collaborators

5 papers

cs.SD2025

CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching

Leying Zhang, Yao Qian, Xiaofei Wang +8

Generating natural-sounding, multi-speaker dialogue is crucial for applications such as podcast creation, virtual agents, and multimedia content generation. However, existing syste…

eess.AS2025

SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning

Prabhat Pandey, Rupak Vignesh Swaminathan, K V Vijay Girish +4

We introduce SIFT (Speech Instruction Fine-Tuning), a 50M-example dataset designed for instruction fine-tuning and pre-training of speech-text large language models (LLMs). SIFT-50…

eess.AS2025

Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis

Yifan Yang, Shujie Liu, Jinyu Li +10

Recent zero-shot text-to-speech (TTS) systems face a common dilemma: autoregressive (AR) models suffer from slow generation and lack duration controllability, while non-autoregress…

cs.CL2025

Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Microsoft, :, Abdelrahman Abouelenin +73

We introduce Phi-4-Mini and Phi-4-Multimodal, compact yet highly capable language and multimodal models. Phi-4-Mini is a 3.8-billion-parameter language model trained on high-qualit…

eess.AS2024

TS3-Codec: Transformer-Based Simple Streaming Single Codec

Haibin Wu, Naoyuki Kanda, Sefik Emre Eskimez +1

Neural audio codecs (NACs) have garnered significant attention as key technologies for audio compression as well as audio representation for speech language models. While mainstrea…