{"total":30,"items":[{"citing_arxiv_id":"2606.31128","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling","primary_cat":"cs.SD","submitted_at":"2026-06-30T04:46:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniSAE unifies speaker, emotion, and multi-granularity content editing in speech via a new discrete phonetic posteriorgram representation and diffusion-based rendering.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29031","ref_index":37,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"How to Leverage Synthetic Speech for LLM-Based ASR Systems?","primary_cat":"cs.CL","submitted_at":"2026-06-27T17:57:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Layer selection plus RIR augmentation on synthetic speech matches full real-data ASR performance using 25% real speech in SLAM-ASR.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23190","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech","primary_cat":"eess.AS","submitted_at":"2026-06-22T11:37:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FlowTTS-GRPO applies online RL with weighted multi-objective rewards to flow-matching TTS models via ODE-to-SDE conversion, reporting gains in speaker similarity and perceptual quality on CosyVoice 3.0 and F5-TTS.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21343","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"An Evaluation Framework for Text-to-Speech Voice Reconstruction","primary_cat":"eess.AS","submitted_at":"2026-06-19T11:41:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The paper introduces a subjective-objective evaluation framework using Best Worst Scaling and a novel dual-reference distributional measure to better assess intelligibility versus speaker identity trade-offs in TTS voice reconstruction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.16417","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Joycent: Diffusion-based Accent TTS without Accented Phone Prediction","primary_cat":"cs.SD","submitted_at":"2026-06-15T08:55:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Joycent uses diffusion modeling and conditional layer normalization to synthesize accented speech from standard phones and references, claiming better accentedness and speaker preservation than two-stage baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11611","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations","primary_cat":"cs.SD","submitted_at":"2026-06-10T03:23:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"SARA is a dual-stream VAE that integrates semantic and acoustic streams to achieve high-fidelity reconstruction and natural zero-shot TTS without complex regularizers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20650","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis","primary_cat":"cs.CL","submitted_at":"2026-06-08T06:54:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EmoInstruct-TTS uses Emotion2embed and an Instruction-Conditioned Emotion Flow Model (ICE-Flow) to generate acoustically grounded emotion representations from free-form instructions and integrate them into an LLM-based TTS pipeline.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09019","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech","primary_cat":"cs.SD","submitted_at":"2026-06-08T04:32:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TLDR groups codec tokens into patches for patch-level autoregressive modeling in pretrained TTS systems, yielding 1.8x speedup and 75% KV-cache reduction at patch size 4.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06940","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models","primary_cat":"eess.AS","submitted_at":"2026-06-05T06:11:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"CogAudio-LLM introduces LIME-440K dataset, EIPS chain-of-thought reasoning, and DR-SAPO optimization to address semantic dominance and improve affective responses in audio language models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05896","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Resonant Minds: Closed-Loop Social Avatars with Theory of Mind","primary_cat":"cs.CV","submitted_at":"2026-06-04T09:03:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A dual-agent closed-loop system integrates Theory of Mind reasoning with multimodal video generation to create social avatars that outperform full-information baselines on dialogue quality under information asymmetry.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01677","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","primary_cat":"cs.SD","submitted_at":"2026-06-01T04:35:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniVocal presents a text-context-only framework for speech-singing code-switching synthesis via two-stage curriculum learning and a synthetic data pipeline, claiming SOTA on a new benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01016","ref_index":107,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","primary_cat":"cs.CL","submitted_at":"2026-05-31T05:13:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PolySpeech-100 is a new benchmark for native-level speech comprehension across 110 linguistic variants that evaluates 22 models and reports E2E advantages on dialects, robustness gaps on low-resource languages, and degradation from Chain-of-Thought prompting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30993","ref_index":63,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue","primary_cat":"eess.AS","submitted_at":"2026-05-29T08:27:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SwanVoice is a zero-shot TTS system for 1-4 speakers that reports higher richness and hierarchy scores than open-source baselines on monologue and dialogue tasks via mixed training and DiffusionNFT post-training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22083","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching","primary_cat":"cs.SD","submitted_at":"2026-05-21T07:22:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RobustSpeechFlow improves TTS alignment robustness by extending contrastive flow matching with length-preserving repeat and skip latent augmentations, lowering WER from 1.44 to 1.38 on Seed-TTS-eval and CER on ZERO500.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00066","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech","primary_cat":"cs.SD","submitted_at":"2026-05-20T07:46:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"DUET enables fine-grained emotion control in pretrained diffusion and flow-matching TTS models via unified hidden-space steering and mel-space guidance, outperforming supervised baselines on multiple backbones.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16026","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation","primary_cat":"cs.CL","submitted_at":"2026-05-15T15:01:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"S2ST-Omni 2 uses typology-informed hierarchical encoding, gated Dual-CTC, and typology-aware prompting to improve multilingual S2ST over flat-label baselines on CVSS-C, with gains in low-data regimes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17583","ref_index":74,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech","primary_cat":"cs.CV","submitted_at":"2026-05-14T13:31:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AgentSteerTTS proposes a multi-agent framework with adversarial disentanglement, dual-stream anchoring via acoustic prototypes, and fast-slow feedback to achieve intent-faithful expressive TTS for composite instructions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11866","ref_index":14,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AuDirector: A Self-Reflective Closed-Loop Framework for Immersive Audio Storytelling","primary_cat":"cs.SD","submitted_at":"2026-05-12T09:46:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AuDirector proposes a self-reflective closed-loop multi-agent framework with identity-aware pre-production, collaborative synthesis-correction, and human-guided refinement for coherent immersive audio storytelling.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"demonstrated that large language models (LLMs) can act as con- trollers to decompose and solve complex cross-modal tasks by generating executable programs or invoking domain expert mod- els. Inspired by this, works like AudioGPT [ 13] that integrate multi-task understanding have also emerged in the audio domain. In audio storytelling, pioneering works such as WavJourney [14] and PodAgent [15] leverage the reasoning capabilities of LLMs to generate executable scripts, constructing auditory narratives by integrating various audio foundational models. Although agent-driven audio storytelling has advanced sig- nificantly, current frameworks still face several limitations: First, constrained adaptive speech representation."},{"citing_arxiv_id":"2605.06765","ref_index":110,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","primary_cat":"cs.CL","submitted_at":"2026-05-07T17:59:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"VITA-QinYu is the first expressive end-to-end spoken language model supporting role-playing and singing alongside conversation, trained on 15.8K hours of data and outperforming prior models on expressiveness and conversational benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.26347","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation","primary_cat":"eess.AS","submitted_at":"2026-04-29T06:59:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Emotion embedding similarities are unsuitable for zero-shot evaluation of emotional expressiveness in speech generation due to confounding by non-emotional acoustic features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23742","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RTCFake: Speech Deepfake Detection in Real-Time Communication","primary_cat":"cs.SD","submitted_at":"2026-04-26T14:42:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RTCFake is the first large-scale dataset of real-time communication speech deepfakes paired with offline versions, paired with a phoneme-guided consistency learning method that improves cross-platform and noise-robust detection.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22225","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis","primary_cat":"cs.CL","submitted_at":"2026-04-24T05:01:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TTS-PRISM defines a 12-dimensional perceptual schema, builds a targeted diagnostic dataset via adversarial synthesis and expert labels, and tunes an end-to-end model that outperforms generalist LLMs in human alignment on a 1,600-sample Mandarin test set while profiling six TTS paradigms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17435","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation","primary_cat":"cs.CL","submitted_at":"2026-04-19T13:34:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MoVE uses specialized LoRA expert adapters and a soft router to translate non-verbal vocalizations in S2ST, reproducing them in 76% of cases versus at most 14% for baselines while scoring highest on naturalness and emotional fidelity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12292","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing","primary_cat":"cs.SD","submitted_at":"2026-04-14T05:03:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CoSyncDiT is a cognitive-inspired diffusion transformer that achieves state-of-the-art lip synchronization and naturalness in movie dubbing by guiding noise-to-speech generation through acoustic, visual, and contextual stages plus joint regularization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08363","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation","primary_cat":"cs.SD","submitted_at":"2026-04-09T15:27:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CapTalk unifies single-utterance and dialogue voice design via utterance- and speaker-level captions plus a hierarchical variational module for stable timbre with adaptive expression.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.01897","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection","primary_cat":"cs.SD","submitted_at":"2026-04-02T11:00:37+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":1,"top_context_role":"dataset","top_context_polarity":"use_dataset","context_text":"Since thewaitstate is rare in natural conversations, we sup- plement the set with 1,000 samples generated using DeepSeek V3 [21] for text and IndexTTS2 [22] for audio synthesis. 3. Experiments 3.1. Datasets ASR Task. We use large-scale open-source corpora and in- ternal datasets, including AISHELL-1 [23], AISHELL-2 [24], WenetSpeech [25], LibriSpeech [26], GigaSpeech [27], and MLS [28], totaling over 30,000 hours of Chinese and English speech to support robust feature learning. Turn Detection Task.We use the Easy Turn training set, augmented with internal conversational data and synthetic cor- pora. Dialogue texts are generated by Qwen3-32B [20] and DeepSeek-v3 [21], then synthesized into speech using In-"},{"citing_arxiv_id":"2605.15202","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DeepSlide: From Artifacts to Presentation Delivery","primary_cat":"cs.AI","submitted_at":"2026-04-01T13:38:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DeepSlide introduces a multi-agent system for full presentation preparation that matches baselines on slide quality but improves narrative flow, pacing, and script synergy via a new dual-scoreboard benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.00688","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models","primary_cat":"cs.CL","submitted_at":"2026-04-01T09:45:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"OmniVoice introduces a diffusion language model-style non-autoregressive TTS system that directly maps text to multi-codebook acoustic tokens, scaling zero-shot synthesis to over 600 languages with SOTA results on multilingual benchmarks using 581k hours of open data.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"OmniV oice-Emilia surpasses all NAR baselines (F5-TTS [14], ZipV oice [16], MaskGCT [19]) trained on the same Emilia corpus, verifying the effectiveness of our proposed architecture. The final multilingual version OmniV oice model yields competitive overall performance across all benchmarks against baselines trained on unconstrained datasets (IndexTTS2 [5], CosyV oice3 [33], V oxCPM [10], Qwen3-TTS [42]), with particular advantages in speaker similarity and intelligibility. This demonstrates OmniV oice's strong capability on the two most high-resource languages. 4.2 Evaluation on Multilingual Benchmarks We validate OmniV oice's multilingual capability on the 24-language MiniMax-Multilingual-24 benchmark and the 102-language FLEURS-Multilingual-102 benchmark."},{"citing_arxiv_id":"2601.22143","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion","primary_cat":"cs.GR","submitted_at":"2026-01-29T18:57:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"JUST-DUB-IT adapts a joint audio-visual diffusion model via LoRA to generate high-quality dubbed videos with translated audio and lip-synced facial motion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.03170","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis","primary_cat":"cs.SD","submitted_at":"2026-01-06T16:51:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A training-free framework for intra-utterance emotion and duration control in pretrained zero-shot TTS via segment-aware conditioning and steering strategies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}