{"total":16,"rows":[{"id":"2604.25441","title":"Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2606.29031","title":"How to Leverage Synthetic Speech for LLM-Based ASR Systems?","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2609.08936","title":"AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2607.02763","title":"LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.16870","title":"Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.17812","title":"ESCUCHA: A Spanish Speech Benchmark for Heterogeneous Acoustic Conditions","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.25667","title":"MyMentorLLM: A psychotherapy GenAI environment with multimodal voice/text patients, trainees and experts for deliberate practice","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.01865","title":"Analyzing Speech Condition Effects in Dysarthric ASR: A Layer-wise Probing Study","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.11650","title":"Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.12814","title":"FastThaiG2P: Lightning-fast Thai Grapheme-to-phoneme Conversion for Voice Agent Pipelines","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.20346","title":"Building and Evaluating a Synthetic Bengali Speech Resource for Telecom Customer Care","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2609.11545","title":"Complex-Text Robustness Evaluation and Failure Diagnosis for Low-Resource Multilingual Text-to-Speech","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.19805","title":"Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.28974","title":"Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.29123","title":"Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.06057","title":"A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment Models","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}