The DOI matches its Crossref record; 58 of the 60 references it cites were found in a registry or an index.
The Microsoft 2017 Conversational Speech Recognition System
Open accessAbstract
We describe the latest version of Microsoft's conversational speech recognition system for the Switchboard and CallHome domains. The system adds a CNN-BLSTM acoustic model to the set of model architectures we combined previously, and includes character-based and dialog session aware LSTM language models in rescoring. For system combination we adopt a two-stage approach, whereby acoustic model posteriors are first combined at the senone/frame level, followed by a word-level voting via confusion networks. We also added another language model rescoring step following the confusion network combination. The resulting system yields a 5.1% word error rate on the NIST 2000 Switchboard test set, and 9.8% on the CallHome subset.
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.
Integrity signals
Registry
Cites
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Importantly, a 24% word error rate is probably not yet sufficiently low for everyday use (for example, compared with a 4–5% word error rate for state-of-the-art speech-to-text systems23,37).”
From A high-performance speech neuroprosthesis (2023) · cites this paper as [23]
In the citing paper
“They are, however, not limited to image processing and analysis but are outperforming other approaches in areas like natural language processing [3, 4, 5], speech recognition and synthesis [6, 7] 2 , and in the analysis of unstructured, tabular-type data using entity embeddings [8, 9].”
From An overview of deep learning in medical imaging focusing on MRI (2019) · cites this paper as [6]
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891
Framewise phoneme classification with bidirectional LSTM and other neural network architectures
Graves, A., & Schmidhuber, J. (2005) · Neural Networks · doi:10.1016/j.neunet.2005.06.042 · Cited by 6,152
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390
Convolutional networks for images, speech, and time series
LeCun, Y., & Bengio, Y. (1998) · HAL · doi:10.5555/303568.303704 · Cited by 4,646
SRILM - an extensible language modeling toolkit
Stolcke, A. (2002) · International Conference on Spoken Language Processing (ICSLP) · doi:10.21437/icslp.2002-303 · Cited by 4,385
Self-citationA Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Williams, R. J., & Zipser, D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.2.270 · Cited by 4,369
Research works printed but not linked: 2
- 0, The Microsoft Cognition Toolkit (CNTK)
- xiong, 2017, Conversational session-level language modeling with LSTMs, Submitted to IEEE ICASSP-2018
Cited by
Sorted by citations
Items 401–464 of 464
Towards robust and secure deep learning models and beyond
Wang, S. (2022) · doi:10.17760/d20467286 · Cited by 1
REQUIREMENTS ENGINEERING FOR ML-ENABLED SYSTEMS: STATUS QUO AND PROBLEMS
Alves, A. P. S. (2023) · doi:10.17771/pucrio.acad.65995 · Cited by 1
Paaß, G., & Hecker, D. (2023) · Springer eBooks · doi:10.1007/978-3-031-50605-5_7 · Cited by 1
Effendi, J., Tjandra, A., Sakti, S., & Nakamura, S. (2019) · arXiv (Cornell University)
Żelasko, P., Mizgajski, J. T., Morzy, M., Szymczak, A., Szymański, P., Augustyniak, Ł., & Carmiel, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.07888
Ultra low-power, high-performance accelerator for speech recognition
Aminabadi, R. Y. (2019) · doi:10.5821/dissertation-2117-167843
Simplified LSTMS for Speech Recognition
Saon, G., Tüske, Z., Audhkhasi, K., Kingsbury, B. E. D., Picheny, M., & Thomas, S. (2019) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru46091.2019.9003898
Using Convolution and Sequence-discriminative Training to Improving Children Speech Recognition
Meng, F., Peng, S., & Zhang, G. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023109
Voice Conversion Attacks on Speaker De-Identification Schemes
He, S., & Roelse, P. (2020) · International Conference on Consumer Electronics · doi:10.1109/icce46568.2020.9043154
User Intent Inference for Web Search and Conversational AgentsPreprint
Ahmadvand, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.13808
A responsabilidade dos linguistas no combate à manipulação da opinião pública via Internet
Albano, E. C. (2020) · Cadernos de Linguística · doi:10.25189/2675-4916.2020.v1.n4.id305
Support software for Automatic Speech Recognition systems targeted for non-native speech
Radzikowski, K., Yoshie, O., & Nowak, R. M. (2020) · International Conference on Information Integration and Web-based Applications & Services (iiWAS) · doi:10.1145/3428757.3429971
Liao, J., Shi, Y., Gong, M., Shou, L., Eskimez, Ş. E., Lu, L., Qu, H., & Zeng, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.11114
Paaß, G., & Hecker, D. (2020) · Künstliche Intelligenz · doi:10.1007/978-3-658-30211-5_7
Feature Replacement and Combination for Hybrid ASR Systems.Preprint
Vieting, P., Lüscher, C., Michel, W., Schlüter, R., & Ney, H. (2021) · arXiv (Cornell University)
Drivers' Manoeuvre Modelling and Prediction for Safe HRIPreprint
Pulgarín, E. J. L., Herrmann, G., & Leonards, U. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.01730
Edge service resource allocation strategy based on intelligent predictionPreprint
Wamg, Y., Du, X., Chen, X., & Lu, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.12740
Grid Cell as Interface Representation between Animal Brains and Artificial Neural Networks
Li, S., Deng, Y. S., & Wang, Z. (2021) · IEEE International Conference on Big Data and Artificial Intelligence (BDAI) · doi:10.1109/bdai52447.2021.9515218
Graphs as Tools to Improve Deep Learning MethodsPreprint
Lassance, C., Bontonou, M., Hamidouche, M., Pasdeloup, B., Drumetz, L., & Gripon, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.03999
A Study of Content-Based Recognition of Speech Utterance
Shafi, Y., & Saini, S. (2022) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2022.41292
Motion Imagination EEG Modal Automatic Recognition Based on CNN NetworkPreprint
Lyu, S., & Liu, L. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3980352
The Comprehensive Analysis Speech Recognition System
Soni, A., & Jitendra, J. (2021) · International Journal of Innovative Research in Computer Science & Technology · doi:10.55524/ijircst.2021.9.6.27
Vocal Parameters Analysis for Amazigh Phonemes Recognition System
Ouhnini, A., Aksasse, B., & Ouanan, M. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-01942-5_5
Design and Implementation of Distributed Image Recognition App with Federal Learning Techniques
Chan, Y.-W., Wu, B.-Y., Huang, Y., & Yang, C. (2022) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-20398-5_8
Mouth2Audio: intelligible audio synthesis from videos with distinctive vowel articulation
Garg, S., Ruan, H., Hamarneh, G., Behne, D. M., Jongman, A., Sereno, J. A., & Wang, Y. (2023) · International Journal of Speech Technology · doi:10.1007/s10772-023-10030-3
Leveraging Cross-Utterance Context For ASR Decoding
Flynn, R., & Ragni, A. (2023) · Interspeech (USB) · doi:10.21437/interspeech.2023-1941
Ogbaga, I. N., & Ezeanya, C. U. (2023) · doi:10.36227/techrxiv.23899788
Ogbaga, I. N., & Ezeanya, C. U. (2023) · doi:10.36227/techrxiv.23899788.v1
Nested perceptron model and its learning algorithm
Huang, X., Liu, Z., Liu, H., & Deng, Z. (2023) · International Conference on Frontiers of Electronics, Information and Computation Technologies · doi:10.1109/icfeict59519.2023.00056
Self-citationMa, Z., Li, Y., Liu, D., Zhang, Z., & Zheng, K. (2023) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3587716.3587744
Automatic Language Identification from Non-Uniform Region Using Bi-LSTM and CNN
Karthika, M. R., & George, A. (2023) · International Conference on Circuit, Power and Computing Technologies · doi:10.1109/iccpct58313.2023.10245174
Detecting speech recognition errors using topic information and BERT
Yokoyama, M., & Shimada, K. (2023) · IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiai-aai59060.2023.00084
What Are the Capabilities of Artificial Intelligence?
Paaß, G., & Hecker, D. (2023) · Springer eBooks · doi:10.1007/978-3-031-50605-5_2
Circuit Design of Piecewise Linear Activation Function for Memristive Neural Networks
Cai, R., Yang, L., Ding, Z., & Li, S. (2024) · International Conference on Artificial Intelligence and Computer Information Technology (AICIT) · doi:10.1109/aicit62434.2024.10730549
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3674128
Searching Personal Collections
Bendersky, M., Metzler, D., Najork, M., & Wang, X. (2024) · ACM eBooks · doi:10.1145/3674127.3674142
Query-driven Search Functionality
Li, L. (2024) · ACM eBooks · doi:10.1145/3674127.3674133
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3702962
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3674129
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3702961
Hersh, W., & Roberts, K. E. (2024) · ACM eBooks · doi:10.1145/3674127.3702960
Bast, H., Kalmbach, J., Klumpp, T., & Korzen, C. (2024) · ACM eBooks · doi:10.1145/3674127.3674134
Memristor-Based Neural Network and Its Application
Yu, Y., Wang, X., Feng, X., Shen, J., Tashi, N., & Mazumder, P. (2025) · Springer eBooks · doi:10.1007/978-981-96-0332-9_8
Shubham, S., Myanapuri, N., Mohanty, S., & Lashkare, S. (2025) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2025.3576359
Lee, M., Cho, H. W., & Lee, Y. H. (2025) · Investigative Magnetic Resonance Imaging · doi:10.13104/imri.2025.0005
Using Cross-Attention for Conversational ASR over the Telephone
Dymbe, S., Siniscalchi, S. M., Svendsen, T. K., & Salvi, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02548-7_33
Research on optimization of brain-controlled typing recognition based on imaginary handwriting
Nan, J., Xu, P., Zhang, K., Xu, Q., Zhang, S., Xia, Y., Han, C., Li, D., & Meng, Y. (2025) · Cluster Computing · doi:10.1007/s10586-025-05761-8
Otani, T., Aihara, R., Takashima, R., Takiguchi, T., & Saito, T. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3759757
Benchmarking STT Systems for Turkish: Accuracy and Transcription Performance Evaluation
Kamali, H. O., Oz, Z., Gorgulu, A. B., Kızıltepe, R. S., & Karakuş, M. (2025) · doi:10.1109/ubmk67458.2025.11206751
Machine Intelligence Propelled Chatbot for College Inquiries Control
Raul, P., Dutta, S., Sarangi, R., Mishra, N., Yang, T., Mo, D., & Rathore, B. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8343-7_35
Multilingual and Accent-Aware Transformation of Read Speech to Conversational Speech
Hallikar, R. S., & Porwal, A. (2026) · IEEE Access · doi:10.1109/access.2026.3653970
DDSS: Detecting Different Stuttered Speech Using Various Feature Extraction Techniques
Batra, A., Hema, Y., Rao, V., & Das, P. K. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-14534-5_26
Improving Contextual Biasing in Chinese ASR via Multimodal Large Language Models
Zhang, K., Zhang, Q., Wang, C.-C., & Jang, J. R. (2026) · IEEE Access · doi:10.1109/access.2026.3667399
XBMU-AMDO31: A dataset of speech recognition dataset for the Amdo dialect of Tibetan
Chenyu, X. I. E., Guanyu, L. I., Like, M. A., Sun, Q., & Yuhao, G. U. O. (2026) · China Scientific Data · doi:10.11922/11-6035.csd.2025.0113.zh
Towards a Usage-Based Pedagogy for Second Language Learning with Robots
Verhelst, E., & Belpaeme, T. (2026) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3776734.3794484
STM-WFBP: Selective Tensor Merging Method in Distributed Learning
Dong, P., Yi, Q., Zhang, L., & Tang, W. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-8405-5_8
Leveraging lyrics from audio for MIR
Vaglio, A. (2021) · theses.fr (ABES) · doi:10.70675/23fad121zeacfz49ebzb9b4z227132cfc0e4
Kumar, C. P., Santosh, B. C. R. S., Kumar, C. S. M., Mathan, N., & Reddy, C. A. M. (2026) · doi:10.1109/iccsp68173.2026.11539240
A Comparative Analysis of Multilingual Speech Recognition Using Vosk and Whisper Models
Shinde, S. A., Bhamare, A., Jagtap, S., Sutar, A., & Ghorpade, M. (2026) · International Conference on Computing Communication Control and automation · doi:10.1109/iccubea69821.2026.11702082
Metadata
- Authors
- Xiong, W., Wu, L., Alleva, F., Droppo, J., Huang, X., & Stolcke, A.
- Affiliations
- Microsoft (United States) (US)
- Venue
- 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2018-04
- Pages
- 5934-5938
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2916979304
- Cited by
- 472
- References
- 60
- Citations by year
- 2026: 11 · 2025: 18 · 2024: 38 · 2023: 33 · 2022: 59 · 2021: 72 · 2020: 96 · 2019: 103 · 2018: 35
- FWCI
- 30.44
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- conversational speech recognition, switchboards, CALLHOME, LSTM language models, confusion networks, system combination, word error rate
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
