✨Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering

📝 Summary:
Large audio-language models can under-utilize audio. This work identifies audio-specialist attention heads that provide a listening signal. An inference-time intervention amplifies audio influence, improving LALM accuracy by up to 8% without parameter updates.

🔹 Publication Date: Published on Mar 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.06854
• PDF: https://arxiv.org/pdf/2603.06854

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AudioLanguageModels #DeepLearning #AttentionMechanisms #AIResearch #MachineLearning

✨PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmark

📝 Summary:
PARSA-Bench is the first benchmark for Persian audio-language models, featuring 16 tasks covering speech, paralinguistics, and cultural audio comprehension. It reveals current models struggle with Persian's unique audio challenges like poetry and music, performing poorly on culturally-grounded ta...

🔹 Publication Date: Published on Mar 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14456
• PDF: https://arxiv.org/pdf/2603.14456

✨ Datasets citing this paper:
• https://huggingface.co/datasets/MohammadJRanjbar/PARSA-Bench

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#PersianAI #AudioLanguageModels #NLP #Benchmarking #SpeechProcessing

✨SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding

📝 Summary:
SpotSound improves audio language models for precise temporal grounding in long, noisy audio. It uses a novel training objective to suppress false timestamps, addressing sparse events in challenging backgrounds. SpotSound achieves state-of-the-art performance on temporal grounding benchmarks.

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13023
• PDF: https://arxiv.org/pdf/2604.13023
• Project Page: https://loiesun.github.io/spotsound/
• Github: https://github.com/LoieSun/SpotSound

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AudioLanguageModels #TemporalGrounding #AIResearch #MachineLearning #AudioProcessing

🔥 Continuous Audio Language Models

💡 The paper introduces Continuous Audio Language Models, a new approach to audio generation that addresses the limitations of traditional discrete audio language models. Discrete models represent audio as sequences of discrete tokens, which are extracted from lossy codecs with limited bitrate, resulting in a trade-off between audio quality and computational cost. To overcome this issue, the authors propose Continuous Audio Language Models, which instantiate a large Transformer backbone that produces a contextual embedding at every time step. This sequential information then conditions a multilayer perceptron to generate the next continuous frame of an audio Variational Autoencoder through consistency modeling. By avoiding lossy compression, Continuous Audio Language Models achieve higher quality at lower computational cost than their discrete counterparts. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. The approach enables the generation of high-quality audio samples, which are made available for demonstration purposes. Overall, the paper contributes a novel method for continuous audio language modeling, which has the potential to improve the efficiency and quality of audio generation tasks.

📅 Published on Sep 8, 2025

🔗 Links:
• arXiv: https://arxiv.org/abs/2509.06926
• PDF: https://arxiv.org/pdf/2509.06926
• Project Page: https://huggingface.co/spaces/kyutai/calm-samples
• GitHub: https://github.com/kyutai-labs/pocket-tts ⭐ 4.2k

🤖 Models citing this paper:
• https://huggingface.co/kyutai/pocket-tts
• https://huggingface.co/kyutai/pocket-tts-without-voice-cloning
• https://huggingface.co/Verylicious/pocket-tts-ungated

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/D3vShoaib/pocket-tts
• https://huggingface.co/spaces/kyutai/calm-samples
• https://huggingface.co/spaces/Xlnk/tts

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#AudioLanguageModels #ContinuousAudioGeneration #TransformerBackbone #AudioVariationalAutoencoders #MultilayerPerceptron