the noisy speech in a dictionary containing both speech and noise exemplars, and uses the activated dictionary atoms to create a time-varying filter to enhance the noisy speech. The speech enhancement(More)