{"total":14,"rows":[{"id":"2511.00850","title":"MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models","created":"2025-11-02","cited_by_count":9,"area":null},{"id":"2511.03601","title":"Step-Audio-EditX Technical Report","created":"2025-11-05","cited_by_count":7,"area":null},{"id":"2509.14946","title":"SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understanding","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2603.15352","title":"NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation","created":"2026-03-16","cited_by_count":6,"area":null},{"id":"2607.18934","title":"Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2509.02523","title":"Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2604.22225","title":"TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2511.01619","title":"ParlaSpeech 3.0: Richly Annotated Spoken Parliamentary Corpora of Croatian, Czech, Polish, and Serbian","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2601.04508","title":"WESR: Scaling and Evaluating Word-level Event-Speech Recognition","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2606.15888","title":"NVMOS: Non-Verbal Vocalization Quality Assessment in Speech","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2609.23462","title":"Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2603.25727","title":"Back to Basics: Revisiting ASR in the Age of Voice Agents","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2607.06179","title":"TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific Scenarios","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2609.14231","title":"Modeling, Scaling, and Decoding: Optimizing Controllable Speech Generation with Nonverbal Vocalizations","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}