This paper presents clustering experiments performed over noisy texts (i.e. texts that have been extracted through an automatic process like character or speech recognition). The effect of recognition errors is investigated by comparing clustering results performed over both clean (manually typed data) and noisy (automatic speech transcriptions) versions of the same speech recording corpus.

A successful speech enhancement system requires strong models for both speech and noise to decompose a mixture into the most likely combination. However, if the noise encountered differs significantly from the system’s assumptions, performance will suffer. In previous work, we proposed a speech enhancement framework based on decomposing the noisy spectrogram into low rank background noise and a...

Existing objective speech-intelligibility measures are suitable for several types of degradation, however, it turns out that they are less appropriate in cases where noisy speech is processed by a time-frequency weighting. To this end, an extensive evaluation is presented of objective measure for intelligibility prediction of noisy speech processed with a technique called ideal time frequency (...

Speech enhancement aims to enhance the perceived speech quality and intelligibility in the presence of noise. Classical speech enhancement methods are mainly based on audio only processing which often perform poorly in adverse conditions, where overwhelming noise is present. This paper presents an interactive prototype demo, as part of a disruptive cognitivelyinspired multimodal hearing-aid bei...

We present a method to combine standard and throat microphone signals for noise-robust speech recognition. Our approach is to extend the probabilistic optimum filter (POF) mapping algorithm to estimate standard microphone clean speech feature vectors from both microphones’ noisy speech feature vectors. We tested the proposed approach in two noisy speech recognition tasks. In the first task we u...

In this paper we propose a method for enhancement of speech in the presence of additive noise. The objective is to selectively enhance the high SNR regions in the noisy speech in the temporal and spectral domains, without causing signiicant distortion in the resulting enhanced speech. This is proposed to be done at three diierent levels: (a) At the gross level, by identifying the regions of spe...

We present a new method for speech denoising and robust speech recognition. Using the framework of probabilistic models allows us to integrate detailed speech models and models of realistic non-stationary noise signals in a principled manner. The framework transforms the denoising problem into a problem of Bayes-optimal signal estimation, producing minimum mean square error estimators of desire...

Speech is bimodal in nature and includes the audio and visual modalities. In addition to acoustic speech perception, speech can be also perceived using visual information provided by the mouth/face (i.e., automatic lipreading). In this study, the visual speech production in noisy environments is investigated. The authors show that the Lombard effect plays an important role not only in audio spe...

This paper extends the technique of speech reconstruction from MFCCs by considering the effect of noisy speech. To reconstruct a clean speech signal from noise contaminated MFCCs an estimate of the clean mel-filterbank vector is required together with a robust estimate of the pitch. This work applies spectral subtraction to the mel-filterbank vector (derived from noisy MFCCs) to provide a clean...

In this paper we propose a method for enhancement of speech in the presence of additive noise. The objective is to selectively enhance the high signal-to-noise ratio (SNR) regions in the noisy speech in the temporal and spectral domains, without causing signi®cant distortion in the resulting enhanced speech. This is proposed to be done at three di€erent levels. (a) At the gross level, by identi...