no code implementations • 28 Mar 2024 • Yash Jain, David Chan, Pranav Dheram, Aparna Khare, Olabanji Shonibare, Venkatesh Ravichandran, Shalini Ghosh
Recent advances in machine learning have demonstrated that multi-modal pre-training can improve automatic speech recognition (ASR) performance compared to randomly initialized models, even when models are fine-tuned on uni-modal tasks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 26 Jan 2024 • Jinhan Wang, Long Chen, Aparna Khare, Anirudh Raju, Pranav Dheram, Di He, Minhua Wu, Andreas Stolcke, Venkatesh Ravichandran
We propose an approach for continuous prediction of turn-taking and backchanneling locations in spoken dialogue by fusing a neural acoustic model with a large language model (LLM).
no code implementations • 17 Jan 2024 • Anirudh Raju, Aparna Khare, Di He, Ilya Sklyar, Long Chen, Sam Alptekin, Viet Anh Trinh, Zhe Zhang, Colin Vaz, Venkatesh Ravichandran, Roland Maas, Ariya Rastrow
Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands.
no code implementations • 22 Dec 2023 • Anirudh S. Sundar, Chao-Han Huck Yang, David M. Chan, Shalini Ghosh, Venkatesh Ravichandran, Phani Sankar Nidadavolu
In cases where some data/compute is available, we present Learnable-MAM, a data-driven approach to merging attention matrices, resulting in a further 2. 90% relative reduction in WER for ASR and 18. 42% relative reduction in AEC compared to fine-tuning.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 16 Nov 2023 • Helin Wang, Venkatesh Ravichandran, Milind Rao, Becky Lammers, Myra Sydnor, Nicholas Maragakis, Ankur A. Butala, Jayne Zhang, Lora Clawson, Victoria Chovaz, Laureano Moro-Velazquez
Spoken language understanding (SLU) systems often exhibit suboptimal performance in processing atypical speech, typically caused by neurological conditions and motor impairments.
no code implementations • 27 Mar 2023 • Srinath Tankasala, Long Chen, Andreas Stolcke, Anirudh Raju, Qianli Deng, Chander Chandak, Aparna Khare, Roland Maas, Venkatesh Ravichandran
We propose a novel approach for ASR N-best hypothesis rescoring with graph-based label propagation by leveraging cross-utterance acoustic similarity.
no code implementations • 23 Mar 2023 • Do June Min, Andreas Stolcke, Anirudh Raju, Colin Vaz, Di He, Venkatesh Ravichandran, Viet Anh Trinh
In this paper, we aim to provide a solution for adaptive endpointing by proposing an efficient method for choosing an optimal endpointing configuration given utterance-level audio features in an online setting, while avoiding hyperparameter grid-search.
no code implementations • 4 Nov 2022 • Xin Zhang, Iván Vallés-Pérez, Andreas Stolcke, Chengzhu Yu, Jasha Droppo, Olabanji Shonibare, Roberto Barra-Chicote, Venkatesh Ravichandran
By fine-tuning an ASR model on synthetic stuttered speech we are able to reduce word error by 5. 7% relative on stuttered utterances, with only minor (<0. 2% relative) degradation for fluent utterances.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 8 Jul 2022 • Long Chen, Yixiong Meng, Venkatesh Ravichandran, Andreas Stolcke
Speaker identification (SID) in the household scenario (e. g., for smart speakers) is an important but challenging problem due to limited number of labeled (enrollment) utterances, confusable voices, and demographic imbalances.
no code implementations • 8 Feb 2022 • Olabanji Shonibare, Xiaosu Tong, Venkatesh Ravichandran
We propose a simple but effective method called 'Detect and Pass' to make modern ASR systems accessible for People Who Stutter in a limited data setting.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 15 Jun 2021 • Long Chen, Venkatesh Ravichandran, Andreas Stolcke
We show in experiments on the VoxCeleb dataset that this approach makes effective use of unlabeled data and improves speaker identification accuracy compared to two state-of-the-art scoring methods as well as their semi-supervised variants based on pseudo-labels.