A novel approach to soft-mask estimation and Log-Spectral enhancement for robust speech recognition

Hout, Julien van; Alwan, Abeer

doi:10.1109/icassp.2012.6288821

Cited by 14 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, van Hout and Alwan propose to estimate a smoothed ratio mask using noise power estimators and a median filter, which they use to perform feature enhancement in the log Mel spectral domain before cepstral transformation [17].…”

Section: Prior Workmentioning

confidence: 99%

Ideal ratio mask estimation using deep neural networks for robust speech recognition

Narayanan

Wang

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

479

255

View full text Add to dashboard Cite

We propose a feature enhancement algorithm to improve robust automatic speech recognition (ASR). The algorithm estimates a smoothed ideal ratio mask (IRM) in the Mel frequency domain using deep neural networks and a set of time-frequency unit level features that has previously been used to estimate the ideal binary mask. The estimated IRM is used to filter out noise from a noisy Mel spectrogram before performing cepstral feature extraction for ASR. On the noisy subset of the Aurora-4 robust ASR corpus, the proposed enhancement obtains a relative improvement of over 38% in terms of word error rates using ASR models trained in clean conditions, and an improvement of over 14% when the models are trained using the multi-condition training data. In terms of instantaneous SNR estimation performance, the proposed system obtains a mean absolute error of less than 4 dB in most frequency channels.

show abstract

Section: Prior Workmentioning

confidence: 99%

Ideal ratio mask estimation using deep neural networks for robust speech recognition

Narayanan

Wang

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

479

255

View full text Add to dashboard Cite

show abstract

“…Finally, the transform gate of our architecture is similar to adaptive soft-masking filtering [13] in speech enhancement. Hence, it is expected that knowledge can be shared between voice conversion and speech enhancement.…”

Section: Discussionmentioning

confidence: 99%

Voice Conversion Using Input-to-Output Highway Networks

Saito

Takamichi

Saruwatari

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper proposes Deep Neural Network (DNN)-based Voice Conversion (VC) using input-to-output highway networks. VC is a speech synthesis technique that converts input features into output speech parameters, and DNN-based acoustic models for VC are used to estimate the output speech parameters from the input speech parameters. Given that the input and output are often in the same domain (e.g., cepstrum) in VC, this paper proposes a VC using highway networks connected from the input to output. The acoustic models predict the weighted spectral differentials between the input and output spectral parameters. The architecture not only alleviates over-smoothing effects that degrade speech quality, but also effectively represents the characteristics of spectral parameters. The experimental results demonstrate that the proposed architecture outperforms Feed-Forward neural networks in terms of the speech quality and speaker individuality of the converted speech. key words: statistical parametric speech synthesis, DNN-based voice conversion, highway networks, over-smoothing

show abstract

“…The LSEN feature was initially introduced in [25] for enhancement of the mel-spectrum with applications to noiserobust speech recognition. It was adapted in [26] to enhance the gammatone power-normalized spectra of noisy speech obtained with the power-normalized cepstral coefficients (PNCC) features pipeline and renamed LSEN-PNCC.…”

Section: Log-spectrally Enhanced Power Normalized Cepstral Coefficienmentioning

confidence: 99%

Fusion Strategies for Robust Speech Recognition and Keyword Spotting for Channel- and Noise-Degraded Speech

et al. 2016

Self Cite

View full text Add to dashboard Cite

Recognizing speech under high levels of channel and/or noise degradation is challenging. Current state-of-the-art automatic speech recognition systems are sensitive to changing acoustic conditions, which can cause significant performance degradation. Noise-robust acoustic features can improve speech recognition performance under varying background conditions, where it is usually observed that robust modeling techniques and multiple system fusion can help to improve the performance even further. This work investigates a wide array of robust acoustic features that have been previously used to successfully improve speech recognition robustness. We use these features to train individual acoustic models, and we analyze their individual performance. We investigate and report results for simple feature combination, feature-map combination at the output of convolutional layers, and fusion of deep neural nets at the senone posterior level. We report results for speech recognition on a large-vocabulary, noiseand channel-degraded Levantine Arabic speech corpus distributed through the Defense Advance Research Projects Agency (DARPA) Robust Automatic Speech Transcription (RATS) program. In addition, we report keyword spotting results to demonstrate the effect of robust features and multiple levels of information fusion.

show abstract

A novel approach to soft-mask estimation and Log-Spectral enhancement for robust speech recognition

Cited by 14 publications

References 12 publications

Ideal ratio mask estimation using deep neural networks for robust speech recognition

Ideal ratio mask estimation using deep neural networks for robust speech recognition

Voice Conversion Using Input-to-Output Highway Networks

Fusion Strategies for Robust Speech Recognition and Keyword Spotting for Channel- and Noise-Degraded Speech

Contact Info

Product

Resources

About