Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization

arXiv:2610.01492 · cs.SD, cs.CL, eess.AS · Submitted 2026-10-01 · Read on arXiv

cs.SD, cs.CL, eess.AS

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• Quantization — 9× in this paper · explained in 12 episodes
• Transformer — 8× in this paper · explained in 2 episodes
• Tokenization — 7× in this paper · explained in 2 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Distillation — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Adversarial Training — 1× in this paper · explained in 1 episode
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 7 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes

Sources

• Moshi: a speech-text foundation model for real-time dialogue
• HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec
• FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
• OmniCodec: Low Frame Rate Universal Audio Codec with Semantic-Acoustic Disentanglement

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
• Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment