Estimation of the signal-to-noise ratio with amplitude modulation spectrograms

Tchorz, Jürgen; Kollmeier, Birger

doi:10.1016/s0167-6393(01)00040-1

Cited by 18 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is clearly seen from the 10/90 percentiles. A similar effect was observed by Tchorz and Kollmeier (2002) to a much larger extend (up to 6dB) than the systematic bias of maximal 2dB absolute in the current approach. Looking at individual frequency channels (cf.…”

Section: Resultssupporting

confidence: 85%

“…The categories 'alarm' and 'babble' includes types of noise, which do contain alarm sounds and speech fragments, but may as well contain additional stationary or instationary types of noise. It is worth noting, that the raw speech and noise material that forms the data set for this study is the same as used by Tchorz and Kollmeier (2002). Also the way of dividing into training and test set is left unchanged to allow for a comparison of the results.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Sub-band SNR estimation using auditory feature processing

Kleinschmidt

Hohmann

2003

Speech Communication

View full text Add to dashboard Cite

In this paper a new approach is presented for estimating the long-term speechto-noise ratio (SNR) in individual frequency bands that is based on methods known from automatic speech recognition (ASR). It uses a model of auditory perception as front end, physiologically and psychoacoustically motivated sigma-pi cells as secondary features, and a linear or non-linear neural network as classifier. A non-linear neural network back end is capable of estimating the SNR in time segments of 1s with a root-mean-square error of 5.68dB on unknown test material. This performance is obtained on a large set of natural types of noise, containing instationary signals and alarm sounds. However, the SNR estimation works best for more stationary types of noise. The individual components of the estimation algorithms are examined with respect to their importance for the estimation accuracy. The algorithm presented in this paper yields similar or better results with comparable computational effort relative to other methods known from the literature for shortterm SNR estimation. The new approach is purely based on slow spectro-temporal modulations and is therefore a valuable contribution to both, digital hearing aids and ASR systems. Zusammenfassung

show abstract

Section: Resultssupporting

confidence: 85%

Section: Methodsmentioning

confidence: 99%

Sub-band SNR estimation using auditory feature processing

Kleinschmidt

Hohmann

2003

Speech Communication

View full text Add to dashboard Cite

show abstract

“…In contrast to literature on modulation spectrograms (e.g., Tchorz and Kollmeier (2002)), signal processing techniques for cochlear implants (e.g., Rosen et al (1999)) and temporal aspects of speech intelligibility (e.g., Shannon et al (1995)), the modulation frequencies of interest in this paper are much higher (>100Hz). The primary object is to characterize the relationship of the modulation index at f 0 to other properties of speech, such as voicing strength, place of articulation and individual speaker differences.…”

Section: Introductionmentioning

confidence: 94%

Amplitude modulation of turbulence noise by voicing in fricatives

Pincas

Jackson

2006

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

The two principal sources of sound in speech, voicing and frication, occur simultaneously in voiced fricatives as well as at the vowel-fricative boundary in phonologically voiceless fricatives. Instead of simply overlapping, the two sources interact. This paper is an acoustic study of one such interaction effect: the amplitude modulation of the frication component when voicing is present. Corpora of sustained and fluent-speech English fricatives were recorded and analyzed using a signal-processing technique designed to extract estimates of modulation depth. Results reveal a pattern, consistent across speaking style, speaker, and place of articulation, for modulation at f0 to rise at low voicing strengths and subsequently saturate. Voicing strength needed to produce saturation varied 60–66dB across subjects and experimental conditions. Modulation depths at saturation varied little across speakers but significantly for place of articulation (with [z] showing particularly strong modulation) clustering at approximately 0.4–0.5 (a 40%–50% fluctuation above and below unmodulated amplitude); spectral analysis of modulating signals revealed weak but detectable modulation at the second and third harmonics (i.e., 2f0 and 3f0)

show abstract

“…Since σ 2 can be estimated during pause intervals (nonspeech activity) between speech signals, we assume that its value is known. A number of approaches [21][22][23] have been proposed over the past years for robust estimation of SNR. Applying these general arguments to the local energy features, we compensate these in the presence of noise by subtracting the estimated noise variance of a subsegment, Dσ 2 /T from the energies of the noisy subsegments, i.e.…”

Section: Hybrid Featuresmentioning

confidence: 99%

Towards robust phoneme classification with hybrid features

Yousafzai

Cvetković

Sollich

2010

2010 IEEE International Symposium on Information Theory

View full text Add to dashboard Cite

Abstract-In this paper, we investigate the robustness of phoneme classification to additive noise with hybrid features using support vector machines (SVMs). In particular, the cepstral features are combined with short term energy features of acoustic waveform segments to form a hybrid representation. The energy features are then taken into account separately in the SVM kernel, and a simple subtraction method allows them to be adapted effectively in noise. This hybrid representation contributes significantly to the robustness of phoneme classification and narrows the performance gap to the ideal baseline of classifiers trained under matched noise conditions.

show abstract

Estimation of the signal-to-noise ratio with amplitude modulation spectrograms

Cited by 18 publications

References 16 publications

Sub-band SNR estimation using auditory feature processing

Sub-band SNR estimation using auditory feature processing

Amplitude modulation of turbulence noise by voicing in fricatives

Towards robust phoneme classification with hybrid features

Contact Info

Product

Resources

About