AURORA-2J: An Evaluation Framework for Japanese Noisy Speech Recognition

Nakamura, Satoshi; Takeda, Kazuya; Yamamoto, Kazumasa; Yamada, Takeshi; Kuroiwa, Shingo; Kitaoka, Norihide; Nishiura, Takanobu; Sasou, Akira; Mizumachi, Mitsunori; Fujimoto, Masakiyo; Endo, Toshiki

doi:10.1093/ietisy/e88-d.3.535

Cited by 52 publications

(25 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The test conditions were almost the same as those in Sect. 2.1, except that the noisy continuous digit utterances included in the AURORA-2J database [11] were used and the two different noise reduction algorithms described below were adopted instead of the algorithms (E) and (S).…”

Section: Overall Qualitymentioning

confidence: 99%

Non-reference Objective Quality Evaluation for Noise-Reduced Speech Using Overall Quality Estimation Model

Kasuya

Shinohara

Kitawaki

2010

IEICE Trans. Commun.

View full text Add to dashboard Cite

SUMMARYThis paper describes non-reference objective quality evaluation for noise-reduced speech. First, a subjective test is conducted in accordance with ITU-T Rec. P.835 to obtain the speech quality, the noise quality, and the overall quality of noise-reduced speech. Based on the results, we then propose an overall quality estimation model. The unique point of the proposed model is that the estimation of the overall quality is done only using the previously estimated speech quality and noise quality, in contrast to conventional models, which utilize the acoustical features extracted. Finally, we propose a non-reference objective quality evaluation method using the proposed model. The results of an experiment with different noise reduction algorithms and noise types confirmed that the proposed method gives more accurate estimates of the overall quality compared with the method described in ITU-T Rec. P.563. key words: non-reference objective quality evaluation, noise-reduced speech, overall quality estimation model,

show abstract

Section: Overall Qualitymentioning

confidence: 99%

Non-reference Objective Quality Evaluation for Noise-Reduced Speech Using Overall Quality Estimation Model

Kasuya

Shinohara

Kitawaki

2010

IEICE Trans. Commun.

View full text Add to dashboard Cite

show abstract

“…. Grammar-based recognition: The speech data used were 4,004 connected-digit utterances by 52 male and female speakers, which were the same as those in the AURORA-2J database [14]. The grammar allows arbitrary repetitions of digits, a short pause, and a terminal silence.…”

Section: Experimental Conditionsmentioning

confidence: 99%

Performance estimation of noisy speech recognition using spectral distortion and recognition task complexity

Guo

Miyabe

Makino

et al. 2016

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

Previously, methods for estimating the performance of noisy speech recognition based on a spectral distortion measure have been proposed. Although they give an estimate of recognition performance without actually performing speech recognition, no consideration is given to any change in the components of a speech recognition system. To solve this problem, we propose a novel method for estimating the performance of noisy speech recognition, a major feature of which is the ability to accommodate the use of different noise reduction algorithms and recognition tasks by using two cepstral distances (CDs) and the square mean root perplexity (SMR-perplexity). First, we verified the effectiveness of the proposed distortion measure, i.e., the two CDs. The experimental results showed that the use of the proposed distortion measure achieves estimation accuracy equivalent to the use of the conventional distortion measures, the perceptual evaluation of speech quality (PESQ) and the signal-to-noise ratio (SNR) of noise-reduced speech, and has the advantage of being applicable to noise reduction algorithms that directly output the mel-frequency cepstral coefficient (MFCC) feature. We then evaluated the proposed method by performing a closed test and an open test (10-fold crossvalidation test). The results confirmed that the proposed method gives better estimates without being dependent on the differences among the noise reduction algorithms or the recognition tasks.

show abstract

“…The recognizer setup is based on AURORA-2J [27] with 18 HMM states. Of the 18 states, only 16 are emitting states with 20 Gaussians for the sound events and 36 Gaussians for the silence model.…”

Section: Hidden Markov Model (Hmm) Recognizermentioning

confidence: 99%

Selective Gammatone Envelope Feature for Robust Sound Event Recognition

Leng

Tran

Kitaoka

et al. 2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYConventional features for Automatic Speech Recognition and Sound Event Recognition such as Mel-Frequency Cepstral Coefficients (MFCCs) have been shown to perform poorly in noisy conditions. We introduce an auditory feature based on the gammatone filterbank, the Selective Gammatone Envelope Feature (SGEF), for Robust Sound Event Recognition where channel selection and the filterbank envelope is used to reduce the effect of noise for specific noise environments. In the experiments with Hidden Markov Model (HMM) recognizers, we shall show that our feature outperforms MFCCs significantly in four different noisy environments at various signal-to-noise ratios.

show abstract

AURORA-2J: An Evaluation Framework for Japanese Noisy Speech Recognition

Cited by 52 publications

References 4 publications

Non-reference Objective Quality Evaluation for Noise-Reduced Speech Using Overall Quality Estimation Model

Non-reference Objective Quality Evaluation for Noise-Reduced Speech Using Overall Quality Estimation Model

Performance estimation of noisy speech recognition using spectral distortion and recognition task complexity

Selective Gammatone Envelope Feature for Robust Sound Event Recognition

Contact Info

Product

Resources

About