Search results for: Michael I. Mandel
chapter
Automatic Speech Recognition systems suffer from severe performance degradation in the presence of myriad complicating factors such as noise, reverberation, multiple speech sources, multiple recording devices, etc. Previous challenges have sparked much innovation when it comes to designing systems capable of handling these complications. In this spirit, the CHiME-3 challenge presents system builders...
chapter
This paper utilizes a recently introduced non-linear dictionary-based denoising system in another voice mapping task, that of transforming low-bandwidth, low-bitrate speech into high-bandwidth, high-quality speech. The system uses a deep neural network as a learned nonlinear comparison function to drive unit selection in a concatenative synthesizer based on clean recordings. This neural network is...
chapter
Spectral masking techniques are prevalent for noise suppression but they damage speech in regions of the spectrum where both noise and speech are present. This paper instead utilizes a recently introduced analysis-by-synthesis technique to estimate the spectral envelope of the speech at all frequencies, and adds to it a model of the speech excitation necessary to fully resynthesize a clean speech...
chapter
Localization-based multichannel source separation algorithms typically operate by clustering or classifying individual time-frequency points based on their spatial characteristics, treating adjacent points as independent observations. The Model-based EM Source Separation and Localization (MESSL) algorithm is one such approach for binaural signals that achieves additional robustness by enforcing consistency...
chapter
This paper introduces a new approach to dictionary-based source separation employing a learned non-linear metric. In contrast to existing parametric source separation systems, this model is able to utilize a rich dictionary of speech signals. In contrast to previous dictionary-based source separation systems, the system can utilize perceptually relevant non-linear features of the noisy and clean audio...
chapter
Spectral masking is a promising method for noise suppression in which regions of the spectrogram that are dominated by noise are attenuated while regions dominated by speech are preserved. It is not clear, however, how best to combine spectral masking with the non-linear processing necessary to compute automatic speech recognition features. We propose an analysis-by-synthesis approach to automatic...
chapter
Predicting the intelligibility of noisy recordings is difficult and most current algorithms only aim to be correct on average across many recordings. This paper describes a listening test paradigm and associated analysis technique that can predict the intelligibility of a specific recording of a word in the presence of a specific noise instance. The analysis learns a map of the importance of each...
chapter
This paper evaluates the utility of the Discrete Cosine Transform (DCT) for characterizing singing voice fundamental frequency (F0) trajectories. Specifically, it focuses on the use of the 1st and 2nd DCT coefficients as approximations of slope and curvature. It also considers the impact of vocal vibrato on the DCT calculations, including the influence of segmentation on the consistency of the reported...
article
Speech Communication > 2011 > 53 > 5 > 606-621
We describe a system for separating multiple sources from a two-channel recording based on interaural cues and prior knowledge of the statistics of the underlying source signals. The proposed algorithm effectively combines information derived from low level perceptual cues, similar to those used by the human auditory system, with higher level information related to speaker identity. We combine a probabilistic...
article
IEEE Transactions on Audio, Speech, and Language Processing > 2010 > 18 > 7 > 1872 - 1883
This paper examines the performance of several source separation systems on a speech separation task for which human intelligibility has previously been measured. For anechoic mixtures, automatic speech recognition (ASR) performance on the separated signals is quite similar to human performance. In reverberation, however, while signal separation has some benefit for ASR, the results are still far...
chapter
We describe a system for localizing and separating multiple sound sources from a reverberant two-channel recording. It consists of a probabilistic model of interaural level and phase differences and an EM algorithm for finding the maximum likelihood parameters of this model. By assigning points in the interaural spectrogram probabilistically to sources with the best-fitting parameters and then estimating...
article
Multimedia Systems > 2006 > 12 > 1 > 3-13
Searching and organizing growing digital music collections requires a computational model of music similarity. This paper describes a system for performing flexible music similarity queries using SVM active learning. We evaluated the success of our system by classifying 1210 pop songs according to mood and style (from an online music guide) and by the performing artist. In comparing a number of representations...
