arXiv:2606. 29335v1 Announce Type: cross Abstract: Multimodal speaker identification systems face two key challenges in real-world deployment: missing modalities and language mismatch between training and testing conditions.
arXiv:2501.18157v2 Announce Type: replace-cross Abstract: Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions fr...
arXiv:2609.38887v1 Announce Type: cross Abstract: Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automatic speaker verification (ASV) models. While effect...
The paper introduces task-informed parameter-efficient fine-tuning methods for low-resource speech recognition by applying Fisher-Whitened Cross-Covariance Analysis (FCCA) to Whisper and Qwen3-ASR. Two extensions—Asymmetric-Coupled FCCA (AC‑FCCA) and Adaptive‑Rank FCCA (AR‑FCCA)—are proposed to exploit cross‑layer sharing and adapt rank allocation within a fixed parameter budget. Experiments on multilingual datasets show that standard FCCA matches or surpasses LoRA, while AR‑FCCA consistently improves performance across models without increasing trainable parameters.
arXiv:2512. 10120v2 Announce Type: replace-cross Abstract: General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting.
arXiv:2607. 21496v1 Announce Type: cross Abstract: Cognitive impairment (CI) is a growing public health concern.
arXiv:2606. 03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data.
arXiv:2606. 05931v1 Announce Type: cross Abstract: When retrieving a person from a video archive by voice and face, should the system be multimodal or not?
arXiv:2609.10394v1 Announce Type: cross Abstract: Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the...
Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data. We propose an augmentation pipeline that generates scenario-level dialogues with participant metadata, maps speaker attributes to TTS voice profiles, and assembles synthesized utterances into speaker-aware simulated conversations.
arXiv:2609.26648v1 Announce Type: cross Abstract: Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under chal...
arXiv:2608. 04586v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).
Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time.