Human interaction in natural language with computer systems has been a prime focus of research, and the field of conversational agents (including chatbots and Interactive Voice Response (IVR) systems) has evolved significantly since 2009, with a major boost in 2016, especially for industrial solutions. Emergency systems are crucial elements of today’s societies that can benefit from the advantages of intelligent human–computer interaction systems. In this paper, we present two solutions for human-to-computer emergency systems with critical deadlines that use a multi-layer FreeSwitch IVR solution and the Botpress chatbot platform. We are the pioneers in Romania who designed and implemented such a solution, which was evaluated in terms of performance and resource management concerning Quality of Service (QoS). Additionally, we assessed our Proof of Concept (PoC) with real data as part of the system for real-time Romanian transcription of speech and recognition of emotional states within emergency calls. Based on our feasibility research, we concluded that the telephony IVR best fits the requirements and specifications of the national 112 system, with the presented PoC ready to be integrated into the Romanian emergency system.

The evolution of Natural Language Processing technologies transformed them into viable choices for various accessibility features and for facilitating interactions between humans and computers. A subset of them consists of speech processing systems, such as Automatic Speech Recognition, which became more accurate and more popular as a result. In this article, we introduce an architecture built around various speech processing systems to enhance Romanian emergency services. Our system is designed to help the operator evaluate various situations with the end goal of reducing the response times of emergency services. We also release the largest high-quality speech dataset of more than 150 h for Romanian. Our architecture includes an Automatic Speech Recognition model to transcribe calls automatically and augment the operator’s notes, as well as a Speech Recognition model to classify the caller’s emotions. We achieve state-of-the-art results on both tasks, while our demonstrator is designed to be integrated with the Romanian emergency system.

Despite having approximately 24 million native speakers, Romanian remains a low-resource language for automatic speech recognition (ASR), with few accurate and publicly available systems. To address this gap, this study explores the challenges of adapting modern speech recognition models, such as wav2vec 2.0 and Conformer, to Romanian. Our investigation is a comprehensive analysis of the two models, their capabilities to adapt to Romanian data, and the performance of the trained models. The research also focuses on unique attributes of the Romanian language, data collection techniques, including weakly supervised learning, and processing methodologies. Building on the previously introduced Echo dataset of 378 h, we release CRoWL (Crawled Romanian Weakly Labeled), a weakly supervised dataset of 9000 h created via automatic transcription. We obtain strong results that, to the best of our knowledge, are competitive with or exceed publicly reported results for Romanian under comparable open evaluation settings, with Conformer attaining 3.01% WER on Echo + CRoWL and wav2vec 2.0 reaching 4.04% (Echo) and 4.17% (Echo + CRoWL). In addition to the datasets, we also release our most capable models as open source, along with their training plans, thereby providing a solid foundation for researchers interested in languages with limited representation.

Speaker diarization is a key component for multiple downstream speech technologies, including speech transcription, meeting analytics, and conversational understanding; however, Romanian lacks publicly established diarization resources and benchmarks. This paper evaluates cross-lingual transfer of diarization systems pretrained on predominantly English data, under a strict no-adaptation policy. We compare an end-to-end neural diarization approach (MSDD) and a traditional modular pipeline (segmentation + speaker embeddings + clustering), both used as is with pretrained components. To enable controlled analysis despite the lack of Romanian diarization datasets, we construct a synthetic Romanian conversational benchmark with explicit conditions on speaker count (2–5) and overlap regime (no overlap versus overlap). We report the diarization error rate (DER) and Jaccard error rate (JER) across all conditions, analyze sensitivity to overlap and the number of speakers, and provide an error-component breakdown to identify dominant failure modes. Across all conditions, the end-to-end system outperforms the pipeline (DER 0.140 versus 0.267; JER 0.152 versus 0.320). Performance degrades with overlap and with increasing speaker count in both paradigms, with speaker confusion dominating the additional error under overlap.