Depression is a common mental disorder that is usually addressed by outpatient treatments that favour patients’ inclusion in the society. This raises the need for tools to remotely monitor the emotional state of the patients, which can be carried out via telephone or the Internet using speech processing approaches. However, these strategies lead to privacy concerns caused by the transmission of the patients’ speech and its subsequent storage in servers. The use of speech de‐identification to protect the privacy of these patients seems straightforward, but the influence of this procedure in the manifestation of the disease in the patients’ speech has not been addressed yet. Hence, this study evaluates the performance of an automatic depression level estimation system when dealing with original and de‐identified speech, in order to analyse the influence of the de‐identification procedure in the detection of depression. Two de‐identification approaches based on voice transformation via frequency warping and amplitude scaling are assessed, which can be applied to any speaker without additional training. Experiments carried out in the framework of the audio/visual emotion challenge 2014 show that the proposed de‐identification approaches achieve promising de‐identification results at the expense of a slight degradation of depression detection.

This paper presents a new method for cross-lingual speaker adaptation in the framework of HMM-based speech synthesis. Taking two HTS voice models as input, one for the desired language and another for the aimed speaker identity, it yields a third model that produces speech in the target language while sounding like the target speaker. The method operates at segmental level (spectral information and average fundamental frequency) and does not require any phonetic or linguistic information. Perceptual evaluation experiments show that, when the input models are good enough, the resulting synthetic voice is perceived as similar to the target speaker with no important quality degradation.

Postfiltering is a well known technique that helps increasing the quality of coded speech, enhancing speech intelligibility or alleviating the oversmoothing effect of statistical speech processing methods. This letter presents a new formulation of the radial cepstral postfiltering method that enables the application of different postfiltering factors to low and high frequencies. The transition between bands will be smooth and controllable through an adjustable cut-off frequency. The proposed algorithm can be implemented by means of a simple multiplicative matrix of which an analytical expression is derived. The new method provides a flexible framework to tackle issues related to the quality and intelligibility of synthetic speech.

This paper introduces the Synthetic Speech Detection system developed by Aholab for the Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2015). The detector is a classifier based on Gaussian Mixture Models that are created using the Relative Phase Shift (RPS) transformation for the phase information. Different strategies have been evaluated: modeling the specific attacks using the information provided by the ASVspoof 2015 organizers, and modeling the vocoders possibly used in the spoofing signals, using data from previous works. The evaluation results show that attack specific models work for known attacks but they do not cope with the unknown attacks correctly. When using vocoder models build with other databases, the results suggest that the followed strategy do not take advantage of the available data and thus model adaptation should be explored. Index Terms: synthetic speech detection, phase information, anti-spoofing

In the field of speaker verification (SV) it is nowadays feasible and relatively easy to create a synthetic voice to deceive a speech driven biometric access system. This paper presents a synthetic speech detector that can be connected at the front-end or at the back-end of a standard SV system, and that will protect it from spoofing attacks coming from state-of-the-art statistical Text to Speech (TTS) systems. The system described is a Gaussian Mixture Model (GMM) based binary classifier that uses natural and copy-synthesized signals obtained from the Wall Street Journal database to train the system models. Three different state-of-the-art vocoders are chosen and modeled using two sets of acoustic parameters: 1) relative phase shift and 2) canonical Mel Frequency Cepstral Coefficients (MFCC) parameters, as baseline. The vocoder dependency of the system and multivocoder modeling features are thoroughly studied. Additional phase-aware vocoders are also tested. Several experiments are carried out, showing that the phase-based parameters perform better and are able to cope with new unknown attacks. The final evaluations, testing synthetic TTS signals obtained from the Blizzard challenge, validate our proposal.

Various parametric representations have been proposed to model the speech signal. While the performance of such vocoders is well-known in the context of speech processing, their extrapolation to singing voice synthesis might not be straightforward. The goal of this paper is twofold. First, a comparative subjective evaluation is performed across four existing techniques suitable for statistical parametric synthesis: traditional pulse vocoder, Deterministic plus Stochastic Model, Harmonic plus Noise Model and GlottHMM. The behavior of these techniques as a function of the singer type (baritone, counter-tenor and soprano) is studied. Secondly, the artifacts occurring in high-pitched voices are discussed and possible approaches to overcome them are suggested.

When speaking devices such as smartphones, tablet-PCs, or GPS systems are used in noisy outdoor environments, the intelligibility of speech significantly drops. This is even more pronounced when synthetic speech is used. This article describes how a statistical parametric speech synthesis system trained on an ordinary synthesis database can be designed to generate highly intelligible speech, even at very low signal-to-noise ratios. By using a simple and flexible vocoder based on a full-band harmonic model, the proposed system applies deterministic noise-independent modifications at several levels: speaking rate, average fundamental frequency level and range, energy contour over time, formant sharpness, and intensity of specific spectral bands. The degree of intelligibility achieved by the system has been evaluated by means of a large-scale subjective test, the results of which show that the suggested approach clearly outperforms a reference state-of-the-art TTS system and also unmodified natural speech in some conditions. In comparison with alternative systems evaluated in the same framework, the proposed one exhibits the best performance in the scenarios with lowest signal-to-noise ratio. Finally, the impact of the suggested modifications on naturalness, quality and similarity to the original natural voice is quantified by means of a subjective test.

Voice conversion methods based on frequency warping followed by amplitude scaling have been recently proposed. These methods modify the frequency axis of the source spectrum in such manner that some significant parts of it, usually the formants, are moved towards their image in the target speaker's spectrum. Amplitude scaling is then applied to compensate for the differences between warped source spectra and target spectra. This article presents a fully parametric formulation of a frequency warping plus amplitude scaling method in which bilinear frequency warping functions are used. Introducing this constraint allows for the conversion error to be described in the cepstral domain and to minimize it with respect to the parameters of the transformation through an iterative algorithm, even when multiple overlapping conversion classes are considered. The paper explores the advantages and limitations of this approach when applied to a cepstral representation of speech. We show that it achieves significant improvements in quality with respect to traditional methods based on Gaussian mixture models, with no loss in average conversion accuracy. Despite its relative simplicity, it achieves similar performance scores to state-of-the-art statistical methods involving dynamic features and global variance.

Currently, the statistical framework based on Hidden Markov Models (HMMs) plays a relevant role in speech synthesis, while voice conversion systems based on Gaussian Mixture Models (GMMs) are almost standard. In both cases, statistical modeling is applied to learn distributions of acoustic vectors extracted from speech signals, each vector containing a suitable parametric representation of one speech frame. The overall performance of the systems is often limited by the accuracy of the underlying speech parameterization and reconstruction method. The method presented in this paper allows accurate MFCC extraction and high-quality reconstruction of speech signals assuming a Harmonics plus Noise Model (HNM). Its suitability for high-quality HMM-based speech synthesis is shown through subjective tests.

Statistical parametric synthesizers have achieved very good performance scores during the last years. Nevertheless, as they require the use of vocoders to parameterize speech (during training) and to reconstruct waveforms (during synthesis), the speech generated from statistical models lacks some degree of naturalness. In previous works we explored the usefulness of the harmonics plus noise model in the design of a high-quality speech vocoder. Quite promising results were achieved when this vocoder was integrated into a synthesizer. In this paper, we describe some recent improvements related to the excitation parameters, particularly the so called maximum voiced frequency. Its estimation and explicit modelling leads to an even better synthesis performance as confirmed by subjective comparisons with other well-known methods.

Any modification applied to speech signals has an impact on their perceptual quality. In particular, voice conversion to modify a source voice so that it is perceived as a specific target voice involves prosodic and spectral transformations that produce significant quality degradation. Choosing among the current voice conversion methods represents a trade-off between the similarity of the converted voice to the target voice and the quality of the resulting converted speech, both rated by listeners. This paper presents a new voice conversion method termed Weighted Frequency Warping that has a good balance between similarity and quality. This method uses a time-varying piecewise-linear frequency warping function and an energy correction filter, and it combines typical probabilistic techniques and frequency warping transformations. Compared to standard probabilistic systems, Weighted Frequency Warping results in a significant increase in quality scores, whereas the conversion scores remain almost unaltered. This paper carefully discusses the theoretical aspects of the method and the details of its implementation, and the results of an international evaluation of the new system are also included.

Most existing voice conversion systems, particularly those based on Gaussian mixture models, require a set of paired acoustic vectors from the source and target speakers to learn their corresponding transformation function. The alignment of phonetically equivalent source and target vectors is not problematic when the training corpus is parallel, which means that both speakers utter the same training sentences. However, in some practical situations, such as cross-lingual voice conversion, it is not possible to obtain such parallel utterances. With an aim towards increasing the versatility of current voice conversion systems, this paper proposes a new iterative alignment method that allows pairing phonetically equivalent acoustic vectors from nonparallel utterances from different speakers, even under cross-lingual conditions. This method is based on existing voice conversion techniques, and it does not require any phonetic or linguistic information. Subjective evaluation experiments show that the performance of the resulting voice conversion system is very similar to that of an equivalent system trained on a parallel corpus.

Voice conversion has been traditionally focused on spectrum. Current systems lack a solid prosody conversion method suitable for different speaking styles. Recently, the unit selection technique has been applied to transform emotional intonation contours. This paper goes one step beyond: it explores strategies for training and configuring the selection cost function in an emotion conversion application. The proposed system, which uses accent groups as basic intonation units and performs conversion also on phoneme durations and intensity, is evaluated by means of a carefully designed subjective test involving the big six emotions. Although the expressiveness of the converted sentences is still far from that of natural emotional speech, satisfactory results are obtained when different configurations are used for different emotions.

In current voice conversion systems, obtaining a high similarity between converted and target voices requires a high degree of signal manipulation, which implies important quality degradation, up to the point that in some cases the quality scores are unacceptable for real-life applications. Indeed, a tradeoff can be observed between the similarity scores and the quality scores achieved by a given voice conversion system. In our previous works we proved that statistical methods and frequency warping transformations could be combined to yield a better similarity-quality balance than conventional systems, due to significant quality improvements. In this paper, two different ways of combining these two approaches are compared through perceptual tests in order to determine the best strategy for high-quality voice conversion. The comparison is made under the same training conditions, using the same speech model and vector dimensions. The results indicate that the Weighted Frequency Warping method is preferred by listeners.

This paper presents a new voice conversion method called Weighted Frequency Warping (WFW), which combines the well known GMM approach and the frequency warping approach. The harmonic plus stochastic model has been used to analyze, modify and synthesize the speech signal. Special phase manipulation procedures have been designed to allow the system to work in pitch-asynchronous mode. The experiments show that the proposed technique reaches a high degree of similarity between the converted and target speakers, and the naturalness and quality of the resynthesized speech is much higher than those of classical GMM-based systems. Index Terms: voice conversion, speech synthesis, harmonic model, GMM, weighted frequency warping

Most of the existing voice conversion methods calculate the optimal transformation function from a given set of paired acoustic vectors of the source and target speakers. The alignment of the phonetically equivalent source and target frames is problematic when the training corpus available is not parallel, although this is the most realistic situation. The alignment task is even more difficult in cross-lingual applications because the phoneme sets may be different in the involved languages. In this paper, a new iterative alignment method based on acoustic distances is proposed. The method is shown to be suitable for text-independent and cross-lingual voice conversion, and the conversion scores obtained in our evaluation experiments are not far from the performance achieved by using parallel training corpora. Index Terms: speech synthesis, cross-lingual voice conversion, alignment, GMM, weighted frequency warping