Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 349

The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.

English Conversational Telephone Speech Recognition by Humans and Machines

Open access
Saon, George, Kurata, Gakuto, Sercu, Tom, Audhkhasi, Kartik, Thomas, Samuel, Dimitriadis, Dimitrios, Cui, Xiaodong, Ramabhadran, Bhuvana, Picheny, Michael, Lim, Lynn-Li, Roomi, Bergul, Hall, Phil · 2017 · Interspeech 2017

Abstract

One of the most difficult speech recognition tasks is accurate recognition of human to human communication. Advances in deep learning over the last few years have produced major speech recognition improvements on the representative Switchboard conversational corpus. Word error rates that just a few years ago were 14% have dropped to 8.0%, then 6.6% and most recently 5.8%, and are now believed to be within striking range of human performance. This then raises two issues - what IS human performance, and how far down can we still drive speech recognition error rates? A recent paper by Microsoft suggests that we have already achieved human performance. In trying to verify this statement, we performed an independent set of human performance measurements on two conversational tasks and found that human performance may be considerably better than what was earlier reported, giving the community a significantly harder goal to achieve. We also report on our own efforts in this area, presenting a set of acoustic and language modeling techniques that lowered the word error rate of our own English conversational telephone LVCSR system to the level of 5.5%/10.3% on the Switchboard/CallHome subsets of the Hub5 2000 evaluation, which - at least at the writing of this paper - is a new performance milestone (albeit not at what we measure to be human performance!). On the acoustic side, we use a score fusion of three models: one LSTM with multiple feature inputs, a second LSTM trained with speaker-adversarial multi-task learning and a third residual net (ResNet) with 25 convolutional layers and time-dilated convolutions. On the language modeling side, we use word and character LSTMs and convolutional WaveNet-style language models.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21437/interspeech.2017-405

Cites

26 of 26 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 26 references

Cited by

See all 349

Metadata

Authors
Saon, G., Kurata, G., Sercu, T., Audhkhasi, K., Thomas, S., Dimitriadis, D., Cui, X., Ramabhadran, B., Picheny, M., Lim, L.-L., Roomi, B., & Hall, P.
Venue
Interspeech 2017
Publisher
ISCA
Published
2017-08-20
Pages
132-136
ISSN
2308-457X (ISSN-L)
OpenAlex
W2604132379
Cited by
349
References
26
FWCI
30.23
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: English Conversational Telephone Speech Recognition by Humans and Machines. https://app.cochat.ai/papers/10.21437/interspeech.2017-405
The paper
Saon, G., Kurata, G., Sercu, T., Audhkhasi, K., Thomas, S., Dimitriadis, D., Cui, X., Ramabhadran, B., Picheny, M., Lim, L.-L., Roomi, B., & Hall, P. (2017). English Conversational Telephone Speech Recognition by Humans and Machines. Interspeech 2017. https://doi.org/10.21437/interspeech.2017-405

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.