The study investigates which speech aspects best signal the end of a speaker’s turn in conversational AI. By systematically ablating acoustic, prosodic, and semantic cues in a lightweight trimodal classifier, the authors find that combining acoustic and prosodic features yields the highest accuracy and lowest latency, achieving an utterance F1 of 0.93 with 7.8% false alarms at 400 ms median latency. Adding textual information actually increases premature detections without improving performance, and feature analysis shows prosodic cues provide the strongest class separability while text representations overlap significantly.
By Rini Sharon, Manickavela A, Kadri Hacioglu, Andreas Stolcke
TurnBench is a new multi‑domain benchmark for evaluating turn‑taking dynamics in spoken dialogue. It comprises a 30‑hour hand‑labeled corpus of dyadic human conversations, a standardized evaluation protocol for end‑of‑turn and interruption detection, and covers six distinct interaction styles with triple annotation. The benchmark also provides a 104‑hour training set, a public leaderboard, and an interactive dataset viewer at https://turnbench.sesame.com.
By Freeman Jiang, Ramon Sanabria, Soham Deshmukh, Bandhav Veluri, Simon Michael Vuch Williams, Elliott K. Suen, Garreth Lee, Kevin Yoonho Choi, Takuya Umeki, Riku Kubo, Sathvik Udupa, Chien-yu Huang, Shih-Yun Shan Kuan, Zhuoyan Tao, Satyapriya Krishna, Sefik Emre Eskimez, Yu Tsao, Hung-yi Lee, Shinji Watanabe
arXiv:2607. 12468v1 Announce Type: cross Abstract: We describe our submission to Task 1 of the 2nd MLCSLM Challenge: a cascaded diarization-then-recognition system that combines DiariZen-Large-s80 (WavLM-Large) segmentation, CAM++ embedding-based two-speaker clustering, and a LoRA-adapted omniASR LLM 7B v2 recognizer, with no oracle segmentation or speaker labels at test time.
By Shuming Fang, Shuifei Zeng
The paper introduces a synthetic Bengali speech dataset tailored for telecom customer‑care applications, comprising 10,000 audio‑text pairs (≈26.82 hours) with predefined train, validation, and test splits. The data were generated using OmniVoice voice‑cloning, and include both original and normalized transcripts for ASR/STT use. Automatic intelligibility evaluation with a fine‑tuned Whisper model shows an average WER of 2.54% and CER of 0.59%, indicating strong text‑audio consistency, while the authors note limitations of synthetic speech and STT‑based evaluation.
By Kawshik Kumar Paul, Md. Nafiul Alam Fuji
arXiv:2609.35791v1 Announce Type: new
Abstract: Natural turn-taking in full-duplex voice interaction requires determining from partial speech whether a pause reflects hesitation or a completed conver...
By Puneet Mathur, Dinesh Manocha
arXiv:2606. 03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data.
By M\'at\'e Gedeon, P\'eter Mihajlik
arXiv:2606. 27543v1 Announce Type: cross Abstract: The variations in vocal effort range (e.
By Zahra Omidi, John H. L. Hansen
The paper introduces asymmetric classifier‑free guidance (CFG) for target‑speaker ASR using Whisper, where a speaker‑conditioned branch predicts the target transcript and a speaker‑unconditioned branch predicts serialized multi‑speaker transcripts. CFG modulates the influence of speaker conditioning during decoding via a single guidance scale, which is first set globally on development data and then refined per utterance by a lightweight encoder‑based predictor while keeping the recognition model fixed. The resulting system yields up to 21.8% relative WER reduction over a condition‑only baseline and 5.6% over standard conditional decoding under domain shifts.
By Yiwen Guan, Jacob Whitehill
The paper introduces a new target‑speaker unlearning task for automatic speech recognition (TSU‑ASR) that allows certain speakers to opt out of transcription while still indicating their presence. A lightweight Enrollment‑Conditioned Gating (ECG) module is added to a frozen dual‑stream speech LLM, enabling dynamic unlearning of new opt‑out speakers during inference. Experiments on AMI and AliMeeting datasets show significant drops in transcription accuracy for opt‑out speakers while preserving performance for retained speakers.
By Bo Su, Yueru Yan, Thai Le
arXiv:2607. 08111v1 Announce Type: cross Abstract: Training target speaker extraction (TSE) models for real conversational mixtures remains challenging because large-scale training corpora and clean target speech for supervision are unavailable.
By Wanyi Ning, Wei Zhou, Yingpeng Li, Yinshang Guo, Haitao Qian, Yiming Cheng
arXiv:2603. 04710v2 Announce Type: replace-cross Abstract: Recent advances in automatic speech recognition (ASR) and speech enhancement have strengthened the common belief that cleaner audio should lead to more accurate transcription.
By Akif Islam, Raufun Nahar, Md. Ekramul Hamid
The paper introduces CAFNet, a lightweight cross‑attentive neural network that fuses MFCC, LFCC, and Chroma‑STFT features to detect and localise partially manipulated (half‑truth) speech. CAFNet achieves high ternary accuracy (97.55%) and low boundary mean absolute error (0.037 s) on the MLADDC benchmark, while demonstrating that cross‑corpus transfer depends on both capability and corpus characteristics. Ablation studies show that cross‑attention fusion is the most critical component, and removing a deeply supervised auxiliary head improves in‑domain performance and reduces variance.
By S. Sutharya, Remya K. Sasi