Skip to content
conftrace_

Songxiang Liu

10 papers · 2018–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+3 more ↓ πŸŒ‰ Interdisciplinary Bridge Β· Silver 🌍 Conference Polyglot Β· Bronze πŸƒ Academic Marathon Β· Sprint πŸ—ΊοΈ Taxonomy Completionist (18) πŸ† Keyword Champion (3)
🧬 Topic Evolution πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze

Venues

Interspeech (8) ICML (2)

Top co-authors

Helen Meng (6) Xixin Wu (6) Xunying Liu (5) Yuewen Cao (3) Lifa Sun (3) Dongchao Yang (3) Haohan Guo (2) Shiyin Kang (2) Dan Su (2) Xu Tan (2)

Research topics

Speech & Audio (7) Synthesis (6) Machine Learning (5) Deep Learning (4) Artificial Intelligence (3) Natural Language Processing (3) Application Areas (3) Analysis (2) Architectures (2) Core AI (2) Resources & Methods (2) Applications (1) Core Methods (1) Learning Paradigms (1) Learning Types (1)

Keywords

voice conversion (4) expressive speech synthesis (3) speaker identity (2) model robustness (1) tokenization (1) automatic speech recognition (1) prosody prediction (1) speaker embedding (1) sequence-to-sequence model (1) vector quantization (1) speech intelligibility (1) diffusion model (1) long short-term memory (1) diffusion probabilistic model (1) style adaptation (1) universal model (1) semantic prior (1) natural language understanding (1) knowledge distillation (1) domain adaptation (1)

Papers

ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling ICML 2025 UniAudio: Towards Universal Audio Generation with Large Language Models ICML 2024 Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model Interspeech 2023 NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTS Interspeech 2023 ASR-Robust Natural Language Understanding on ASR-GLUE dataset Interspeech 2022 Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion Interspeech 2021 Transferring Source Style in Non-Parallel Voice Conversion Interspeech 2020 Jointly Trained Conversion Model and WaveNet Vocoder for Non-Parallel Voice Conversion Using Mel-Spectrograms and Phonetic Posteriorgrams Interspeech 2019 Rapid Style Adaptation Using Residual Error Embedding for Expressive Speech Synthesis Interspeech 2018 Voice Conversion Across Arbitrary Speakers Based on a Single Target-Speaker Utterance Interspeech 2018