| Device selection for providing a response JD Meyers, SS Pravinchandra, Y Liu, A Dean, D Miller, A Mandal US Patent 9,875,081, 2018 | 539 | 2018 |
| Fine-grained natural language understanding L Mathias, T Kollar, A Mandal, A Metallinou US Patent 10,304,444, 2019 | 316 | 2019 |
| Multi-task learning and weighted cross-entropy for DNN-based keyword spotting S Panchapagesan, M Sun, A Khare, S Matsoukas, A Mandal, ... | 182 | 2016 |
| Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting M Sun, A Raju, G Tucker, S Panchapagesan, G Fu, A Mandal, ... 2016 IEEE spoken language technology workshop (SLT), 474-480, 2016 | 142 | 2016 |
| Normalized amplitude modulation features for large vocabulary noise-robust speech recognition V Mitra, H Franco, M Graciarena, A Mandal 2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012 | 119 | 2012 |
| Recent innovations in speech-to-text transcription at SRI-ICSI-UW A Stolcke, B Chen, H Franco, VRR Gadde, M Graciarena, MY Hwang, ... IEEE Transactions on Audio, Speech, and Language Processing 14 (5), 1729-1744, 2006 | 116 | 2006 |
| Advancing the state of the art in open domain dialog systems through the alexa prize C Khatri, B Hedayatnia, A Venkatesh, J Nunn, Y Pan, Q Liu, H Song, ... arXiv preprint arXiv:1812.10757, 2018 | 113 | 2018 |
| Monophone-based background modeling for two-stage on-device wake word detection M Wu, S Panchapagesan, M Sun, J Gu, R Thomas, SNP Vitaladevuni, ... 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 93 | 2018 |
| Clarifying natural language input using targeted questions NF Ayan, A Mandal, J Zheng US Patent 9,805,718, 2017 | 91 | 2017 |
| Using system command utterances to generate a speaker profile V Krishnamoorthy, S Srinivasan, S Matsoukas, A Khare, A Mandal, ... US Patent 10,490,195, 2019 | 82 | 2019 |
| Further progress in meeting recognition: The ICSI-SRI Spring 2005 speech-to-text evaluation system A Stolcke, X Anguera, K Boakye, Ö Çetin, F Grézl, A Janin, A Mandal, ... Machine Learning for Multimodal Interaction: Second International Workshop …, 2006 | 74 | 2006 |
| Dialog management for multiple users P Krishnan, A Mandal, SR Jonnalagadda, N Strom, A Rastrow, Y Shi, ... US Patent 11,908,468, 2024 | 68 | 2024 |
| Direct modeling of raw audio with dnns for wake word detection K Kumatani, S Panchapagesan, M Wu, M Kim, N Strom, G Tiwari, ... 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2017 | 64 | 2017 |
| Robust i-vector based adaptation of DNN acoustic model for speech recognition S Garimella, A Mandal, N Ström, B Hoffmeister, S Matsoukas, ... | 62 | 2015 |
| Keyword spotting using multi-task configuration S Panchapagesan, B Hoffmeister, A Mandal, A Khare, SNP Vitaladevuni, ... US Patent 10,304,440, 2019 | 61 | 2019 |
| Trigger word detection using neural network waveform processing A Mandal, N Strom, K Kumatani, S Panchapagesan US Patent 10,847,137, 2020 | 54 | 2020 |
| Time-delayed bottleneck highway networks using a DFT feature for keyword spotting J Guo, K Kumatani, M Sun, M Wu, A Raju, N Ström, A Mandal 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 49 | 2018 |
| Further advances in open domain dialog systems in the third alexa prize socialbot grand challenge R Gabriel, Y Liu, A Gottardi, M Eric, A Khatri, A Chadha, Q Chen, ... | 48 | 2019 |
| Effective Arabic Dialect Classification Using Diverse Phonotactic Models. M Akbacak, D Vergyri, A Stolcke, N Scheffer, A Mandal Interspeech 11 (2011), 737-740, 2011 | 46 | 2011 |
| fMLLR based feature-space speaker adaptation of DNN acoustic models SHK Parthasarathi, B Hoffmeister, S Matsoukas, A Mandal, N Ström, ... | 45 | 2015 |
Andreas StolckeDistinguished AI Scientist, UniphoreVerified email at icsi.berkeley.edu
