Spoken Language Models
PulseAugur coverage of Spoken Language Models — every cluster mentioning Spoken Language Models across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New framework aims to bridge structural gaps in spoken language models
Researchers have identified a significant gap in current Spoken Language Models (SLMs), noting that while they generate text from speech, the underlying speech and text representations remain poorly aligned. This struct…
-
New TELEVAL benchmark evaluates Chinese spoken language models
Researchers have introduced TELEVAL, a new benchmark designed to evaluate Spoken Language Models (SLMs) in Chinese interactive scenarios. Unlike existing benchmarks that focus on semantic correctness in structured setti…
-
Lychee-FD framework enhances full-duplex SLMs by separating acoustic and semantic modalities · 2 sources tracked
Researchers have introduced Lychee-FD, a novel framework designed to improve full-duplex Spoken Language Models (SLMs) by addressing modality interference. The framework employs a hierarchical parameter separation strat…
-
New research explores multimodal and sparse autoencoder methods to combat LLM jailbreaks
Researchers are developing new methods to combat jailbreaking attacks on spoken language models (SLMs). One approach, JAMA, uses a joint multimodal optimization framework to simultaneously attack both audio and text mod…