The diverse environments multi-channel acoustic noise database: A database of multichannel environmental noise recordings

Thiemann, Joachim; Ito, Nobuyasu; Vincent, Emmanuel

doi:10.1121/1.4806631

Cited by 243 publications

(90 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data set is a selection of 30 speakers from the Voice Bank corpus [28]: 28 are included in the train set and 2 in the test set. To make the noisy training set, a total of 40 different conditions are considered [27]: 10 types of noise (2 artificial and 8 from the Demand database [29]) with 4 signal-to-noise ratio (SNR) each (15, 10, 5, and 0 dB). There are around 10 different sentences in each condition per training speaker.…”

Section: Data Setmentioning

confidence: 99%

SEGAN: Speech Enhancement Generative Adversarial Network

Pascual

Bonafonte

Serrà³

2017

Interspeech 2017

870

640

View full text Add to dashboard Cite

Current speech enhancement techniques operate on the spectral domain and/or exploit some higher-level feature. The majority of them tackle a limited number of noise conditions and rely on first-order statistics. To circumvent these issues, deep networks are being increasingly used, thanks to their ability to learn complex functions from large example sets. In this work, we propose the use of generative adversarial networks for speech enhancement. In contrast to current techniques, we operate at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them. We evaluate the proposed model using an independent, unseen test set with two speakers and 20 alternative noise conditions. The enhanced samples confirm the viability of the proposed model, and both objective and subjective evaluations confirm the effectiveness of it. With that, we open the exploration of generative architectures for speech enhancement, which may progressively incorporate further speech-centric design choices to improve their performance.

show abstract

Section: Data Setmentioning

confidence: 99%

SEGAN: Speech Enhancement Generative Adversarial Network

Pascual

Bonafonte

Serrà³

2017

Interspeech 2017

870

640

View full text Add to dashboard Cite

show abstract

“…To create the noisy database used for training we used ten different noise types: two artificially generated (speech-shaped noise and babble) and eight real noise recordings from the Demand database [25]. The speech-shaped noise was created by filtering white noise with a filter whose frequency response matched that of the long term speech level of a male speaker.…”

Section: Databasementioning

confidence: 99%

Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech

Valentini-Botinhao¹,

Wang²,

Takaki³

et al. 2016

9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)

287

148

View full text Add to dashboard Cite

The quality of text-to-speech (TTS) voices built from noisy speech is compromised. Enhancing the speech data before training has been shown to improve quality but voices built with clean speech are still preferred. In this paper we investigate two different approaches for speech enhancement to train TTS systems. In both approaches we train a recursive neural network (RNN) to map acoustic features extracted from noisy speech to features describing clean speech. The enhanced data is then used to train the TTS acoustic model. In one approach we use the features conventionally employed to train TTS acoustic models, i.e Mel cepstral (MCEP) coefficients, aperiodicity values and fundamental frequency (F0). In the other approach, following conventional speech enhancement methods, we train an RNN using only the MCEP coefficients extracted from the magnitude spectrum. The enhanced MCEP features and the phase extracted from noisy speech are combined to reconstruct the waveform which is then used to extract acoustic features to train the TTS system. We show that the second approach results in larger MCEP distortion but smaller F0 errors. Subjective evaluation shows that synthetic voices trained with data enhanced with this method were rated higher and with similar to scores to voices trained with clean speech.

show abstract

“…We use the IEEE corpus recorded by a male speaker (IEEE, 1969) and six nonstationary noises from the DEMAND corpus (Thiemann et al, 2013) to create mixtures. All signals are sampled at 16 KHz.…”

Section: Resultsmentioning

confidence: 99%

Noise perturbation for supervised speech separation

Chen

Wang

2016

Speech Communication

View full text Add to dashboard Cite

Speech separation can be treated as a mask estimation problem, where interference-dominant portions are masked in a time-frequency representation of noisy speech. In supervised speech separation, a classifier is typically trained on a mixture set of speech and noise. It is important to efficiently utilize limited training data to make the classifier generalize well. When target speech is severely interfered by a nonstationary noise, a classifier tends to mistake noise patterns for speech patterns. Expansion of a noise through proper perturbation during training helps to expose the classifier to a broader variety of noisy conditions, and hence may lead to better separation performance. This study examines three noise perturbations on supervised speech separation: noise rate, vocal tract length, and frequency perturbation at low signal-to-noise ratios (SNRs). The speech separation performance is evaluated in terms of classification accuracy, hit minus false-alarm rate and short-time objective intelligibility (STOI). The experimental results show that frequency perturbation is the best among the three perturbations in terms of speech separation. In particular, the results show that frequency perturbation is effective in reducing the error of misclassifying a noise pattern as a speech pattern.

show abstract

The diverse environments multi-channel acoustic noise database: A database of multichannel environmental noise recordings

Cited by 243 publications

References 4 publications

SEGAN: Speech Enhancement Generative Adversarial Network

SEGAN: Speech Enhancement Generative Adversarial Network

Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech

Noise perturbation for supervised speech separation

Contact Info

Product

Resources

About