REVIEW 3 cited by
Towards Robust Speech Representation Learning for Thousands of Languages
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the world's 7000+ languages. We propose XEUS, a Cross-lingual Encoder for Universal Speech, trained on over 1 million hours of data across 4057 languages, extending the language coverage of SSL models 4-fold. We combine 1 million hours of speech from existing publicly accessible corpora with a newly created corpus of 7400+ hours from 4057 languages, which will be publicly released. To handle the diverse conditions of multilingual speech data, we augment the typical SSL masked prediction approach with a novel dereverberation objective, increasing robustness. We evaluate XEUS on several benchmarks, and show that it consistently outperforms or achieves comparable results to state-of-the-art (SOTA) SSL models across a variety of tasks. XEUS sets a new SOTA on the ML-SUPERB benchmark: it outperforms MMS 1B and w2v-BERT 2.0 v2 by 0.8% and 4.4% respectively, despite having less parameters or pre-training data. Checkpoints, code, and data are found in https://www.wavlab.org/activities/2024/xeus/.
Forward citations
Cited by 3 Pith papers
-
Chain-of-Thought Training for Open E2E Spoken Dialogue Systems
Staged ASR-to-text-response-to-TTS training makes open end-to-end spoken dialogue systems trainable on 300 hours of public human-human data and more coherent than one-step speech-to-speech models.
-
From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition
Fine-tuning TTS models on tens of hours of real audio enables generation of 500,000 hours of synthetic speech that reduces ASR error rates by over 30% on Whisper-large-v3.
-
EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion
EZ-VC combines discrete units from a multilingual self-supervised encoder (Xeus) with an F5-TTS flow-matching decoder to achieve zero-shot any-to-any voice conversion, without text labels or multiple disentangling encoders.
Discussion (0). Continue with ORCID to comment.