Audio LLMs
PulseAugur coverage of Audio LLMs — every cluster mentioning Audio LLMs across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Audio-LLMs enhance speech translation data filtering
Researchers have developed a novel method using audio-large language models (Audio-LLMs) to filter noisy speech-to-speech translation (S2ST) training data. This approach employs a two-stage Rank-to-Distill strategy, whe…
-
New Benchmark Reveals Audio LLMs Struggle with Paralinguistic Understanding
Researchers have developed VoxParadox, a new benchmark designed to test the paralinguistic understanding capabilities of audio large language models (Audio LLMs). The benchmark, comprising 2,000 synthesized examples, in…
-
New audio tokenizers enhance AI's understanding and generation of sound
Researchers have developed several new methods for creating more effective audio tokenizers, which are crucial for unifying audio understanding and generation tasks in AI models. UniAudio-Token aims to enhance semantic …
-
DPO improves code-switching speech recognition in audio LLMs
Researchers have developed a new method using Direct Preference Optimization (DPO) to improve how audio large language models handle speech that switches between English and Mandarin. The models often fail by omitting l…
-
New attack bypasses audio LLM defenses via latent space manipulation
Researchers have developed a novel adversarial attack called CodecAttack that bypasses compression defenses in audio large language models (LLMs). Unlike previous methods that directly perturbed audio waveforms, CodecAt…