Search

International audience; This paper uses the recent glottal flow model for iterative adaptive inverse filtering to analyze recordings from dysfunctional speakers, namely those with larynx-related impairment such as laryngectomy. The analytical model allows extraction of the voice source spectrum, described by a compact set of parameters. This single model is used to visualize and better understand speech production characteristics across impaired and nonimpaired voices. The analysis reveals some discriminative aspects of the source model which map to a physiological class description of those impairments. Furthermore, being based on analysis of source parameters only, it is complementary to any existing techniques of vocal-tract or phonetic analysis. The results indicate the potential for future automated speech reconstruction systems that adapt to the method of reconstruction required, as well as being useful for mainstream speech systems, such as ASR, in which front-end analysis can direct back-end models to suit characteristics of impaired speech.

Speech glottal flow has been predominantly described in the time-domain in past decades, the Liljencrants-Fant (LF) model being the most widely used in speech analysis and synthesis, despite its computational complexity. The causal/anti-causal linear model (LF

International audience; Whisper-to-speech conversion is motivated by laryngeal disorders, in which malfunction of the vocal folds leads to loss of voicing. Many patients with laryngeal disorders can still produce functional whispers, since these are characterised by the absence of vocal fold vibration. Whispers therefore constitute a common ground for speech rehabilitation across many kinds of laryngeal disorder. Whisper-to-speech conversion involves recreating natural-sounding speech from recorded whispers, and is a non-invasive and non-surgical rehabilitation that can maintain a natural method of speaking, unlike the existing methods of rehabilitation. This paper proposes a new rule-based method for whisper-to-speech conversion that replaces the noisy whisper sound source with a synthesised speech-like harmonic source, while maintaining the vocal tract component unaltered. In particular, a novel glottal source generator is developed in which whisper information is used to parameterise the excitation through a high-quality glottis model. Evaluation of the system against the standard pulse train excitation method reveals significantly improved performance. Since our method is glottis-based, it is potentially compatible with the many existing vocal tract component adaptation systems.

International audience; Neural vocoders are systematically evaluated on homogeneous train and test databases. This kind of evaluation is efficient to compare neural vocoders in their "comfort zone", yet it hardly reveals their limits towards unseen data during training. To compare their extrapolation capabilities, we introduce a methodology that aims at quantifying the robustness of neural vocoders in synthesising unseen data, by precisely controlling the ranges of seen/unseen data in the training database. By focusing in this study on the pitch (F0) parameter, our methodology involves a careful splitting of a dataset to control which F0 values are seen/unseen during training, followed by both global (utterance) and local (frame) evaluation of vocoders. Comparison of four types of vocoders (autoregressive, sourcefilter, flows, GAN) displays a wide range of behaviour towards unseen input pitch values, including excellent extrapolation (WaveGlow); widely-spread F0 errors (WaveRNN); and systematic generation of the training set median F0 (LPCNet, Parallel WaveGAN). In contrast, fewer differences between vocoders were observed when using homogeneous train and test sets, thus demonstrating the potential and need for such evaluation to better discriminate the neural vocoders abilities to generate out-of-training-range data.

International audience; Audio books are commonly used to train text-to-speech models (TTS), as they offer large phonetic content with rather expressive pronunciation, but number and sizes of publicly available audio books corpora differ between languages. Moreover, the quality and accuracy of the available utterance segmentations are debatable. Yet, the impact of segmentation on the output synthesis is not well established. Additionally, utterances are generally used individually, without taking advantage of text level structuring information, even though they influence speaker reading. In this paper, we conduct a multidimensional evaluation of Tacotron2 trained on different segmentations and text level annotations of the same French corpus. We show that both spectrum accuracy and expressiveness depend on the segmentation used. In particular, a shorter segmentation, in addition with the annotation of paragraphs, benefits to spectrum reconstruction at the detriment of phrasing. Multidimensional analysis of mean opinion scores obtained with a MUSHRA-experiment revealed that phrasing was relatively more important than spectrum accuracy in perceptual judgement. This work serves as evidence that particular attention must be given to models evaluation, as well as how to use the training corpus to maximize synthesis characteristics of interest.

Digital plays a key role in the transformation of medicine. Beyond the simple computerisation of healthcare systems, many non-drug treatments are now possible thanks to digital technology. Thus, interactive stimulation exercises can be offered to people suffering from cognitive disorders, such as developmental disorders, neurodegenerative diseases, stroke or traumas. The efficiency of these new treatments, which are still primarily offered face-to-face by therapists, can be greatly improved if patients can pursue them at home. However, patients are left to their own devices which can be problematic. We introduce THERADIA, a 5-year project that aims to develop an empathic virtual agent that accompanies patients while receiving digital therapies at home, and that provides feedback to therapists and caregivers. We detail the architecture of our agent as well as the framework of our Wizard-of-Oz protocol, designed to collect a large corpus of interactions between people and our virtual assistant in order to train our models and improve our dialogues.

International audience

International audience; Cantor Digitalis is a performative singing synthesizer that is composed of two main parts: a chironomic control interface and a parametric voice synthesizer. The control interface is based on a pen/touch graphic tablet equipped with a template representing vocalic and melodic spaces. Hand and pen positions, pen pressure, and a graphical user interface are assigned to specific vocal controls. This interface allows for real-time accurate control over high-level singing synthesis parameters. The sound generation system is based on a parametric synthesizer that features a spectral voice source model, a vocal tract model consisting of parallel filters for vocalic formants and cascaded with anti-resonance for the spectral effect of hypo-pharynx cavities, and rules for parameter settings and source/filter dependencies between fundamental frequency, vocal effort, and formants. Because Cantor Digitalis is a parametric system, every aspect of voice quality can be controlled (e.g., vocal tract size, aperiodicities in the voice source, vowels, and so forth). It offers several presets for different voice types. Cantor Digitalis has been played on stage in several public concerts, and it has also been proven to be useful as a tool for voice pedagogy. The aim of this article is to provide a comprehensive technical overview of Cantor Digitalis.

International audience; Audio, visual, and proprioceptive actions are involved when manipulating a graphic tablet musical interface. Previous works suggested a possible dominance of the visual over the auditory modality in this situation. The main goal of the present study is to examine the interferences between these modalities in visual, audio, and audiovisual target acquisition tasks. Experiments are based on a movement replication paradigm, where a subject controls a cursor on a screen or the pitch of a synthesized sound by changing the stylus position on a covered graphic tablet. The experiments consisted of the following tasks: (1) a target acquisition task that was aimed at a visual target (reaching a cue with the cursor displayed on a screen), an audio target (reaching a reference note by changing the pitch of the sound played in headsets), or an audiovisual target, and (2) the replication of the target acquisition movement in the opposite direction. In the return phase, visual and audio feedback were suppressed. Different gain factors perturbed the relationships among the stylus movements, visual cursor movements, and audio pitch movements. The deviations between acquisition and return movements were analyzed. The results showed that hand amplitudes varied in accordance with visual, audio, and audiovisual perturbed gains, showing a larger effect for the visual modality. This indicates that visual, audio, and audiovisual actions interfered with the motor modality and confirms the spatial representation of pitch reported in previous studies. In the audiovisual situation, vision dominated over audition, as the latter had no significant influence on motor movement. Consequently, visual feedback is helpful for musical targeting of pitch on a graphic tablet, at least during the learning phase of the instrument. This result is linked to the underlying spatial organization of pitch perception. Finally, this work brings a complementary approach to previous studies showing that audition may dominate over vision for other aspects of musical sound (e.g., timing, rhythm, and timbre).