A study of complexity and quality of speech waveform coders

Tribolet, José; Noll, P.; McDermott, Barbara; Crochiere, R.

doi:10.1109/icassp.1978.1170567

Cited by 102 publications

(45 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clear reduction of speech quality is heard in comparison with original speech. Consequently, we utilize frequency-weighted segmental signal-to-noise ratio [32] to measure performance, which takes into account of phase information. Specifically, (14) where is the original noise-and reverberation-free signal, and is the processed signal.…”

Section: Results and Comparisonsmentioning

confidence: 99%

A two-stage algorithm for one-microphone reverberant speech enhancement

Wang

2006

IEEE Trans. Audio Speech Lang. Process.

161

View full text Add to dashboard Cite

Abstract-Under noise-free conditions, the quality of reverberant speech is dependent on two distinct perceptual components: coloration and long-term reverberation. They correspond to two physical variables: signal-to-reverberant energy ratio (SRR) and reverberation time, respectively. Inspired by this observation, we propose a two-stage reverberant speech enhancement algorithm using one microphone. In the first stage, an inverse filter is estimated to reduce coloration effects or increase SRR. The second stage employs spectral subtraction to minimize the influence of long-term reverberation. The proposed algorithm significantly improves the quality of reverberant speech. A comparison with a recent enhancement algorithm is made on a corpus of speech utterances in a number of reverberant conditions, and the results show that our algorithm performs substantially better.

show abstract

Section: Results and Comparisonsmentioning

confidence: 99%

A two-stage algorithm for one-microphone reverberant speech enhancement

Wang

2006

IEEE Trans. Audio Speech Lang. Process.

161

View full text Add to dashboard Cite

show abstract

“…For example, the phase of the reverberant speech Φ r i could be different from the phase of reconstructed signal Φ s i , because for a spectrogram-like matrix in the time-frequency domain, it is not guaranteed there exists a time-domain signal whose STFT is equal to that matrix [25]. Thus the following DSB is not reliable, and the dereverberated signal might have relative worse performance on temporal-domain measures, like frequency-weighted segmental signal-to-noise ratio (fwSegSNR) [26].…”

Section: Dnns-dsbmentioning

confidence: 99%

“…In addition, frequency weighted segmental SNR (fwSegSNR) [26], short-time objective intelligibility (STOI) [44], and perceptual evaluation of speech quality (PESQ) [45] were used to evaluate the system performance.…”

Section: Dnnspatialmentioning

confidence: 99%

A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation

Yang

Huang

et al. 2017

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

A reverberation-time-aware deep-neural-network (DNN)-based multi-channel speech dereverberation framework is proposed to handle a wide range of reverberation times (RT60s). There are three key steps in designing a robust system. First, to accomplish simultaneous speech dereverberation and beamforming, we propose a framework, namely DNNSpatial, by selectively concatenating log-power spectral (LPS) input features of reverberant speech from multiple microphones in an array and map them into the expected output LPS features of anechoic reference speech based on a single deep neural network (DNN). Next, the temporal auto-correlation function of received signals at different RT60s is investigated to show that RT60-dependent temporal-spatial contexts in feature selection are needed in the DNNSpatial training stage in order to optimize the system performance in diverse reverberant environments. Finally, the RT60 is estimated to select the proper temporal and spatial contexts before feeding the log-power spectrum features to the trained DNNs for speech dereverberation. The experimental evidence gathered in this study indicates that the proposed framework outperforms the state-of-the-art signal processing dereverberation algorithm weighted prediction error (WPE) and conventional DNNSpatial systems without taking the reverberation time into account, even for extremely weak and severe reverberant conditions. The proposed technique generalizes well to unseen room size, array geometry and loudspeaker position, and is robust to reverberation time estimation error.

show abstract

“…The following four metrics were used in order to assess the audio quality of the algorithms: the signal-to-interference ratio (SIR), the so-termed "target-related" perceptual score (TPS), a frequency-weighted signal-to-noise ratio (SNRF) [17], and the "auditory" bandwidth as the counterpart of the "articulatory" bandwidth [17]. The first two metrics were computed with the PEASS toolkit [18].…”

Section: Objective Performance Metricsmentioning

confidence: 99%

Informed Audio Source Separation Using Linearly Constrained Spatial Filters

Gorlow

Marchand

2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-In this work we readdress the issue of audio source separation in an informed scenario, where certain information about the sound sources is embedded into their mixture as an imperceptible watermark. In doing so, we provide a description of an improved algorithm that follows the linearly constrained minimum-variance filtering approach in the subband domain, in order to obtain perceptually better estimates of the source signals in comparison to other published approaches. Just as its predecessor, the algorithm does not impose any restrictions on the number of simultaneously active sources, neither on their spectral overlap. It rather adapts to a given signal constellation and provides the best possible estimates under given constraints in linearithmic time. The validity of the approach is demonstrated on a stereo mixture with two levels of sound complexity. It is also shown by means of both objective and subjective evaluation that the proposed algorithm outperforms a reference algorithm by at least one grade. Bearing high perceptual resemblance to the original signals at a fairly tolerable data rate of 10-20 kbps per source, the algorithm hence seems well-suited for active listening applications such as re-mixing or re-spatialization in real time.Index Terms-Array signal processing, audio quality assessment, audio watermarking, informed audio source separation.

show abstract

A study of complexity and quality of speech waveform coders

Cited by 102 publications

References 7 publications

A two-stage algorithm for one-microphone reverberant speech enhancement

A two-stage algorithm for one-microphone reverberant speech enhancement

A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation

Informed Audio Source Separation Using Linearly Constrained Spatial Filters

Contact Info

Product

Resources

About