Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.28758

BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge

Prakriti Subedi·Howard Prioleau·Saurav K Aryal
View original source ↗Read source document ↗Export metadata ↓

Abstract

We describe our submission to the Unsupervised Speech in the Wild (UPS) Challenge at Interspeech 2026, a bidirectional Mamba-2 (BiMamba2) encoder trained with masked discrete-unit prediction following the HuBERT-style paradigm. The 47.88M-parameter model is trained on 250 hours of speech across 67 languages from the MLCommons Unsupervised People's Speech dataset, with no labeled data. The objective combines masked k-means pseudo-label prediction with language identification supervision and VICReg regularization. On official evaluation, the system achieves an Adjusted Rand Index of 0.735, exceeding four baselines on speaker clustering. Language identification macro-F1 (0.073) and character error rate (0.870) remain below supervised baselines. We analyze a local-official discrepancy in metric scale and checkpoint ranking, highlighting limitations of in-distribution diagnostics for predicting Dynabench probe outcomes.

Explore related subjects

cs.SDcs.CL

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Prakriti Subedi, Howard Prioleau, Saurav K Aryal. 2026-09-23. BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge. https://doi.org/10.21437/interspeech.2026-2966

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Same Words, Different Judgments: How Preferences Vary Across Modalities

Preference-based reinforcement learning (PbRL) is the dominant framework for aligning AI systems to human preferences. However, evaluation protocols for such data were designed for text and have not been validated for speech. We present the first intraclass correlation coefficient (ICC)-based, controlled cross-modal study of human and synthetic preference annotations, comparing text and audio evaluations of identical semantic content across 100 prompts. We show that achieving \textit{good} agreement within either modality (ICC(2,$k$) $\approx$ .80) requires $\sim$9 raters and modalities show marked differences in how people report preferences: audio raters exhibit narrower decision thresholds, reduced length bias, and more user-oriented evaluation criteria, with near-chance cross-modality agreement. We demonstrate that synthetic ratings can be used to effectively predict inter-rater agreement, thus serving as an early signal for stimulus selection and proxy for human annotations. Together, these findings argue that evaluation protocols for audio preference data require modality-specific design rather than direct adaptation from text. Code, data, and the audio corpus are available at: https://huggingface.co/datasets/sciminds/same-words-different-judgements

cs.SD↗
arXiv2026

Oído: Real-Time Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator

Speech recognition on low-cost microcontrollers is, in practice, limited to keyword spotting or a fixed list of commands. We present Oído, an inference engine and a family of models that run open-vocabulary English speech recognition entirely on an ESP32-S3 (240 MHz Xtensa LX7, 8 MB of PSRAM, 16 MB of flash, no neural accelerator) faster than real time on one core. Version 1 of this work ran a 13 M-parameter Conformer-CTC at 1.97x the duration of the audio. We measured on the board that the bound was memory traffic and per-frame cost, not arithmetic: external memory reads at 89 MB/s (PSRAM) and 32 MB/s (flash), and a streaming recognizer re-reads every weight for every chunk. Version 2 combines a model built for that memory system (80 ms frame stacking, a 64-channel front end, 12 or 16 blocks, int4 weights that mostly fit in PSRAM, fine-tuned from the version 1 model) with engine changes that overlap the weight stream with compute (an asynchronous data-cache preload), keep work buffers in SRAM and make the decoder cheap. On a physical board the streaming real-time factor falls from 1.77 to 0.54 (variant B) and 0.72 (variant A), the final text appears 259 ms (B) or 431 ms (A) after the end of speech with audio fed at real-time speed, and the host build and the firmware produce identical transcripts. Variant A reaches 7.1%/16.4% word error rate on LibriSpeech test-clean/test-other in streaming mode with 0.64 s chunks and the on-chip language model (4.6%/10.7% with full context). Code, models and the raw board measurements are released.

cs.SD↗
arXiv2026

Biologically Inspired Predictive Gating Signed-Dyadic Coding for Mandarin Keyword Spotting

In continuous spiking keyword spotting, temporally correlated acoustic frames can repeatedly trigger memory access and neural computation at a dense input interface, even when hidden activity is sparse. Predictive processing and sensory adaptation suggest retaining predictable input locally and responding selectively to deviations. Inspired by this mechanism, we propose Predictive Gating Signed-Dyadic Coding (PG). PG maintains a local prediction for each input channel and transmits an event only when the residual exceeds a learned threshold. Each event carries a sign and a finite power-of-two magnitude, and the receiver reconstructs it with fixed-point shifts and additions. In Mandarin keyword spotting, INPUT-PG reaches 90.00% accuracy while reducing mean SRAM reads by 33.87% and inference cycles by 32.77%. PG provides a hardware interface for research on low-power continuous speech processing and event-based sensory systems.

cs.SD↗