{"slug": "costa-compressed-speech-token-adaptation-for-efficient-spoken-dialogue-models", "title": "CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models", "summary": "Researchers introduced CoSTA, a compatibility-preserving post-hoc framework that decouples generation and synthesis token spaces in Spoken Dialogue Models while retaining the original speech tokenizer and decoder, according to an arXiv paper (arXiv:2610.21143v1). CoSTA extends the generation token space with compressed representations via mean-initialized vocabulary extension, pronunciation adaptation, and dialogue adaptation, then deterministically expands back to the original speech-token space before synthesis. On bilingual speech-dialogue benchmarks, CoSTA achieved approximately 1.7x expanded speech-token generation speed, lower full-response latency, and higher throughput while preserving response quality, with further experiments showing cross-architecture transfer and complementarity to low-rate tokenization.", "body_md": "arXiv:2610.21143v1 Announce Type: new \nAbstract: Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech tokenizers shorten sequences but may introduce compression-quality trade-offs and costly replacement without breaking this coupling. To address this limitation, we propose CoSTA, a compatibility-preserving post-hoc framework that decouples generation and synthesis token spaces while retaining the original speech tokenizer and decoder. CoSTA extends the generation token space with compressed representations via mean-initialized vocabulary extension, pronunciation adaptation, and dialogue adaptation, followed by deterministic expansion back to the original speech-token space before synthesis. On bilingual speech-dialogue benchmarks, CoSTA achieves approximately $1.7\\times$ expanded speech-token generation speed, lower full-response latency, and higher throughput while preserving response quality. Analyses show more sustained interaction under limited budgets and a practical trade-off among compression, decoding efficiency, and quality. Further experiments demonstrate cross-architecture transfer and complementarity to low-rate tokenization.", "url": "https://wpnews.pro/news/costa-compressed-speech-token-adaptation-for-efficient-spoken-dialogue-models", "canonical_source": "https://www.machinebrief.com/news/costa-compressed-speech-token-adaptation-for-efficient-spoke-x08q", "published_at": "2026-10-16 04:00:00+00:00", "updated_at": "2026-10-16 05:08:46.336988+00:00", "lang": "en", "topics": ["artificial-intelligence", "natural-language-processing", "machine-learning", "ai-research"], "entities": ["CoSTA", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/costa-compressed-speech-token-adaptation-for-efficient-spoken-dialogue-models", "markdown": "https://wpnews.pro/news/costa-compressed-speech-token-adaptation-for-efficient-spoken-dialogue-models.md", "text": "https://wpnews.pro/news/costa-compressed-speech-token-adaptation-for-efficient-spoken-dialogue-models.txt", "jsonld": "https://wpnews.pro/news/costa-compressed-speech-token-adaptation-for-efficient-spoken-dialogue-models.jsonld"}}