End-to-End Automatic Speech Translation of Audiobooks

Alexandre B\'erard; Ali Can Kocabiyikoglu; Laurent Besacier; Olivier Pietquin

RECORD

End-to-End Automatic Speech Translation of Audiobooks

Alexandre Bérard, Laurent Besacier, Ali Can Kocabiyikoglu, Olivier Pietquin

Computation and Language · Submitted 12 Feb 2018

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim Experimental results show that it is possible to train compact and efficient end-to-end speech translation models in this setup.

how it is stated · hedged possibility 0.50 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

arXiv ID1802.04200 (version 1)

Pith IDCJPMO6GJ, Pith's permanent record of this paper and its review

CitationAlexandre B\'erard, Ali Can Kocabiyikoglu, Laurent Besacier, Olivier Pietquin. "End-to-End Automatic Speech Translation of Audiobooks." arXiv:1802.04200 (2018). https://pith.science/paper/CJPMO6GJ

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 4,169 input tokens.

What the abstract itself states, as probabilities: claims first 0.05 · states limitation 0.26 · human participants 0.06 · controlled comparison 0.33 · randomized assignment 0.01 · states quantitative result 0.05 · compares with prior results 0.53 · mentions code or data availability 0.83.

The abstract, sentence by sentence

arXiv listing abstract v1. Results and the main claim are underlined; show every role.

We investigate end-to-end speech-to-text translation on a corpus of audiobooks specifically augmented for this task. Previous works investigated the extreme case where source language transcription is not available during learning nor decoding, but we also study a midway case where source language transcription is available at training time only. In this case, a single model is trained to decode source speech into target text in a single pass. Experimental results show that it is possible to train compact and efficient end-to-end speech translation models in this setup. We also distribute the corpus and hope that our speech translation baseline on this corpus will be challenged in the future.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	We investigate end-to-end speech-to-text translation on a corpus of audiobooks specifically augmented for this task.	contribution 0.97	0.92	0.06	asserted 0.88
s1	Previous works investigated the extreme case where source language transcription is not available during learning nor decoding, but we also study a midway case where source language transcription is available at training time only.	contribution 0.59	0.65	0.05	asserted 0.99
s2	In this case, a single model is trained to decode source speech into target text in a single pass.	method 0.98	0.76	0.07	asserted 0.96
s3	Experimental results show that it is possible to train compact and efficient end-to-end speech translation models in this setup.	result 0.92	0.95	0.68	hedged possibility 0.50
s4	We also distribute the corpus and hope that our speech translation baseline on this corpus will be challenged in the future.	future work 0.92	0.79	0.04	asserted 0.52

What kind of paper the classifier reports this is: dataset or benchmark 0.80 · evidence from observation or experiment 0.99.

What was examined, and what was not

sources read

arXiv listing abstract v1

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

We investigate end-to-end speech-to-text translation on a corpus of audiobooks specifically augmented for this task. Previous works investigated the extreme case where source language transcription is not available during learning nor decoding, but we also study a midway case where source language transcription is available at training time only. In this case, a single model is trained to decode source speech into target text in a single pass. Experimental results show that it is possible to train compact and efficient end-to-end speech translation models in this setup. We also distribute the corpus and hope that our speech translation baseline on this corpus will be challenged in the future.

Human review

How Pith checks papers → · Full audit of this paper →

How the literature uses it

6 arXiv papers cite this in 9 sentences

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers citing it · 3 sentences without a confident label

Uses its method or tool 1 paper

This can be implemented through multi-task training [ref] .

Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation · Introduction · 0.81

Cites it as background 4 papers

While traditionally realized by cascading an automatic speech recognition (ASR) and a machine translation (MT) component, recent work showed that it is feasible to employ a single sequence-to-sequence model instead [ref] .

Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation · Introduction · 0.88
Synthesized speech data were translated in [ref] using a model similar to the Listen Attend and Spell model [ref] , while a larger-scale study [ref] used an end-to-end system for translating audio books between French and English.

Leveraging translations for speech transcription in low-resource settings · Related Work · 0.96
Synthesized speech data were translated in [ref] using a model similar to the Listen Attend and Spell model [ref] , while a larger-scale study [ref] used an end-to-end system for translating audio books between French and English.

A small Griko-Italian speech translation corpus · Related Work · 0.94

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.