Digital processing of speech signals

Digital Coding of Waveforms

Reducing the interference noise in a monaural noisy speech signal has been a challenging task for many years. Compared to traditional unsupervised speech enhancement methods, e.g., Wiener filtering, supervised approaches, such as algorithms based on hidden Markov models (HMM), lead to higher-quality enhanced speech signals. However, the main practical difficulty of these approaches is that for each noise type a model is required to be trained a priori. In this paper, we investigate a new class of supervised speech denoising algorithms using nonnegative matrix factorization (NMF). We propose a novel speech enhancement method that is based on a Bayesian formulation of NMF (BNMF). To circumvent the mismatch problem between the training and testing stages, we propose two solutions. First, we use an HMM in combination with BNMF (BNMF-HMM) to derive a minimum mean square error (MMSE) estimator for the speech signal with no information about the underlying noise type. Second, we suggest a scheme to learn the required noise BNMF model online, which is then used to develop an unsupervised speech enhancement system. Extensive experiments are carried out to investigate the performance of the proposed methods under different conditions. Moreover, we compare the performance of the developed algorithms with state-of-the-art speech enhancement schemes using various objective measures. Our simulations show that the proposed BNMF-based methods outperform the competing algorithms substantially.

/pdf/supervised-and-unsupervised-speech-enhancement-using-4wn3tj6e0b.pdf

Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization

Existing speech enhancement algorithms can improve speech quality but not speech intelligibility, and the reasons for that are unclear. In the present paper, we present a theoretical framework that can be used to analyze potential factors that can influence the intelligibility of processed speech. More specifically, this framework focuses on the fine-grain analysis of the distortions introduced by speech enhancement algorithms. It is hypothesized that if these distortions are properly controlled, then large gains in intelligibility can be achieved. To test this hypothesis, intelligibility tests are conducted with human listeners in which we present processed speech with controlled speech distortions. The aim of these tests is to assess the perceptual effect of the various distortions that can be introduced by speech enhancement algorithms on speech intelligibility. Results with three different enhancement algorithms indicated that certain distortions are more detrimental to speech intelligibility degradation than others. When these distortions were properly controlled, however, large gains in intelligibility were obtained by human listeners, even by spectral-subtractive algorithms which are known to degrade speech quality and intelligibility.

/pdf/reasons-why-current-speech-enhancement-algorithms-do-not-d6joni8z73.pdf

Reasons why Current Speech-Enhancement Algorithms do not Improve Speech Intelligibility and Suggested Solutions

Speaker identity is one of the important characteristics of human speech. In voice conversion, we change the speaker identity from one to another, while keeping the linguistic content unchanged. Voice conversion involves multiple speech processing techniques, such as speech analysis, spectral conversion, prosody conversion, speaker characterization, and vocoding. With the recent advances in theory and practice, we are now able to produce human-like voice quality with high speaker similarity. In this article, we provide a comprehensive overview of the state-of-the-art of voice conversion techniques and their performance evaluation methods from the statistical approaches to deep learning, and discuss their promise and limitations. We will also report the recent Voice Conversion Challenges (VCC), the performance of the current state of technology, and provide a summary of the available resources for voice conversion research.

/pdf/an-overview-of-voice-conversion-and-its-challenges-from-3qss1ln75j.pdf

An Overview of Voice Conversion and Its Challenges: From Statistical Modeling to Deep Learning

In this chapter, we provide an overview of methods for speech quality assessment First, we define the term speech quality and outline in Sect 51 the main causes of degradation of speech quality Then, we discuss subjective test methods for quality assessment, with a focus on standardized methods Section 53 is dedicated to objective algorithms for quality assessment We conclude the chapter with a reference table containing common quality assessment scenarios and the corresponding most suitable methods for quality assessment

Speech Quality Assessment

Kalman filtering is a powerful technique for the estimation of a signal observed in noise that can be used to enhance speech observed in the presence of acoustic background noise. In a speech communication system, the speech signal is typically buffered for a period of 10-40 ms and, therefore, the use of either a causal or a noncausal filter is possible. We show that the causal Kalman algorithm is in conflict with the basic properties of human perception and address the problem of improving its perceptual quality. We discuss two approaches to improve perceptual performance. The first is based on a new method that combines the causal Kalman algorithm with pre- and postfiltering to introduce perceptual shaping of the residual noise. The second is based on the conventional Kalman smoother. We show that a short lag removes the conflict resulting from the causality constraint and we quantify the minimum lag required for this purpose. The results of our objective and subjective evaluations confirm that both approaches significantly outperform the conventional causal implementation. Of the two approaches, the Kalman smoother performs better if the signal statistics are precisely known, if this is not the case the perceptually weighted Kalman filter performs better.

On causal algorithms for speech enhancement

This paper presents ITU-T Embedded Variable Bit-Rate (EV-VBR) codec being standardized by Question 9 of Study Group 16 (Q9/16) as recommendation G.718. The codec provides a scalable solution for compression of 16 kHz sampled speech and audio signals at rates between 8 kbit/s and 32 kbit/s, robust to significant rates of frame erasures or packet losses. It comprises 5 layers where higher layer bitstreams can be discarded without affecting the lower layer decoding. The core layer takes advantage of signal-classification based CELP encoding. The second layer reduces the coding error from the first layer by means of additional pitch contribution and another algebraic codebook. The higher layers encode the weighted error signal from lower layers using MDCT transform coding. Sev-eral technologies are used to encode the MDCT coefficients for best performance both for speech and music. The codec performance is demonstrated with selected results from ITU-T Characterization test.

ITU-T EV-VBR: A robust 8-32 kbit/s scalable coder for error prone telecommunications channels

Postfilters are commonly used in speech coding for the attenuation of quantization noise. In the presence of acoustic background noise or distortion due to tandeming operations, the postfilter parameters are not adjusted and the performance is, therefore, not optimal. We propose a modification that consists of replacing the nonadaptive postfilter parameters with parameters that adapt to variations in spectral flatness, obtained from the noisy speech. This generalization of the postfiltering concept can handle a larger range of noise conditions, but has the same computational complexity and memory requirements as the conventional postfilter. Test results indicate that the presented algorithm improves on the standard postfilter, as well as on the combination of a noise attenuation preprocessor and the conventional postfilter.

Generalized Postfilter for Speech Quality Enhancement

We describe an algorithm for monitoring subjective speech quality without access to the original signal that has very low computational and memory requirements. The features used in the proposed algorithm can be computed from commonly used speech-coding parameters. Reconstruction and perceptual transformation of the signal are not performed. The algorithm generates quality assessment ratings without explicit distortion modeling. The simulation results indicate that the proposed non-intrusive objective quality measure performs better than the ITU-T P.563 standard despite its very low computational complexity.

Volodya Grancharov

Papers

Speech Quality Assessment

On causal algorithms for speech enhancement

ITU-T EV-VBR: A robust 8-32 kbit/s scalable coder for error prone telecommunications channels

Generalized Postfilter for Speech Quality Enhancement

Non-Intrusive Speech Quality Assessment with Low Computational Complexity