arXiv subjects

Alexander Erdmann

Publications and source records attributed to Alexander Erdmann.

3 recordsLinked to original sources

arXiv2026

Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents

Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to the limited memory constraints of real-time processing, these systems are adversely impacted by conversational phenomena such as long silences and backchannels. While many agentic pipelines mitigate this by resetting state at each turn, this approach discards vital context and impairs performance at turn onsets. We propose two state-management strategies that preserve cross-utterance context to reduce onset errors. In experiments with two state-of-the-art streaming models on two spoken dialogue benchmarks, our best method yields an average of 15-21% relative WER reduction at utterance onsets.

cs.LG↗

arXiv2020

The Paradigm Discovery Problem

This work treats the paradigm discovery problem (PDP), the task of learning an inflectional morphological system from unannotated sentences. We formalize the PDP and develop evaluation metrics for judging systems. Using currently available resources, we construct datasets for the task. We also devise a heuristic benchmark for the PDP and report empirical results on five diverse languages. Our benchmark system first makes use of word embeddings and string similarity to cluster forms by cell and by paradigm. Then, we bootstrap a neural transducer on top of the clustered data to predict words to realize the empty paradigm slots. An error analysis of our system suggests clustering by cell across different inflection classes is the most pressing challenge for future work. Our code and data are available for public use.

cs.CL↗

arXiv2017

Low Resourced Machine Translation via Morpho-syntactic Modeling: The Case of Dialectal Arabic

We present the second ever evaluated Arabic dialect-to-dialect machine translation effort, and the first to leverage external resources beyond a small parallel corpus. The subject has not previously received serious attention due to lack of naturally occurring parallel data; yet its importance is evidenced by dialectal Arabic's wide usage and breadth of inter-dialect variation, comparable to that of Romance languages. Our results suggest that modeling morphology and syntax significantly improves dialect-to-dialect translation, though optimizing such data-sparse models requires consideration of the linguistic differences between dialects and the nature of available data and resources. On a single-reference blind test set where untranslated input scores 6.5 BLEU and a model trained only on parallel data reaches 14.6, pivot techniques and morphosyntactic modeling significantly improve performance to 17.5.

cs.CL↗