The reviewed record of science sign in
Pith

arxiv: 2205.12446 · v1 · pith:CHNUWEDW · submitted 2022-05-25 · cs.CL · cs.LG· cs.SD· eess.AS

FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech

Alexis Conneau , Min Ma , Simran Khanuja , Yu Zhang , Vera Axelrod , Siddharth Dalmia , Jason Riesa , Clara Rivera
show 1 more author
Ankur Bapna
This is my paper

Reviewed by Pithpith:CHNUWEDWopen to challenge →

classification cs.CL cs.LGcs.SDeess.AS
keywords speechfleursbenchmarkevaluationfew-shotlanguagelanguageslearning
0
0 comments X
read the original abstract

We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of the machine translation FLoRes-101 benchmark, with approximately 12 hours of speech supervision per language. FLEURS can be used for a variety of speech tasks, including Automatic Speech Recognition (ASR), Speech Language Identification (Speech LangID), Translation and Retrieval. In this paper, we provide baselines for the tasks based on multilingual pre-trained models like mSLAM. The goal of FLEURS is to enable speech technology in more languages and catalyze research in low-resource speech understanding.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Multilingual Phonological Feature Recognition with Self-Supervised Speech Models

    cs.CL 2026-05 unverdicted novelty 7.0

    PhonoQ-2.0 directly predicts structured phonological features from self-supervised models with a gating mechanism, outperforming phoneme baselines by 8+ macro-F1 points on average across in-domain, out-of-domain, and ...

  2. Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition

    cs.CL 2026-05 unverdicted novelty 7.0

    Introduces a complexity-tiered benchmark for Indic ASR and a reverse multi-stage fine-tuning recipe enabling smaller models to match larger ones on spontaneous speech.

  3. Benchmarking Multilingual Speech Models on Pashto: Zero-Shot ASR, Script Failure, and Cross-Domain Evaluation

    cs.CL 2026-04 conditional novelty 7.0

    Multilingual ASR models show 39.7-297% zero-shot WER on Pashto public data, Whisper models output correct script in under 0.8% of cases, and fine-tuned models degrade to 32.5-59% WER on out-of-domain sets.

  4. Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs

    cs.CL 2025-12 unverdicted novelty 7.0

    Cascaded systems remain the most reliable for speech translation overall, but recent SpeechLLMs match or outperform them in many conditions while standalone speech models lag.

  5. When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR

    cs.CL 2026-05 unverdicted novelty 6.0

    Domain-adapted ASR leaks private context by transcribing phonetically similar words from prompts or training data even when a different word is spoken.

  6. Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition

    cs.CL 2026-05 accept novelty 6.0

    Vividh-ASR benchmark and reverse multi-stage fine-tuning enable smaller Whisper models to match larger ones on complex Indic speech by concentrating adaptation in the decoder.

  7. UAF: A Unified Audio Front-end LLM for Full-Duplex Speech Interaction

    cs.AI 2026-04 unverdicted novelty 6.0

    UAF is the first unified audio front-end LLM that turns multiple front-end tasks into one sequence prediction model processing streaming audio chunks and reference prompts to output semantic and control tokens for ful...

  8. BlasBench: An Open Benchmark for Irish Speech Recognition

    cs.CL 2026-04 conditional novelty 6.0

    BlasBench supplies an Irish-aware normalizer and scoring harness that enables reproducible ASR comparisons and exposes a 33-43 point generalization gap for fine-tuned models versus 7-10 points for massively multilingual ones.

  9. MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages

    cs.CL 2025-12 conditional novelty 6.0

    MCAT scales MLLMs to many-to-many speech translation across 70 languages via curriculum learning and a 30-token speech adapter, surpassing prior SOTA on FLEURS while improving speed.

  10. StepAudio 2.5 Technical Report

    eess.AS 2026-05 unverdicted novelty 5.0

    StepAudio 2.5 is a unified audio-language foundation model that reaches state-of-the-art results on ASR, TTS, and realtime interaction by using task-tailored RLHF on a shared backbone.

  11. Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps

    cs.CL 2026-04 unverdicted novelty 5.0

    Four attention metrics enable logistic regression classifiers that detect hallucinations in SpeechLLMs with up to +0.23 PR-AUC gains over baselines on ASR and translation tasks.

  12. Factors affecting ASR performance: A study using state of the art ASR models in Indic Languages

    eess.AS 2026-06 unverdicted novelty 4.0

    Empirical analysis of speaker and acoustic factors correlated with ASR word error rates across five Indic languages using zero-shot evaluation on multiple open-source models.