[Paper 리뷰] DisCo-Speech: Controllable Zero-Shot Speech Generation with a Disentangled Speech Codec
DisCo-Speech: Controllable Zero-Shot Speech Generation with a Disentangled Speech Codec기존 codec은 timbre, prosody의 entanglement로 인해 independent control이 어려움DisCo-SpeechParallel encoder와 hybrid loss를 사용하여 speech를 content, prosody, timbre의 tri-factor로 disentangleUnified content-prosody token을 구성해 disentanglement-reconstruction trade-off를 balance논문 (ACL 2026) : Paper Link1. IntroductionCodec-based L..
[Paper 리뷰] Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-Training
Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-TrainingFine-grained speaking style을 modeling 하는 것은 어려움CLSP47k hours speech, 19M fine-grained caption을 포함한 FCaps dataset을 구축FCaps dataset을 기반으로 global, fine-grained supervision을 integrate 한 contrastive language-speech pre-trained modeling을 수행논문 (ACL 2026) : Paper Link1. IntroductionSpeaking style은 gender, age와 같은 speaker-int..
[Paper 리뷰] ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment
ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation AlignmentEnvironmental audio와 함께 speech를 jointly generate 하는 것은 어려움ImmersiveTTSMutimodal diffusion Transformer를 기반으로 transcript-aligned speech latent와 text-conditioned environmental context를 joint attention으로 fuseSemantic consistency를 향상하기 위해 domain-specific representation alig..
[Paper 리뷰] SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization
SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream QuantizationSpeech codec은 semantically-rich representation과 high-quality reconstruction에 대한 trade-off가 존재함SACSemantic-acoustic dual-stream quantization을 활용해 semantic, acoustic modeling을 disentangling두 개의 dedicated stream을 각각의 respective role에 맞게 optimize논문 (ACL 2026) : Paper Link1. IntroductionSpeech tokenizer는 continuous speech wavefor..
[Paper 리뷰] TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis
TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech SynthesisControllable Text-to-Speech는 여전히 fine-grained intra-utterance expression 측면에서 한계가 있음TED-TTSCausal masking과 monotonic stream alignment를 combine 한 segment-aware emotion conditioning를 도입추가적으로 local duration embedding steering과 global EOS logit modulation을 combine 한 segment-aware duration steering strateg..
[Paper 리뷰] Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech
Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-SpeechLarge Language Model-based Text-to-Speech는 fine-grained emotion intensity control의 한계가 있음Emo-LiPOFixed transcript 하에서 각 emotion에 대한 global intensity ordering을 modeling추가적으로 multi-speaker dataset인 ESD-Plus를 구축논문 (IJCAI 2026) : Paper Link1. IntroductionLarge Language Model (LLM)-based T..