Speech recognition using noise-adaptive prototypes

Nádas, Arthur; Nahamoo, D.; Picheny, Michael

doi:10.1109/29.35387

Cited by 158 publications

(85 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The methods operate on observed speech and additive noise mixtures in a magnitude-compressed spectral domain, where additive noise can be modelled as an occluder (Nádas et al, 1989). The missing data front-end used in the current work operates on log-magnitude-compressed mel-spectral features.…”

Section: Mask Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Comparing human and automatic speech recognition in a perceptual restoration experiment

Remes

López

Juvela

et al. 2016

Computer Speech & Language

View full text Add to dashboard Cite

Speech that has been distorted by introducing spectral or temporal gaps is still perceived as continuous and complete by human listeners, so long as the gaps are filled with additive noise of sufficient intensity. When such perceptual restoration occurs, the speech is also more intelligible compared to the case in which noise has not been added in the gaps. This observation has motivated so-called 'missing data' systems for automatic speech recognition (ASR), but there have been few attempts to determine whether such systems are a good model of perceptual restoration in human listeners. Accordingly, the current paper evaluates missing data ASR in a perceptual restoration task. We evaluated two systems that use a new approach to bounded marginalisation in the cepstral domain, and a bounded conditional mean imputation method. Both methods model available speech information as a clean-speech posterior distribution that is subsequently passed to an ASR system. The proposed missing data ASR systems were evaluated using distorted speech, in which spectro-temporal gaps were optionally filled with additive noise. Speech recognition performance of the proposed systems was compared against a baseline ASR system, and with human speech recognition performance on the same task. We conclude that missing data methods improve speech recognition performance in a manner that is consistent with perceptual restoration in human listeners.

show abstract

Section: Mask Estimationmentioning

confidence: 99%

“…We denote the observed speech and additive noise mixture in channel d of time frame τ in the log-mel-spectral domain by Y (τ, d). According to the so-called logmax approximation (Nádas et al, 1989;Varga and Moore, 1990) the log-magnitude-compressed observations can be approximated as…”

Section: Mask Estimationmentioning

confidence: 99%

Comparing human and automatic speech recognition in a perceptual restoration experiment

Remes

López

Juvela

et al. 2016

Computer Speech & Language

View full text Add to dashboard Cite

show abstract

“…However, while the previous set of algorithms utilize a mixture of auto-regressive models in the time domain, our algorithm models the log-spectrum by a mixture of diagonal covariance Gaussians. In this paper, we follow the MIXMAX approximation, which was originally suggested by Nádas et al [15] in the context of speech recognition, and propose a new speech enhancement algorithm. For this purpose, various modifications, adaptations and improvements were made in the algorithm proposed in [15] in order to make it a high-quality, low-complexity speech enhancement algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we follow the MIXMAX approximation, which was originally suggested by Nádas et al [15] in the context of speech recognition, and propose a new speech enhancement algorithm. For this purpose, various modifications, adaptations and improvements were made in the algorithm proposed in [15] in order to make it a high-quality, low-complexity speech enhancement algorithm. In [15], the MIXMAX model is used to design a noise adaptive, discrete density, HMM-based, speech recognition algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…For this purpose, various modifications, adaptations and improvements were made in the algorithm proposed in [15] in order to make it a high-quality, low-complexity speech enhancement algorithm. In [15], the MIXMAX model is used to design a noise adaptive, discrete density, HMM-based, speech recognition algorithm. In [16], we used the MIXMAX model to design various noise adaptive, continuous density, HMM-based speech recognition systems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Speech enhancement using a mixture-maximum model

Burshtein

Gannot

2002

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

Abstract-We present a spectral domain, speech enhancement algorithm. The new algorithm is based on a mixture model for the short time spectrum of the clean speech signal, and on a maximum assumption in the production of the noisy speech spectrum. In the past this model was used in the context of noise robust speech recognition. In this paper we show that this model is also effective for improving the quality of speech signals corrupted by additive noise. The computational requirements of the algorithm can be significantly reduced, essentially without paying performance penalties, by incorporating a dual codebook scheme with tied variances. Experiments, using recorded speech signals and actual noise sources, show that in spite of its low computational requirements, the algorithm shows improved performance compared to alternative speech enhancement algorithms.Index Terms-Gaussian mixture model, MIXMAX model, speech enhancement.

show abstract

Factorial Models for Noise Robust Speech Recognition

Hershey¹,

Rennie²,

Roux³

2012

Techniques for Noise Robustness in Automatic Speech Recognition

View full text Add to dashboard Cite

Noise compensation techniques for robust automatic speech recognition (ASR) attempt to improve system performance in the presence of acoustic interference. In feature-based noise compensation, which includes speech enhancement approaches, the acoustic features that are sent to the recognizer are first processed to remove the effects of noise (see Chapter 9). Model compensation approaches, in contrast, are concerned with modifying and even extending the acoustic model of speech to account for the effects of noise. A taxonomy of the different approaches to noise compensation is depicted in Figure 12.1, which serves as a road map for the present discussion.The two main strategies used for model compensation approaches are model adaptation and model-based noise compensation. Model adaptation approaches implicitly account for noise by adjusting the parameters of the acoustic model of speech, whereas model-based noise compensation approaches explicitly model the noise and its effect on the noisy speech features. Common adaptation approaches include maximum likelihood linear regression (MLLR) [56], maximum a posteriori (MAP) adaptation [32], and their generalizations [17,29,47]. These approaches, which are discussed in Chapter 11, alter the speech acoustic model in a completely data-driven way given additional training data or test data. Adaptation methods are somewhat more general than model-based approaches in that they may handle effects on the signal that are difficult to explicitly model, such as nonlinear distortion and changes in the voice in reaction to noise (the Lombard effect [53]). However, in the presence of additive noise, failing to take take into account the known interactions between speech and noise can be detrimental to performance.Model-based noise compensation approaches, in contrast to adaptation approaches, explicitly model the different factors present in the acoustic environment: the speech, the various sources of acoustic interference, and how they interact to form the noisy speech Techniques for Noise Robustness in Automatic Speech Recognition Tuomas Virtanen, Rita Singh, and Bhiksha Raj, Eds.

show abstract

Speech recognition using noise-adaptive prototypes

Cited by 158 publications

References 12 publications

Comparing human and automatic speech recognition in a perceptual restoration experiment

Comparing human and automatic speech recognition in a perceptual restoration experiment

Speech enhancement using a mixture-maximum model

Factorial Models for Noise Robust Speech Recognition

Contact Info

Product

Resources

About