End-to-end (E2E) spoken dialogue systems are replacing cascaded pipelines for voice-based human-AI interaction. Existing benchmarks primarily evaluate these systems on synthetic speech and single-turn tasks, leaving multi-turn conversational ability underexplored. We introduce Audio MultiChallenge an open-source benchmark to evaluate these systems under natural multi-turn interaction patterns. Building on the text-based MultiChallenge framework, which evaluates Inference Memory, Instruction Retention, and Self Coherence, we introduce a new axis Voice Editing that tests robustness to mid-utterance speech repairs and backtracking. We augment each axis to the audio modality, such as introducing Audio-Cue challenges for Inference Memory that require recalling ambient sounds and paralinguistic signals beyond semantic content. We curate 452 conversations from 47 speakers with 1,712 instance-specific rubrics through a hybrid pipeline that exposes model failures at scale while preserving natural disfluencies found in unscripted human speech. Our evaluation reveals that even frontier models struggle on our benchmark, with our highest-performing model achieving a 54.65% pass rate. Error analysis shows that models are not sufficiently robust to human speech when tracking instructions, edits, and audio cues, highlighting the need for improved audio-native multi-turn interaction capabilities.

Understanding tone in Twitter posts will be increasingly important as more and more communication moves online. One of the most difficult, yet important tones to detect is sarcasm. In the past, LSTM and transformer architecture models have been used to tackle this problem. We attempt to expand upon this research, implementing LSTM, GRU, and transformer models, and exploring new methods to classify sarcasm in Twitter posts. Among these, the most successful were transformer models, most notably BERT. While we attempted a few other models described in this paper, our most successful model was an ensemble of transformer models including BERT, RoBERTa, XLNet, RoBERTa-large, and ALBERT. This research was performed in conjunction with the sarcasm detection shared task section in the Second Workshop on Figurative Language Processing, co-located with ACL 2020.