Papers › The Microsoft 2016 Conversational Speech Recognition System

The Microsoft 2016 Conversational Speech Recognition System

12 Sep 2016arXiv:1609.03528archive 2025-07-28

W. Xiong, J. Droppo, X. Huang, F. Seide, M. Seltzer, A. Stolcke, D. Yu, G. Zweig

We describe Microsoft's conversational speech recognition system, in which we combine recent developments in neural-network-based acoustic and language modeling to advance the state of the art on the Switchboard recognition task. Inspired by machine learning ensemble techniques, the system uses a range of convolutional and recurrent neural networks. I-vector modeling and lattice-free MMI training provide significant gains for all acoustic model architectures. Language model rescoring with multiple forward and backward running RNNLMs, and word posterior-based system combination provide a 20% boost. The best single system uses a ResNet architecture acoustic model with RNNLM rescoring, and achieves a word error rate of 6.9% on the NIST 2000 Switchboard task. The combined system has an error rate of 6.2%, representing an improvement over previously reported results on this benchmark task.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingSpeech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition Switchboard + Hub500 Microsoft 2016 Percentage error 6.2 #5 of 30 Archive leaderboard report
Speech Recognition Switchboard + Hub500 VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+Broadcast Percentage error 6.3 #6 of 30 Archive leaderboard report
Speech Recognition Switchboard + Hub500 RNNLM Percentage error 6.9 #10 of 30 Archive leaderboard report
Speech Recognition swb_hub_500 WER fullSWBCH VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+Broadcast Percentage error 11.9 #4 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections