PRISM‑Bench is an audio‑centric diagnostic benchmark for text‑to‑audio‑video generation, built from 900 human‑verified samples. It evaluates audio along two axes—audio type (speech, music, sound) and sound‑source visibility (on‑screen vs. off‑screen)—across four perceptual dimensions (audio‑visual coherence, audio quality, audio expressiveness, and prompt following) using 35 fine‑grained criteria. The benchmark employs an enhanced MLLM‑as‑a‑Judge protocol that aligns strongly with human raters, revealing a performance gap between frontier and open‑source T2AV models and highlighting overfitting to perceptual fidelity while struggling with complex grounding and control tasks, especially for music and synchronized on‑screen audio.
By Yuchen Sun, Qian Yang, Jun Wang, Detai Xin, Guoqiao Yu, Guanglu Wan, Qi Jia
arXiv:2608.21176v1 Announce Type: cross
Abstract: Automatic speech quality assessment aims to predict Mean Opinion Scores (MOS) consistent with human subjective perception and is essential for evalua...
By Naiyuan Li, Li Dong, Diqun Yan
arXiv:2606. 15888v1 Announce Type: cross Abstract: Non-verbal vocalizations (NVs), such as laughter, sighs, and coughs, are important acoustic cues for emotion and intent.
By Jialong Mai, Jinxin Ji, Xiaofen Xing, Wencui Liu, Xiangmin Xu
GrainSpeech is a compact speech synthesis model that uses a fixed‑receptive‑field convolutional encoder to reduce pitch, energy, and duration prediction errors by 36.0%, 17.3%, and 3.4% respectively. It introduces a Mel‑specific gradient‑variance supervision that improves fine‑scale variation while avoiding quality degradation. With only 264.8K parameters, GrainSpeech achieves 17.9× real‑time Mel generation on a microcontroller and attains UTMOS scores comparable to much larger models, using less than 1.5% of their parameters.
By Zitao Liang, Chang Gao
arXiv:2606. 06907v1 Announce Type: cross Abstract: Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data.
By Seonuk Kim, Yonghyeon Jun, Ju Yeon Kang, Jimin Hong, Yoonhyeong Lee, Nam Soo Kim
arXiv:2606. 10233v1 Announce Type: cross Abstract: While speech quality is typically assessed on complete utterances, streaming and generative systems require incremental estimation from partial audio.
By Zhuoyan Tao, Jiatong Shi, Hye-jin Shim, Shinji Watanabe
arXiv:2608. 09288v1 Announce Type: cross Abstract: Audio-visual speech enhancement under real-world conditions remains challenging due to unreliable visual inputs and the lack of large-scale training data with realistic acoustic conditions.
By Wei Zhou, Wanyi Ning, Yinshang Guo, Qianxiao Fang, Haitao Qian, Yingpeng Li
arXiv:2606. 11922v1 Announce Type: cross Abstract: Recent respiratory sound classification (RSC) studies largely rely on CLS-token driven self-attention architectures such as the Audio Spectrogram Transformer (AST).
By Hemansh Shridhar, Miika Toikkanen, June-Woo Kim
The paper investigates whether audio‑language models capture paralinguistic cues beyond spoken content. Using the Expresso dataset and four open‑source models, the authors trace how speaking style information is encoded in the late layers of the audio encoder but is degraded before reaching the final output. They find that some models are content‑driven while others are acoustic‑driven, revealing a gap between what is encoded and what is utilized in current audio‑language models.
By Bhuvan Koduru, Dareen Safar B Alharthi, Rita Singh, Bhiksha Raj
arXiv:2609.10366v1 Announce Type: cross
Abstract: While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true...
By Rishabh Jain, Naomi Harte
arXiv:2610.10208v1 Announce Type: cross
Abstract: Automatic audio scene description turns a recording into a text account of a situation. One difficulty is deciding which elements of the audio should...
By Marcel Gibier, Thomas Thebaud, Olivier Bo\"effard, Jean-Fran\c{c}ois Bonastre
arXiv:2606. 14647v1 Announce Type: cross Abstract: Transformer-based automatic speech recognition (ASR) models such as Whisper are highly accurate, but their predictions remain difficult to interpret.
By Ravi Ranjan, Utkarsh Grover, Xiaomin Lin, Agoritsa Polyzou