The report details the winning approach for the AES AIMLA 2025 Challenge on querying sound effects by vocal imitation. It explores two fine‑tuning strategies: contrastive learning with a frozen, pretrained CED encoder, and joint contrastive‑triplet learning using a MobileNetV3 encoder with semi‑hard negatives. Updated post‑challenge, the document includes additional released details.
arXiv:2605. 03297v2 Announce Type: replace-cross Abstract: ASR systems based on self-supervised acoustic pretraining and CTC fine-tuning achieve strong performance on native speech but remain sensitive to accent variability.
arXiv:2606. 27543v1 Announce Type: cross Abstract: The variations in vocal effort range (e.
arXiv:2609.14231v1 Announce Type: cross Abstract: Controllable synthesis of nonverbal vocalizations (NVVs) is es- sential for natural and expressive speech, but remains challeng- ing due to their aco...
arXiv:2604.18360v4 Announce Type: replace-cross Abstract: Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; how...
arXiv:2606. 14922v1 Announce Type: cross Abstract: For the last couple of years, the field of speech synthesis has improved dramatically thanks to deep learning.
arXiv:2606. 30700v1 Announce Type: cross Abstract: Self-supervised learning enables audio representations that transfer across domains and tasks.
arXiv:2606. 15751v1 Announce Type: cross Abstract: Audio-Language Models (ALMs) have shown remarkable success in zero-shot audio classification by aligning audio waveforms with text.
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...
arXiv:2510. 20441v2 Announce Type: replace-cross Abstract: Neural audio codecs have largely promoted the application of language models (LMs) for speech applications.
HuPER is a human-inspired framework that models phonetic perception as adaptive inference over acoustic‑phonetics evidence and linguistic knowledge. Using only 100 hours of training data, it achieves state‑of‑the‑art phonetic error rates on five English benchmarks and demonstrates strong zero‑shot transfer to 95 unseen languages. It uniquely enables adaptive, multi‑path phonetic perception across diverse acoustic conditions, and all training data, models, and code are open‑sourced.
arXiv:2606. 26534v1 Announce Type: cross Abstract: Recently, zero-shot text-to-speech (TTS) has enabled high-fidelity and expressive speech synthesis, but it often fails to imitate unseen speaking styles from uncommon scenarios (e.
arXiv:2509.10452v3 Announce Type: replace-cross Abstract: Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance....