A network of deep neural networks for distant speech recognition

Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and reverberation are met.

cs.CL cs.LG Computer Science Engineering

Paper

Similar papers

Deep Learning for Distant Speech RecognitionM. Ravanelli2017 · arXiv.org · 16 citations In Library

Ensemble of Jointly Trained Deep Neural Network-Based Acoustic Models for Reverberant Speech RecognitionJee-Hye Lee, Myungin Lee, Joon‐Hyuk Chang2016 · Digit. Signal Process. · 28 citations In Library

STC Speaker Recognition Systems for the VOiCES From a Distance ChallengeSergey Novoselov, Aleksei Gusev, Artem Ivanov et al.2019 · Interspeech · 26 citations In Library

Joint training of DNNs by incorporating an explicit dereverberation structure for distant speech recognitionTian Gao, Jun Du, Yong Xu et al.2016 · EURASIP Journal on Advances in Signal Processing · 4 citations In Library

Batch-normalized joint training for DNN-based distant speech recognitionM. Ravanelli, Philemon Brakel, M. Omologo et al.2016 · Spoken Language Technology Workshop · 35 citations In Library

Evaluation of Mixed Deep Neural Networks for Reverberant Speech EnhancementMichelle Gutiérrez-Muñoz, Astryd González-Salazar, Marvin Coto-Jiménez2019 · Biomimetics · 8 citations In Library

A novel stochastic deep resilient network for effective speech recognitionShilpi Shukla, Madhu Jain2021 · International Journal of Speech Technology · 7 citations In Library

Deep encoder/decoder dual-path neural network for speech separation in noisy reverberation environmentsChunxi Wang, Maoshen Jia, Xinfeng Zhang2023 · EURASIP Journal on Audio, Speech, and Music Processing · 7 citations In Library

Analyzing Large Receptive Field Convolutional Networks for Distant Speech RecognitionSalar Jafarlou, S. Khorram, Vinay Kothapally et al.2019 · Automatic Speech Recognition & Understanding · 10 citations In Library

Multi-Channel Training for End-to-End Speaker Recognition Under Reverberant and Noisy EnvironmentDanwei Cai, Xiaoyi Qin, Ming Li2019 · Interspeech · 23 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal