Papers with Code 아카이브
Audio-Visual Speech Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 4
- 보존된 평가 기록
- 24
Audio-visual speech recognition is the task of transcribing a paired audio and visual stream into text.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions
CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech
Towards a Japanese Full-duplex Spoken Dialogue System
WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing
Zero-Shot Text-to-Speech for Vietnamese
SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction
Cocktail-Party Audio-Visual Speech Recognition
Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models
Chain-of-Thought Training for Open E2E Spoken Dialogue Systems
Speech Token Prediction via Compressed-to-fine Language Modeling for Speech Generation
Werewolf: A Straightforward Game Framework with TTS for Improved User Engagement
LLM-Synth4KWS: Scalable Automatic Generation and Synthesis of Confusable Data for Custom Keyword Spotting
EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge
Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes
Can Emotion Fool Anti-spoofing?
Spotlight-TTS: Spotlighting the Style via Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment
Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling
KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization
DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech
Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis
CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning
SpeakStream: Streaming Text-to-Speech with Interleaved Data
MPE-TTS: Customized Emotion Zero-Shot Text-To-Speech Using Multi-Modal Prompt
RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations
Speechless: Speech Instruction Training Without Speech for Low Resource Languages
UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information
What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition
Benchmarking Expressive Japanese Character Text-to-Speech with VITS and Style-BERT-VITS2
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information
MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling
Voicing Personas: Rewriting Persona Descriptions into Style Prompts for Controllable Text-to-Speech
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.