Speech disorders are significant barriers to the balanced development of a child. Many children in Poland are affected by lisps (sigmatism)-the incorrect articulation of sibilants. Since speech therapy diagnostics is complex and multifaceted, developing computer-assisted methods is crucial. This paper presents the results of assessing the usefulness of hybrid feature vectors extracted based on multimodal (video and audio) data for the place of articulation assessment in sibilants /s/ and /ʂ/. We used acoustic features and, new in this field, visual parameters describing selected articulators' texture and shape. Analysis using statistical tests indicated the differences between various sibilant realizations in the context of the articulation pattern assessment using hybrid feature vectors. In sound /s/, 35 variables differentiated dental and interdental pronunciation, and 24 were visual (textural and shape). For sibilant /ʂ/, we found 49 statistically significant variables whose distributions differed between speaker groups (alveolar, dental, and postalveolar articulation), and the dominant feature type was noise-band acoustic. Our study suggests hybridizing the acoustic description with video processing provides richer diagnostic information. Since speech therapy diagnostics is complex and multifaceted, developing computer-assisted methods is crucial. This paper presents the results of assessing the usefulness of hybrid feature vectors extracted based on multimodal (video and audio) data for the place of articulation assessment in sibilants /s/ and /ʂ/. We used acoustic features and, new in this field, visual parameters describing selected articulators’ texture and shape. Analysis using statistical tests indicated the differences between various sibilant realizations in the context of the articulation pattern assessment using hybrid feature vectors. Neglecting speech defects that appear in childhood may further deepen them and, as a result, affect adult life. Studies conducted in the 1980s among Polish children reported the occurrence of disorders in approximately 20–30% of In Polish, there are 12 sibilants, denoted using the International Phonetic Alphabet (IPA) as /s/, /z/, /ʦ/, /dz/, /ʂ/, /ʐ/, /tʂ/, /dʐ/, /ɕ/, /ʑ/, /ʨ/, /ʥ/. However, in this study, we analyze only two sibilants: /s/ and /ʂ/, regarding their place of articulation. 1.1. Background and State of the Art Speech diagnosis is a complex process. Specialists assess not only free speech (incl. vocabulary, correctness of sentence construction, fluency, and prosody) but also selected anatomical and physiological aspects [ 2 , 3 ]. Features related to motor skills and the structure of articulators (i.e., organs involved in speech generation) include, for example, the degree of shortening of the lingual frenulum, teeth condition, bite, temporomandibular joint efficiency, and the structure of the palate and nasal cavity. Characteristics related to the subject’s physiology include assessment of phonemic and physical hearing and breathing and swallowing functions. The last group describes features associated with the production of individual sounds, mainly regarding the manner and places of articulation and the position of articulators. The place of articulation we analyze in this study is crucial in terms of sibilant formation [ 2 , 3 ]. Not only do the sounds differ in their place of articulation, but slight deviations from the regular position of the articulators may be identified as sigmatism [ 4 ]. The literature distinguishes multiple pronunciation patterns ( Figure 1 ), incl. The analysis of dental sounds in the literature often employs the processing of the signal spectrum. The use of spectral moments appears in many works [ 19 , 20 ]. Researchers have reported that the center of gravity of the spectrum shifts in sibilants depending on the place of articulation [ 18 ]. Another group of acoustic parameters describing dental sounds are features related to frication noise. Some works focused on searching for differences between sounds in the frequencies and amplitudes of noise formants that appear in the spectrum above 2 or 3 kHz [ 22 , 26 , 27 ]. Contribution of the Paper In this paper, we propose hybridizing acoustic and visual features to assess articulation. Such combining may indicate patterns in various aspects (e.g., not seen in one modality but supplemented by the other) and expand diagnostic information. Changes in the place of articulation often yield an abnormal realization of sounds. We analyzed the articulation of two fricative Polish sibilants: /s/ and /ʂ/ produced by children aged 5–8 (183 and 178 speakers, respectively). The preliminary results presented in this paper indicate the potential of hybridization of visual and audio features in searching for differences in the place of articulation between various realizations of sibilants. That concept benefits in richer diagnostic information. Nevertheless, this study had some limitations, and the proposed idea still has many possibilities for development. We want to extend our research by adding other sounds and articulation features. This preliminary study is a good starting point for constructing expert systems supporting the speech therapy diagnosis of sigmatism. Conclusions In this paper, we addressed combining acoustic and visual features to analyze the place of articulation in Polish sibilants /s/ and /ʂ/. The results justify searching for relevant features in different representations of articulation. The Mann–Whitney U tests indicated variables (both visual and acoustic) that significantly differentiate dental and interdental articulation patterns in /s/. The predominating parameters were visual, including tongue shape and mouth texture features. The Kruskal–Wallis test also showed statistically significant differences between alveolar, dental, and postalveolar pronunciations in /ʂ/, yet with the predominance of acoustic noise-band features.