| 1 | Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models | Anuj Diwan, David Harwath, Eunsol Choi | eess.AS | 2026-10-29 |
| 2 | AVPS-360: A Spatial Audio-Visual Benchmark for Instance Segmentation and Tracking of Sound-Producing Persons | Yifu Sun, Parthasaarathy Sudarsanam, Tuomas Virtanen +1 | cs.CV | 2026-10-29 |
| 3 | Blind Video Denoising for Vocal Tract rtMRI using a Self-Supervised Ensemble | Julian Andres Hernandez-Potes, Tomás Arias-Vergara, Daiqi Liu +2 | eess.IV | 2026-10-29 |
| #4 | Mind The Gap (MTG-AD): Dataset and Fine-grained Evaluation for End-to-End Inline Audio Descriptions | Subhashini Venugopalan, Jenny Tan, Taylor Roper +5 | cs.CV | 2026-10-29 |
| #5 | The Importance of Speech Genre for End-of-Turn Detector Training | Rini Sharon, Kadri Hacioglu, Jeena Prakash +1 | eess.AS | 2026-10-29 |
| #6 | SymKL: A Unified Representation-Space Measure of Signal Degradation | Dhananjaya Jayasundara, Sudarshan Rajagopalan, Vishal M. Patel | cs.CV | 2026-10-29 |
| #7 | Reading-Level Verification of Kanji Words in Japanese Financial Speech Synthesis | Cheng Zhang | cs.SD | 2026-10-29 |
| #8 | Streaming Speech Recognition on a Microcontroller: a 65.7M-Parameter Transducer in 2 and 4 Bits on the ESP32-P4 | Billal Boumedine | eess.AS | 2026-10-28 |
| #9 | Do Audio LLMs HEAR Pain? Tracing Acoustic Evidence from Speech to Language Reasoning | Wenqi Li, Xiangjue Dong, Sulaiman Vesal | cs.CL | 2026-10-28 |
| #10 | Pronunciation-Supervised Text-to-Speech for Irish (Gaeilge) | William Lane | cs.CL | 2026-10-28 |
| #11 | A Tutorial on Generative Models for Music Audio | Mateusz Modrzejewski, Joanna Kurkowska, Dorien Herremans | eess.AS | 2026-10-28 |
| #12 | Beyond Aggregate WER: In-domain Adaptation, Learner Speech, Code-Switching, and Speaker Attribution in Online Spanish Learning Classrooms | Olga Kellert, Samhitha Harish, Johnatan E Bonilla +3 | cs.CL | 2026-10-27 |
| #13 | "It Would Make a Geordie Feel at Home": Regional Accent Perceptions and Speech Accommodation in Voice AI | Dana Serditova, Kevin Tang, Jochen Steffens | cs.HC | 2026-10-27 |
| #14 | Self-Supervised Latent Action-Conditioned World Modeling for Time Series | Chia-Han Kuo, Chengshuai Zhao, Huan Liu +1 | cs.LG | 2026-10-27 |
| #15 | Beyond Utterance-Level Speaker Similarity: Perception-Aligned Segmental Evaluation of Accent in Speech Generation | Jinzuomu Zhong, Alice Ross, Catherine Lai +1 | eess.AS | 2026-10-27 |
| #16 | Depth through Recurrence: Towards Ultra-Efficient On-Device ASR | Chen Feng, Tianyi Xu, Ramchalam Kinattinkara Ramakrishnan +5 | cs.LG | 2026-10-27 |
| #17 | Learning Without Clocks: Partition-Invariant Neural Network | Han Wang, Jingyuan Bao, Juntao Wu +2 | cs.LG | 2026-10-27 |
| #18 | Text Generation in Low-Resource Languages Using Human-Curated Vocabularies | Michael Christlambert Sinanta, Muhammad Dehan Al Kautsar, Amanda Nurul Izzah +4 | cs.CL | 2026-10-27 |
| #19 | Developing a Speech Language Model for Basque | Andoni Sudupe, Inma Hernaez, Ander Arriandiaga +3 | cs.CL | 2026-10-27 |
| #20 | Specialization, Diversity, and Scaling in Child-Scale Language Models | Steven Y. Feng, Michael C. Frank | cs.CL | 2026-10-27 |
| #21 | Tap2Listen: Instant Target Switching for Streaming Audio-Visual Speaker Extraction | Hansol Park, Minkyung Song, Zinu Kim +4 | cs.SD | 2026-10-27 |
| #22 | Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization | Zhiheng Qian, Junhao Du, Jing Peng +6 | cs.CL | 2026-10-27 |
| #23 | ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization | Zhiheng Qian, Junhao Du, Jing Peng +4 | cs.CL | 2026-10-27 |
| #24 | Lipi-Ghor: A Large-Scale, Diarized, Multi-Domain Bengali Speech Corpus and a Scalable Pipeline for Building It | Sanjid Hasan, A H M Fuad, Risalat Labib +1 | cs.CL | 2026-10-26 |
| #25 | ConformalMOS: Uncertainty-Aware MOS Prediction with Conformal Intervals and Ordinal Modeling | Kehinde Elelu, Joshua E. Siegel, Mohammadali Saffary +3 | cs.SD | 2026-10-26 |
| #26 | Preserve to Expand: Source-Aware Adaptation and Model Merging for Multilingual LLM-Based ASR | Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar | cs.CL | 2026-10-26 |
| #27 | Not One Belief: Answer Payloads, Persistence, and Dissociated Confidence Signals in Conversational Question Answering | Duc-Vinh Tran | cs.CL | 2026-10-26 |
| #28 | Integrate the Reward, Don't Sample It: Window Likelihood for Interruptions and Backchannels in Full-Duplex Speech Models | Guoqiang Hu, Lichao Zhang, Yizhou Peng +5 | eess.AS | 2026-10-26 |
| #29 | Probing the phon* representations of the Mimi codebooks | Artem Saloev, Nicolas Ballier, Erin Pacquetet | cs.CL | 2026-10-26 |
| #30 | DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models | Hongze Chen, Miao Pan, Lizhou Liang +7 | cs.CL | 2026-10-26 |
| #31 | Realizing Low-Precision Storage and Sparse Execution in a Folded FPGA Speech Enhancer | Clément Laroche | eess.AS | 2026-10-26 |
| #32 | When Fusion Order Matters: Insights on Progressive Multimodal Representation Learning for Cross-modal Retrieval | Haoxiang Zhao, Bin Wang, Yaofei Wang +3 | cs.AI | 2026-10-26 |
| #33 | SimPOTrans: Self-Adaptation for Offline-to-Simultaneous Speech Translation via Reinforcement Learning | Haotian Tan, Hiroki Ouchi, Sakriani Sakti | cs.CL | 2026-10-26 |
| #34 | Diagnosing and Mitigating Long-Session Degradation in Full-Duplex Speech Models | Junho Kim, CheHyun Lee, Donghun Kang +4 | cs.CL | 2026-10-26 |
| #35 | AIPC: Evidence-Guided Agent Workflows for PyTorch Project Deployment | Zhanwei Wu, Jianhao Su, Brian Zhang +11 | cs.SE | 2026-10-26 |
| #36 | DecisionTraceBench: Tracking Decision-Critical Information in Multi-Party Spoken Conversations | Wenchao Du, Fangxin Shang, Long Wu +3 | cs.CL | 2026-10-26 |
| #37 | From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion | Ye Lu, Shen Wang, Runze Liu +5 | cs.SD | 2026-10-26 |
| #38 | Heard Enough to Act: Early Tool Calling in Spoken Dialogue Systems | Yizhou Peng, Chen Chen, Donghang Wu +2 | cs.CL | 2026-10-26 |
| #39 | One Mean Log-Mel Vector per Phoneme: Simple and Fast Text Injection for Speech Recognition | Albert Zeyer, Davyd Naveriani, Dorian Koch +2 | cs.AI | 2026-10-25 |
| #40 | HobbyLM: A Sparse Mixture-of-Experts Model Family on a Hobby Budget | Harish Santhanalakshmi Ganesan, Hariharan M. S., Prabhurajhan R | cs.AI | 2026-10-25 |
| #41 | Toward Neuroadaptive Communication Interfaces: A Framework for Personalized Speech and Language Support | Carlos Bruno, Luis Ricardo Santos | cs.HC | 2026-10-25 |
| #42 | Spatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion | Kam Man Wu, Yu Zhang, Pengjun Fang +4 | cs.SD | 2026-10-25 |
| #43 | In-Context Adapter Generation for Compositional Generalization in Large Audio Language Models | Yiwei Guo, Siqi Huang, Bohan Li +4 | eess.AS | 2026-10-25 |
| #44 | EmoNet: A Lightweight Attention-Based CNN for Speech Emotion Recognition | Muhammad Moiz Khalid, Abdur Rehman Tariq, Muhammad Okasha Yamin | cs.SD | 2026-10-25 |
| #45 | Late Breaking Results: Audio-Language-Action Models with Direct Speech Conditioning for Robotic Manipulation | Enfu Nan, Pu Zhao, Yixiao Chen +5 | cs.CV | 2026-10-24 |
| #46 | RoleHear: Pseudo-Labeling for Semi-Supervised Role-Attributed Streaming Speech Recognition | Zefang Liu, Chenyang Zhu, Sangwoo Cho +4 | cs.CL | 2026-10-24 |
| #47 | CounselPlex: A Stressor-Aware Full-Duplex Counseling Model | Yeonju Kim, Bella Godiva, Yong Man Ro | cs.CL | 2026-10-23 |
| #48 | Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations | Sarah Sulollari, Vanja Karan, Benjamin Roth | cs.CL | 2026-10-23 |
| #49 | Acoustic and Lexical Signals for Native Language Identification of Language Learners | Ahmet Yavuz Uluslu, Mengjie Qian, Kate Knill +1 | cs.CL | 2026-10-23 |
| #50 | Past as State, Present as Attention: Persistent-State Blockwise Flow Matching for Long-Horizon Co-Speech Motion Generation | Yi Liu, Xiangyue Zhang, Jianfang Li +3 | cs.CV | 2026-10-23 |