The paper presents BiMamba2, a 47.88‑million‑parameter bidirectional Mamba‑2 encoder trained with masked discrete‑unit prediction for multilingual speech representation. It was trained on 250 hours of unlabeled speech from 67 languages and evaluated in the Unsupervised Speech in the Wild Challenge, achieving an Adjusted Rand Index of 0.735 for speaker clustering while reporting lower performance on language identification and character error rate compared to supervised baselines. The authors also discuss a discrepancy between local‑official metric scales and checkpoint rankings, underscoring the limits of in‑distribution diagnostics for predicting Dynabench probe outcomes.
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...
The paper introduces ABX-Accent, a benchmark built on the AESRC dataset that evaluates how well representation learning models adapt to 10 different English accents with less than 10 hours of unlabeled data per accent. It adapts the Zero Resources Challenge ABX metrics for each accent and demonstrates a baseline using adaptive domain normalization to fine‑tune a Contrastive Predictive Coding model, achieving a 23.6% relative improvement on across‑speaker ABX scores compared to non‑adapted models. The dataset and evaluation metrics will be released publicly after the paper is accepted.
arXiv:2607. 12468v1 Announce Type: cross Abstract: We describe our submission to Task 1 of the 2nd MLCSLM Challenge: a cascaded diarization-then-recognition system that combines DiariZen-Large-s80 (WavLM-Large) segmentation, CAM++ embedding-based two-speaker clustering, and a LoRA-adapted omniASR LLM 7B v2 recognizer, with no oracle segmentation or speaker labels at test time.
The paper introduces ABX-Accent, a benchmark for evaluating how well unsupervised speech representation learning models adapt to new accents. It uses the AESRC dataset with 10 English accents, each providing less than 10 hours of unlabeled data, and adapts the Zero Resources Challenge ABX metrics to these accents. A baseline model employing adaptive domain normalization to fine‑tune a Contrastive Predictive Coding model shows a 23.6% relative improvement on across‑speaker ABX scores compared to non‑adapted models.
DiscoPhon is a multilingual benchmark designed to evaluate unsupervised phoneme discovery from discrete speech units. It includes 6 development and 6 test languages that cover a wide range of phonemic contrasts, and requires systems to generate discrete units mapped to a predefined phoneme inventory using only 10 hours of speech from an unseen language. The benchmark assesses unit quality, recognition, and segmentation, and provides four pretrained multilingual HuBERT and SpidR baselines that demonstrate current models can produce units that correlate well with phonemes, though performance varies across languages.
The paper introduces asymmetric classifier‑free guidance (CFG) for target‑speaker ASR using Whisper, where a speaker‑conditioned branch predicts the target transcript and a speaker‑unconditioned branch predicts serialized multi‑speaker transcripts. CFG modulates the influence of speaker conditioning during decoding via a single guidance scale, which is first set globally on development data and then refined per utterance by a lightweight encoder‑based predictor while keeping the recognition model fixed. The resulting system yields up to 21.8% relative WER reduction over a condition‑only baseline and 5.6% over standard conditional decoding under domain shifts.
VietPrism is a newly released, large‑scale Vietnamese speech corpus that combines 993.4 hours of real utterances from 1,262 verified speakers with 3.1 k hours of synthetic spoof speech. It uniquely offers transcripts, consistent speaker identities, five dialect groups, and extensive Vietnamese‑English code‑switching—nearly half of the corpus—while pairing each spoof with a matched bona fide utterance. The dataset enables controlled evaluation of deep‑fake detection models, revealing significant variability in detector performance across dialects and speaker similarity.
arXiv:2607. 03928v1 Announce Type: cross Abstract: Accent normalization (AN) seeks to convert non-native (L2) accented speech into standard (L1) speech while preserving speaker identity.
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.
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:2606. 07080v1 Announce Type: cross Abstract: We present dots.
arXiv:2609. 11786v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems and audio language models (audio LMs) now report low error rates on monolingual benchmarks, but their behavior on code switched speech in low resource, diacritic rich languages remains poorly characterized.