TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers
Paper • 2406.15752 • Published
Xiaofei Wang
xiaofei-wang
AI & ML interests
far-field/robust conversational speech recognition, speech separation and enhancement, audio generation
Recent Activity
authored a paper about 6 hours ago
TacoLM: GaTed Attention Equipped Codec Language Model are Efficient
Zero-Shot Text to Speech Synthesizers authored a paper about 6 hours ago
Phi-Omni-ST: A multimodal language model for direct speech-to-speech
translation authored a paper about 6 hours ago
CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully
Non-Autoregressive Flow MatchingOrganizations
None yet
authored 8
papers about 6 hours ago
Phi-Omni-ST: A multimodal language model for direct speech-to-speech translation
Paper • 2506.04392 • Published
CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching
Paper • 2506.00885 • Published • 1
EdiVal-Agent: An Object-Centric Framework for Automated, Scalable, Fine-Grained Evaluation of Multi-Turn Editing
Paper • 2509.13399 • Published • 5
SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models
Paper • 2510.06917 • Published • 35
Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
Paper • 2505.19931 • Published
FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates
Paper • 2510.00981 • Published • 1
ProImage-Bench: Rubric-Based Evaluation for Professional Image Generation
Paper • 2512.12220 • Published
authored a
paper 9 months ago
authored a
paper almost 2 years ago
authored 3
papers about 2 years ago
NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription
Paper • 2401.08887 • Published
ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering
Paper • 2401.07333 • Published
Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like
Paper • 2402.07383 • Published • 15
authored a
paper over 2 years ago