| Personalized speech enhancement: new models and Comprehensive evaluation | 2 | 0.37 | 2022 |
| Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention | 0 | 0.34 | 2022 |
| One Model to Enhance Them All: Array Geometry Agnostic Multi-Channel Personalized Speech Enhancement | 0 | 0.34 | 2022 |
| Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention. | 0 | 0.34 | 2022 |
| Enhancing Factual Consistency of Abstractive Summarization | 0 | 0.34 | 2021 |
| UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data | 0 | 0.34 | 2021 |
| Leveraging Lead Bias for Zero-shot Abstractive News Summarization | 1 | 0.37 | 2021 |
| Fusing Context Into Knowledge Graph for Commonsense Question Answering. | 0 | 0.34 | 2021 |
| A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining. | 0 | 0.34 | 2020 |
| Mixed-Lingual Pre-training for Cross-lingual Summarization | 0 | 0.34 | 2020 |
| TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising | 0 | 0.34 | 2020 |
| Multi-task Learning for Natural Language Generation in Task-Oriented Dialogue | 2 | 0.37 | 2019 |
| Advances in Online Audio-Visual Meeting Transcription | 5 | 0.53 | 2019 |
| Meeting Transcription Using Asynchronous Distant Microphones | 1 | 0.37 | 2019 |
| Meeting Transcription Using Virtual Microphone Arrays. | 0 | 0.34 | 2019 |
| Achieving Human Parity on Automatic Chinese to English News Translation. | 26 | 0.79 | 2018 |
| Big Data for Speech and Language Processing | 2 | 0.38 | 2018 |
| SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering. | 2 | 0.36 | 2018 |
| Toward Human Parity in Conversational Speech Recognition. | 11 | 0.56 | 2017 |
| Achieving Human Parity in Conversational Speech Recognition. | 64 | 2.51 | 2016 |
| Large-Scale Question Answering with Joint Embedding and Proof Tree Decoding | 0 | 0.34 | 2015 |
| Web Information at Your Fingertips: Paper as an Interaction Metaphor | 1 | 0.36 | 2014 |
| A historical perspective of speech recognition | 31 | 1.38 | 2014 |
| International workshop on question answering on the web (QAWeb2008) | 0 | 0.34 | 2008 |
| Challenges in adopting speech recognition | 58 | 2.94 | 2004 |
| Enabling natural computing | 0 | 0.34 | 2004 |
| Speech and Language Processing for Multimodal Human-Computer Interaction | 4 | 0.42 | 2004 |
| Distributed speech processing in miPad's multimodal user interface | 19 | 1.98 | 2002 |
| High-performance robust speech recognition using stereo training data | 60 | 6.06 | 2001 |
| Mipad: A multimodal interaction prototype | 16 | 1.28 | 2001 |
| Denoising Image Via Minimum Variance Bound Bayesian Estimator | 3 | 0.44 | 2001 |
| A Unified Context-Free Grammar And N-Gram Model For Spoken Language Processing | 26 | 3.56 | 2000 |
| Large-vocabulary speech recognition under adverse acoustic environments | 106 | 10.90 | 2000 |
| Subword-dependent speaker clustering for improved speech recognition | 2 | 1.25 | 2000 |
| MiPad: A next generation pda prototype | 29 | 3.41 | 2000 |
| MiPad: A next generation pda prototype | 29 | 3.41 | 2000 |
| Improved topic-dependent language modeling using information retrieval techniques. | 30 | 3.71 | 1999 |
| IMPROVEMENTS ON SPEECH RECOGNITON FOR FAST TALKERS | 12 | 0.73 | 1999 |
| Unified decoding and feature representation for improved speech recognition | 2 | 0.48 | 1999 |
| Can continuous speech recognizers handle isolated speech? | 5 | 2.32 | 1998 |
| Vocabulary-independent word confidence measure using subword features | 9 | 0.78 | 1998 |
| Automatic Generation Of Synthesis Units For Trainable Text-To-Speech Systems | 31 | 5.79 | 1998 |
| How effective is unsupervised data collection for children's speech recognition? | 3 | 0.66 | 1998 |
| Hmm-Based Smoothing For Concatenative Speech Synthesis | 13 | 2.36 | 1998 |
| Dynamically Configurable Acoustic Models For Speech Recognition | 9 | 1.28 | 1998 |
| Improvements on a trainable letter-to-sound converter | 13 | 2.73 | 1997 |
| Deleted interpolation and density sharing for continuous hidden Markov models | 12 | 1.73 | 1996 |
| Speaker and gender normalization for continuous-density hidden Markov models. | 13 | 1.53 | 1996 |
| Improvements on the pronunciation prefix tree search organization. | 19 | 4.42 | 1996 |
| Whistler: A Trainable Text-To-Speech System | 40 | 8.98 | 1996 |
