TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Audio/Speech Recognition/swb_hub_500 WER fullSWBCH

Speech Recognition on swb_hub_500 WER fullSWBCH

Metric: Percentage error (lower is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Percentage error▲Extra DataPaperDate↕Code
1IBM (LSTM+Conformer encoder-decoder)6.8NoOn the limit of English conversational speech re...2021-05-03-
2IBM (LSTM encoder-decoder)7.8NoSingle headed attention based sequence-to-sequen...2020-01-20-
3ResNet + BiLSTMs acoustic model10.3NoEnglish Conversational Telephone Speech Recognit...2017-03-06-
4VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+Broadcast11.9NoThe Microsoft 2016 Conversational Speech Recogni...2016-09-12-
5RNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + "model M" + NNLM language model12.2NoThe IBM 2016 English Conversational Telephone Sp...2016-04-27-
6HMM-BLSTM trained with MMI + data augmentation (speed) + iVectors + 3 regularizations + Fisher13No---
7HMM-TDNN trained with MMI + data augmentation (speed) + iVectors + 3 regularizations + Fisher (10% / 15.1% respectively trained on SWBD only)13.3No---
8CNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWB16NoDeep Speech: Scaling up end-to-end speech recogn...2014-12-17Code
9HMM-TDNN + iVectors17.1No---
10HMM-DNN +sMBR18.4No---
11DNN + Dropout19.1NoBuilding DNN Acoustic Models for Large Vocabular...2014-06-30Code
12HMM-TDNN + pNorm + speed up/down speech19.3No---