Pith. sign in

REVIEW 2 cited by

Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2007.03001 v2 pith:D4MT2DXW submitted 2020-07-06 eess.AS cs.CLcs.SD

Vineel Pratap , Anuroop Sriram , Paden Tomasello , Awni Hannun , Vitaliy Liptchinsky , Gabriel Synnaeve , Ronan Collobert This is my paper
classification eess.AScs.CLcs.SD
keywords languagesmodellanguagemultilingualtraininghoursjointinput
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all simplifying deployment of ASR systems that support diverse languages. We perform an extensive benchmark on 51 languages, with varying amount of training data by language(from 100 hours to 1100 hours). We compare three variants of multilingual training from a single joint model without knowing the input language, to using this information, to multiple heads (one per language cluster). We show that multilingual training of ASR models on several languages can improve recognition performance, in particular, on low resource languages. We see 20.9%, 23% and 28.8% average WER relative reduction compared to monolingual baselines on joint model, joint model with language input and multi head model respectively. To our knowledge, this is the first work studying multilingual ASR at massive scale, with more than 50 languages and more than 16,000 hours of audio across them.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Finetuned Language Models Are Zero-Shot Learners

    cs.CL 2021-09 accept novelty 8.0 of 10

    Instruction tuning a 137B language model on over 60 NLP tasks described by instructions substantially boosts zero-shot performance on unseen tasks, outperforming larger GPT-3 models.

  2. A Generalist Agent

    cs.AI 2022-05 accept novelty 7.0 of 10

    Gato is a multi-modal, multi-task, multi-embodiment generalist policy using one transformer network to handle text, vision, games, and robotics tasks.

Pith tools