RÉSUMÉ: L'objectif de cet article est de présenter un outil développé en vue de modéliser semi-automatiquement la structure prosodique du français. Sur la base d'un alignement en phonèmes, notre système procède à la détection des syllabes proéminentes en prenant en considération des critères acoustiques basiques tels que la f0, la durée et la présence de pauses. À partir des mesures ainsi prises, le système attribue un degré de proéminence à chacune des syllabes identifiées comme saillante. Nous illustrons ensuite les résultats de l'analyse d'extraits du corpus PROSO_FR. Plus précisément, nous comparons l'analyse prosodique de phrases que l'on pourrait faire avec les règles traditionnelles de la phonologie prosodique avec l'analyse conduite par notre logiciel. Nous discutons ainsi de trois règles: la règle de dominance droite, la règle de clash accentuel et la règle des sept syllabes.
Vocal communication is widespread in animals, with vocal repertoires of varying complexity. The social complexity hypothesis predicts that species may need high vocal complexity to deal with complex social organization (e.g. have a variety of different interindividual relations). We quantified the vocal complexity of two geographically distant captive colonies of rooks, a corvid species with complex social organization and cognitive performances, but understudied vocal abilities. We quantified the diversity and gradation of their repertoire, as well as the inter-individual similarity at the vocal unit level. We found that males produced call units with lower diversity and gradation than females, while song units did not differ between sexes. Surprisingly, while females produced highly similar call repertoires, even between colonies, each individual male produced almost completely different call repertoires from any other individual. These findings question the way male rooks communicate with their social partners. We suggest that each male may actively seek to remain vocally distinct, which could be an asset in their frequently changing social environment. We conclude that inter-individual similarity, an understudied aspect of vocal repertoires, should also be considered as a measure of vocal complexity.
19 February 2018 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
This paper presents non-negative factorization of audio signals for the binaural localization of multiple sound sources within realistic and unknown sound environments. Non-negative tensor factorization (NTF) provides a sparse representation of multichannel audio signals in time, frequency, and space that can be exploited in computational audio scene analysis and robot audition for the separation and localization of sound sources. In the proposed formulation, each sound source is represented by means of spectral dictionaries, temporal activation, and its distribution within each channel (here, left and right ears). This distribution, being dependent on the frequency, can be interpreted as an explicit estimation of the Head-Related Transfer Function (HRTF) of a binaural head which can then be converted into the estimated sound source position. Moreover, the semisupervised formulation of the non-negative factorization allows us to integrate prior knowledge about some sound sources of interest whose dictionaries can be learned in advance, whereas the remaining sources are considered as background sound, which remains unknown and is estimated on the fly. The proposed NTF-based sound source localization is applied here to binaural sound source localization of multiple speakers within realistic sound environments.
Voice conversion (VC) consists of digitally altering the voice of an individual to manipulate part of its content, primarily its identity, while maintaining the rest unchanged. Research in neural VC has accomplished considerable breakthroughs with the capacity to falsify a voice identity using a small amount of data with a highly realistic rendering. This paper goes beyond voice identity manipulation and presents an original neural architecture that allows the manipulation of voice attributes (e.g., gender and age). The proposed architecture is inspired by the fader network, transferring the same ideas to voice manipulation. The information conveyed by the speech signal is disentangled into interpretative voice attributes by means of minimizing adversarial loss to make the encoded information mutually independent while preserving the capacity to generate a speech signal from the disentangled codes. During inference for voice conversion, the disentangled voice attributes can be manipulated and the speech signal can be generated accordingly. For experimental evaluation, the proposed method is applied to the task of voice gender conversion using the freely available VCTK dataset. Quantitative measurements of mutual information between the variables of speaker identity and speaker gender show that the proposed architecture can learn gender-independent representation of speakers. Additional measurements of speaker recognition indicate that speaker identity can be recognized accurately from the gender-independent representation. Finally, a subjective experiment conducted on the task of voice gender manipulation shows that the proposed architecture can convert voice gender with very high efficiency and good naturalness.
In this paper, we present a study on the influence of the expressivity on the articulation degree. It is part of a project that aims to transform the expressivity of an utterance for artistic purposes, such as cinema, theater and contemporary music. An algorithm for formant frequency estimation is presented. Then a measurement of the articulation degree is proposed involving a joint statistical analysis of the vocalic triangle area and of the speech rate. The application of this measurement to an expressive French database, shows that the articulation degree depends on expressivity. Using Lindblom's theoretical framework, we have tried to relate this articulation degree to the activation degree of a dimensional representation of emotions. Finally, speech processing is used to modify the articulation degree of a spoken or synthesized neutral utterance in order to apply a given expressivity to it.
In this paper we discuss French prosody in the light of language contact. Data of three contact varieties of French are compared with two varieties spoken in monolingual contexts. The data are semi-automatically processed, and three prosodic features are analyzed: metrical weight of the Accentual Phrases (AP), respect of AP formation constraints, and realizations of sandhi phenomena. Rhythmic constraints and speech rate measurements are also considered. Our findings suggest that the contact varieties share several features with word prosodic systems.