FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates like 6.25 Hz.
hub
IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
MINT-Bench is a new benchmark using hierarchical taxonomy, multi-stage data pipeline, and hybrid evaluation to assess instruction-following TTS systems, revealing major gaps in compositional and paralinguistic controls.
EchoFake is a new replay-aware dataset combining zero-shot TTS deepfakes and physical replay recordings to improve generalization of speech deepfake detection models over existing lab-focused datasets.
UniSAE unifies speaker, emotion, and multi-granularity content editing in speech via a new discrete phonetic posteriorgram representation and diffusion-based rendering.
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.
READ is a reference-free ASR hypothesis scorer that measures acoustic discrepancy via conditional likelihood from a pretrained auto-regressive TTS model and yields up to 20% relative error rate reduction when used for refinement.
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.
Agentic ASR adds closed-loop semantic correction to ASR and introduces S²ER, an LLM judge for meaning-level errors, showing larger gains on semantic than token metrics across multilingual benchmarks.
SemaVoice adds SFM-guided alignment to refine continuous speech representations in autoregressive TTS, reporting 1.71% English WER on Seed-TTS and competitiveness with open-source SOTA.
AST performs training-free text-based speech editing by stitching inverted source latents with synthesized targets and adaptively guiding the flow-matching decoder, achieving state-of-the-art temporal fidelity and speaker preservation.
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.
ZipVoice-Dialog is a flow-matching non-autoregressive model for zero-shot spoken dialogue generation that uses curriculum learning and speaker-turn embeddings, paired with a new 6.8k-hour OpenDialog dataset, and reports better speed and quality than autoregressive baselines.
CosyVoice 3 achieves better content consistency, speaker similarity, and prosody naturalness in zero-shot multilingual speech synthesis by scaling data to one million hours, model size to 1.5 billion parameters, and introducing a supervised multi-task speech tokenizer plus a differentiable reward模型.
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.
RoboKA is a KAN-based multimodal fusion model that outperforms baselines on a new synthetic dataset for detecting adversarial robocalls via acoustic and linguistic cues.
ActorMind is a four-agent chain-of-thought framework that emulates human actors to produce spontaneous, emotion-infused speech responses for role-playing scenarios.
The authors introduce LLM-based semantic judgment and an agentic interaction loop that improves semantic fidelity and enables iterative corrections in automatic speech recognition beyond traditional WER.
WAND converts full-attention AR-TTS models to global-plus-sliding-window attention with curriculum fine-tuning and teacher distillation, claiming quality preservation with up to 66.2% KV-cache savings and near-constant latency.
PilotTTS achieves lowest WER 1.50% (en) and CER 0.87% (zh) plus highest speaker similarity on Seed-TTS Eval using a Q-Former conditioned autoregressive architecture and a released multi-stage open data pipeline.
AT-ADD introduces standardized tracks and datasets for evaluating audio deepfake detectors on speech under real-world conditions and on diverse unknown audio types to promote generalization beyond speech-centric methods.
citing papers explorer
-
FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model
FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates like 6.25 Hz.
-
MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech
MINT-Bench is a new benchmark using hierarchical taxonomy, multi-stage data pipeline, and hybrid evaluation to assess instruction-following TTS systems, revealing major gaps in compositional and paralinguistic controls.
-
EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection
EchoFake is a new replay-aware dataset combining zero-shot TTS deepfakes and physical replay recordings to improve generalization of speech deepfake detection models over existing lab-focused datasets.
-
UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling
UniSAE unifies speaker, emotion, and multi-granularity content editing in speech via a new discrete phonetic posteriorgram representation and diffusion-based rendering.
-
Joycent: Diffusion-based Accent TTS without Accented Phone Prediction
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.
-
Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy
READ is a reference-free ASR hypothesis scorer that measures acoustic discrepancy via conditional likelihood from a pretrained auto-regressive TTS model and yields up to 20% relative error rate reduction when used for refinement.
-
UniVocal: Unified Speech-Singing Code-Switching Synthesis
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.
-
Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation
Agentic ASR adds closed-loop semantic correction to ASR and introduces S²ER, an LLM judge for meaning-level errors, showing larger gains on semantic than token metrics across multilingual benchmarks.
-
SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis
SemaVoice adds SFM-guided alignment to refine continuous speech representations in autoregressive TTS, reporting 1.71% English WER on Seed-TTS and competitiveness with open-source SOTA.
-
AST: Adaptive, Seamless, and Training-Free Precise Speech Editing
AST performs training-free text-based speech editing by stitching inverted source latents with synthesized targets and adaptively guiding the flow-matching decoder, achieving state-of-the-art temporal fidelity and speaker preservation.
-
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
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.
-
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
ZipVoice-Dialog is a flow-matching non-autoregressive model for zero-shot spoken dialogue generation that uses curriculum learning and speaker-turn embeddings, paired with a new 6.8k-hour OpenDialog dataset, and reports better speed and quality than autoregressive baselines.
-
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
CosyVoice 3 achieves better content consistency, speaker similarity, and prosody naturalness in zero-shot multilingual speech synthesis by scaling data to one million hours, model size to 1.5 billion parameters, and introducing a supervised multi-task speech tokenizer plus a differentiable reward模型.
-
AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech
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.
-
RoboKA: KAN Informed Multimodal Learning for RoboCall Surveillance System
RoboKA is a KAN-based multimodal fusion model that outperforms baselines on a new synthetic dataset for detecting adversarial robocalls via acoustic and linguistic cues.
-
ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing
ActorMind is a four-agent chain-of-thought framework that emulates human actors to produce spontaneous, emotion-infused speech responses for role-playing scenarios.
-
Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition
The authors introduce LLM-based semantic judgment and an agentic interaction loop that improves semantic fidelity and enables iterative corrections in automatic speech recognition beyond traditional WER.
-
WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models
WAND converts full-attention AR-TTS models to global-plus-sliding-window attention with curriculum fine-tuning and teacher distillation, claiming quality preservation with up to 66.2% KV-cache savings and near-constant latency.
-
PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
PilotTTS achieves lowest WER 1.50% (en) and CER 0.87% (zh) plus highest speaker similarity on Seed-TTS Eval using a Q-Former conditioned autoregressive architecture and a released multi-stage open data pipeline.
-
AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan
AT-ADD introduces standardized tracks and datasets for evaluating audio deepfake detectors on speech under real-world conditions and on diverse unknown audio types to promote generalization beyond speech-centric methods.