We describe the Itgan systems for the three ASR subtasks of NADI 2026, namely robust country-level ASR (1.1), mixed-dialect ASR (1.2), and Tunisian code-switched ASR (1.3). All three share one recipe, Whisper adapted with LoRA on consumer GPUs, and each was carried by a different addition to it. On 1.1, where the dialect label is given at test time, per-dialect specialists continued from a pooled adapter gave the largest gain, and the submitted system reached 57.1% country-average WER. A post-evaluation linear probe on frozen encoder features routes utterances without the label and recovers 44% of what oracle routing gives. On 1.2 the choice of base model mattered more than adapter capacity, and system combination helped only once we added a decorrelated member, reaching 46.7% WER. On 1.3 our system placed second at 14.49% WER with the lowest CER among the leading submissions, 5.38%. Its last 0.60 WER points came without further training, mostly from an exact weight-space average of independently trained runs, with ROVER voting adding the remainder. Every comparison carries a paired-bootstrap test, and we report eight directions that did not work.

We describe our submissions to the four subtasks of the AraSeg 2026 shared task in both tracks. Our components are conventional word-level boundary taggers, and our contribution is a measurement of what combining them is worth. Averaging 21 members gains +0.89 F1 over the best single model, and replacing the uniform probability average with a learned logistic combiner adds a further +0.23 (+1.12 in total), reaching significance only on the two subtasks that lack punctuation. Both are smaller than the encoder swap (+1.82). What the combiner buys is freedom from curation. Added to the base encoder, each of six different pretrained encoders helps under the combiner (+0.12 to +0.72, mean +0.34), whereas under averaging three of the six are harmful, by as much as 0.62. Another seed of an existing encoder is worth nothing under either rule; members should therefore be diversified rather than curated, provided the weights are learned. We also report three null results for inference-time structure, including a semi-Markov CRF whose failure we trace to a length prior that is uninformative at corpus level. Our closed-track systems placed fifth and seventh where ranked. In the open track, pretraining on 3.2M tokens of silver boundaries from Arabic Wikipedia before fine-tuning on the gold training split is worth +0.58 F1, and two of the closed-track findings reproduce on that external data.

This contribution describes an on-going projects a smartphone application called Voice Äpp, which is a follow-up of a previous application called Dialäkt Äpp. The main purpose of both apps is to identify the user’s Swiss German dialect on the basis of the dialectal variations of 15 words. The result is returned as one or more geographical points on a map. In Dialäkt Äpp, launched in 2013, the user provides his or her own pronunciation through buttons, while the Voice Äpp, currently in development, asks users to pronounce the word and uses speech recognition techniques to identify the variants and localize the user. This second app is more challenging from a technical point of view but nevertheless recovers the nature of dialect variation of spoken language. Besides, the Voice Äpp takes its users on a journey in which they explore the individuality of their own voices, answering questions such as: How high is my voice? How fast do I speak? Do I speak faster than users in the neighbouring city?