Hanchen Pei, Shujie Liu, Yayue Deng et al.
Pretrained image-generation models have been successfully repurposed for various downstream visual tasks.Pretrained image-generation models have been successfully repurposed for various downstream visual tasks.
Prince Baah-Mensah, Dennis Owusu Asamoah
Speech Emotion Recognition (SER) is important in human-machine interactions, enabling machines to detect and classify human emotions from solely human speech.Speech Emotion Recognition (SER) is important in human-machine interactions, enabling machines to detect and classify human emotions from solely human speech.
Yoshiyuki Kobayashi
Live pitch displays, score followers and accompaniment systems must know which pitches are sounding within tens of milliseconds, but instrument-agnostic multi-pitch…Live pitch displays, score followers and accompaniment systems must know which pitches are sounding within tens of milliseconds, but instrument-agnostic multi-pitch estimation (MPE) has mainly been designed and evaluated offline.
Wendi Sang, Kai Li, Yifan Li et al.
Streaming audio-visual target speaker extraction (AVTSE) is essential for latency-sensitive applications. However, current causal systems face two coupled gaps.Streaming audio-visual target speaker extraction (AVTSE) is essential for latency-sensitive applications. However, current causal systems face two coupled gaps.
Kirill Borodin, Vasilii Kudryavtsev, Nikita Vasiliev et al.
Text-to-speech (TTS) is usually evaluated by transcribing its output with an automatic speech recognition (ASR) system, so the word error rate also counts recognizer…Text-to-speech (TTS) is usually evaluated by transcribing its output with an automatic speech recognition (ASR) system, so the word error rate also counts recognizer errors.
Yuanzhong Zheng, Wei Huang, Ming Ma et al.
High linear decodability does not entail causal controllability in continuous-latent text-to-speech (TTS).High linear decodability does not entail causal controllability in continuous-latent text-to-speech (TTS). In VoxCPM2, position-matched probes and equal-norm interventions across 30 speakers and 60 directed dyads expose this…
Aditya Srinivas Menon, Kumarmanas Nethil, Kavya Manohar
This paper presents a causal, training-free linker that allows a frozen streaming diarizer to track more speakers than it has output slots.This paper presents a causal, training-free linker that allows a frozen streaming diarizer to track more speakers than it has output slots.
Li Wang, Jindong Wang, Wan Lin et al.
Acoustic capture, device processing, and transmission coding in real calls jointly alter speech signals and may affect the reliability of audio deepfake detection.Acoustic capture, device processing, and transmission coding in real calls jointly alter speech signals and may affect the reliability of audio deepfake detection.
Séverin Baroudi, Yanis Labrak, Petr Motlicek et al.
Qwen3-TTS reports state-of-the-art zero-shot voice cloning, but its technical report leaves open how the model should be conditioned, how it behaves outside read speech…Qwen3-TTS reports state-of-the-art zero-shot voice cloning, but its technical report leaves open how the model should be conditioned, how it behaves outside read speech, and how it fails.
Yi Chen Liu, Syed Irfan Ali Meerza, Jiawei Yu et al.
Advances in generative AI have made it possible to produce music that is nearly indistinguishable from human compositions, raising the question of whether such works can…Advances in generative AI have made it possible to produce music that is nearly indistinguishable from human compositions, raising the question of whether such works can be reliably distinguished from human compositions.
Qituan Shangguan, Bosen Xu, Shuai Wang
Speaker verification (SV) systems now achieve very low error rates on standard public protocols, but those results do not fully describe deployment generalization.Speaker verification (SV) systems now achieve very low error rates on standard public protocols, but those results do not fully describe deployment generalization.
Daniel Varela Sánchez, Guillermo Martín-Coello Juárez
Speech recognition on low-cost microcontrollers is, in practice, limited to keyword spotting or a fixed list of commands.Speech recognition on low-cost microcontrollers is, in practice, limited to keyword spotting or a fixed list of commands. We present O'ido, an inference engine that runs open-vocabulary English speech recognition entirely on an…
Mateusz Modrzejewski, Tomasz Radzikowski
Open audio-language models are used as judges of generated music: given a clip and its text prompt, the model rates the clip, and the judge is validated by how well its…Open audio-language models are used as judges of generated music: given a clip and its text prompt, the model rates the clip, and the judge is validated by how well its ratings correlate with expert ratings.
Zebin Yun, Eyal Ronen, Mahmood Sharif
Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to speaker verification with…Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to speaker verification with minimal resources.
Ksenia Lysikova, Kirill Borodin, Maxim Maslov et al.
Speech anti-spoofing countermeasures degrade when the generator, codec or channel changes, and a common remedy is an auxiliary objective that shapes the embedding space…Speech anti-spoofing countermeasures degrade when the generator, codec or channel changes, and a common remedy is an auxiliary objective that shapes the embedding space; whether it does is invisible to EER, a pure ranking metric.
Tsubasa Ochiai, Marc Delcroix, Nahomi Kusunoki et al.
Non-intrusive MOS predictors are widely used instead of subjective listening tests to evaluate and rank speech enhancement (SE) systems.Non-intrusive MOS predictors are widely used instead of subjective listening tests to evaluate and rank speech enhancement (SE) systems. If they accurately reflect perceived quality, raising their scores should lead to…