Mirror operated in collaboration with local support

Audio and Speech Processing

Authors and titles for recent submissions

[ total of 129 entries: 1-25 | 26-50 | 51-75 | 76-100 | ... | 126-129 ]
[ showing 25 entries per page: fewer | more | all ]

Thu, 21 May 2020

[1]  arXiv:2005.10113 [pdf, other]
Title: A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition
Comments: 4 pages, 2 figures
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
[2]  arXiv:2005.10089 [pdf, other]
Title: Investigation of Large-Margin Softmax in Neural Language Modeling
Comments: submitted to INTERSPEECH2020
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
[3]  arXiv:2005.10049 [pdf, ps, other]
Title: Early Stage LM Integration Using Local and Global Log-Linear Combination
Comments: Submitted to Interspeech 2020
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD); Machine Learning (stat.ML)
[4]  arXiv:2005.09986 [pdf, other]
Title: Evaluating Features and Metrics for High-Quality Simulation of Early Vocal Learning of Vowels
Comments: Submitted to INTERSPEECH 2020
Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
[5]  arXiv:2005.09940 [pdf, other]
Title: Relative Positional Encoding for Speech Recognition and Direct Translation
Comments: Submitted to Interspeech 2020
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
[6]  arXiv:2005.09921 [pdf, other]
Title: End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
[7]  arXiv:2005.09913 [pdf, other]
Title: Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments
Comments: Submitted to Interspeech 2020
Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
[8]  arXiv:2005.09873 [pdf, other]
Title: Consistent ICA: Determined BSS meets spectrogram consistency
Authors: Kohei Yatabe
Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD); Signal Processing (eess.SP)
[9]  arXiv:2005.09862 [pdf, other]
Title: A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
[10]  arXiv:2005.09843 [pdf, ps, other]
Title: Jointly optimal denoising, dereverberation, and source separation
Comments: Submitted to IEEE/ACM Trans. Audio, Speech, and Language Processing on 12 Feb 2020
Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
[11]  arXiv:2005.09824 [pdf, other]
Title: PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR
Comments: Submtted to Interspeech 2020
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
[12]  arXiv:2005.09768 [pdf, ps, other]
Title: Perceptual similarity between piano notes: Simulations with a template-based perception model
Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
[13]  arXiv:2005.09756 [pdf, other]
Title: Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss Criterion
Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)
[14]  arXiv:2005.09684 [pdf, other]
Title: Exploring Transformers for Large-Scale Speech Recognition
Comments: 5 pages, 1 figure
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
[15]  arXiv:2005.10228 (cross-list from cs.SD) [pdf, other]
Title: Sparsity-based audio declipping methods: overview, new algorithms, and large-scale evaluation
Authors: Clément Gaultier (PANAMA), Srđan Kitić, Rémi Gribonval (PANAMA, DANTE), Nancy Bertin (PANAMA)
Comments: arXiv admin note: text overlap with arXiv:1711.11259
Subjects: Sound (cs.SD); Audio and Speech Processing (eess.AS); Signal Processing (eess.SP)
[16]  arXiv:2005.09966 (cross-list from cs.SD) [pdf, other]
Title: SADDEL: Joint Speech Separation and Denoising Model based on Multitask Learning
Comments: The two first authors made equal contributions
Subjects: Sound (cs.SD); Audio and Speech Processing (eess.AS)
[17]  arXiv:2005.09834 (cross-list from cs.HC) [pdf, other]
Title: Exploring Recurrent, Memory and Attention Based Architectures for Scoring Interactional Aspects of Human-Machine Text Dialog
Subjects: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)

Wed, 20 May 2020 (showing first 8 of 25 entries)

[18]  arXiv:2005.09629 [pdf, other]
Title: Improved Noisy Student Training for Automatic Speech Recognition
Comments: 5 pages, 5 figures, 4 tables. Submitted to Interspeech 2020
Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG)
[19]  arXiv:2005.09587 [pdf, other]
Title: GEV Beamforming Supported by DOA-based Masks Generated on Pairs of Microphones
Subjects: Audio and Speech Processing (eess.AS)
[20]  arXiv:2005.09463 [pdf, other]
Title: Learning Joint Articulatory-Acoustic Representations with Normalizing Flows
Comments: 5 pages, 4 figures
Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD); Machine Learning (stat.ML)
[21]  arXiv:2005.09409 [pdf, other]
Title: Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge
Comments: 5 pages, 3 figures, 2 tables
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL)
[22]  arXiv:2005.09394 [pdf, other]
Title: Enhancing Monotonic Multihead Attention for Streaming ASR
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD)
[23]  arXiv:2005.09336 [pdf, ps, other]
Title: Investigations on Phoneme-Based End-To-End Speech Recognition
Comments: submission to Interspeech 2020
Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
[24]  arXiv:2005.09319 [pdf, other]
Title: A New Training Pipeline for an Improved Neural Transducer
Comments: submission to Interspeech 2020
Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Machine Learning (stat.ML)
[25]  arXiv:2005.09297 [pdf, other]
Title: Should we hard-code the recurrence concept or learn it instead ? Exploring the Transformer architecture for Audio-Visual Speech Recognition
Comments: Submitted to INTERSPEECH 2020
Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG)
[ total of 129 entries: 1-25 | 26-50 | 51-75 | 76-100 | ... | 126-129 ]
[ showing 25 entries per page: fewer | more | all ]
Ϸ