<progress id="hpfzt"><pre id="hpfzt"></pre></progress>
        <ruby id="hpfzt"></ruby>
        <big id="hpfzt"><p id="hpfzt"></p></big>

        <progress id="hpfzt"></progress>

        <big id="hpfzt"><pre id="hpfzt"></pre></big>

        <i id="hpfzt"></i>

            <strike id="hpfzt"><video id="hpfzt"><ins id="hpfzt"></ins></video></strike>
            <dl id="hpfzt"></dl>
                Mirror operated in collaboration with local support

                Audio and Speech Processing

                Authors and titles for recent submissions

                [ total of 131 entries: 1-25 | 26-50 | 51-75 | 76-100 | ... | 126-131 ]
                [ showing 25 entries per page: fewer | more | all ]

                Mon, 25 May 2020

                [1]  arXiv:2005.11262 [pdf, other]
                Title: LibriMix: An Open-Source Dataset for Generalizable Speech Separation
                Comments: submitted to INTERSPEECH 2020
                Subjects: Audio and Speech Processing (eess.AS)
                [2]  arXiv:2005.11258 [pdf, other]
                Title: LEAP Submission to CHiME-6 ASR Challenge}
                Subjects: Audio and Speech Processing (eess.AS)
                [3]  arXiv:2005.11172 [pdf, other]
                Title: Deep Reinforcement Learning with Pre-training for Time-efficient Training of Automatic Speech Recognition
                Comments: arXiv admin note: substantial text overlap with arXiv:1910.11256
                Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
                [4]  arXiv:2005.11138 [pdf, other]
                Title: TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids
                Comments: First four authors contributed equally. For audio samples, see this https URL
                Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD); Machine Learning (stat.ML)
                [5]  arXiv:2005.11129 [pdf, other]
                Title: Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
                Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
                [6]  arXiv:2005.11004 [pdf, other]
                Title: NAUTILUS: a Versatile Voice Cloning System
                Comments: Submitted to The IEEE/ACM Transactions on Audio, Speech, and Language Processing
                Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
                [7]  arXiv:2005.11185 (cross-list from cs.CL) [pdf, other]
                Title: Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection
                Subjects: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
                [8]  arXiv:2005.11184 (cross-list from cs.CL) [pdf, other]
                Title: End-to-end Named Entity Recognition from English Speech
                Comments: submitted to Interspeech-2020
                Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)

                Fri, 22 May 2020 (showing first 17 of 19 entries)

                [9]  arXiv:2005.10803 [pdf, other]
                Title: Formant Tracking Using Dilated Convolutional Networks Through Dense Connection with Gating Mechanism
                Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
                [10]  arXiv:2005.10627 [pdf, other]
                Title: Dynamic Sparsity Neural Networks for Automatic Speech Recognition
                Comments: Submitted to INTERSPEECH 2020
                Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD)
                [11]  arXiv:2005.10548 [pdf, other]
                Title: Coswara -- A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis
                Comments: A description of Coswara dataset to evaluate COVID-19 diagnosis using respiratory sounds
                Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
                [12]  arXiv:2005.10479 [pdf, other]
                Title: End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming
                Comments: 5 pages, 3 figures, conference
                Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
                [13]  arXiv:2005.10470 [pdf, other]
                Title: Multistream CNN for Robust Acoustic Modeling
                Comments: Submitted to Interspeech 2020
                Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
                [14]  arXiv:2005.10469 [pdf, other]
                Title: ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition
                Comments: Submitted to Interspeech 2020
                Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
                [15]  arXiv:2005.10456 [pdf]
                Title: Pitchtron: Towards audiobook generation from ordinary people's voices
                Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
                [16]  arXiv:2005.10441 [pdf, other]
                Title: Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario
                Comments: in preparation for Neural Networks journal Special issue on Advances in Deep Learning Based Speech Processing
                Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)
                [17]  arXiv:2005.10407 [pdf, other]
                Title: Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning
                Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)
                [18]  arXiv:2005.10406 [pdf, other]
                Title: Training Keyword Spotting Models on Non-IID Data with Federated Learning
                Comments: Submitted to Interspeech 2020
                Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD)
                [19]  arXiv:2005.10393 [pdf, other]
                Title: Spoofing Attack Detection using the Non-linear Fusion of Sub-band Classifiers
                Comments: Submitted to Interspeech 2020 conference, 5 pages
                Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
                [20]  arXiv:2005.10390 [pdf, other]
                Title: Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis
                Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD); Machine Learning (stat.ML)
                [21]  arXiv:2005.10386 [pdf, other]
                Title: End-to-End Multi-Look Keyword Spotting
                Comments: Submitted to Interspeech2020
                Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
                [22]  arXiv:2005.10294 [pdf, other]
                Title: Towards Cover Song Detection with Siamese Convolutional Neural Networks
                Authors: Marko Stamenovic
                Comments: Code available at this https URL
                Journal-ref: Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, PMLR 80, 2018
                Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD); Machine Learning (stat.ML)
                [23]  arXiv:2005.10637 (cross-list from cs.SD) [pdf, other]
                Title: Inaudible Adversarial Perturbations for Targeted Attack in Speaker Recognition
                Comments: 5 pages, 2 figures
                Subjects: Sound (cs.SD); Audio and Speech Processing (eess.AS)
                [24]  arXiv:2005.10539 (cross-list from cs.SD) [pdf, other]
                Title: An approach to Beethoven's 10th Symphony
                Subjects: Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
                [25]  arXiv:2005.10480 (cross-list from cs.SD) [pdf, other]
                Title: Understanding the Importance of Heart Sound Segmentation for Heart Anomaly Detection
                Subjects: Sound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS); Quantitative Methods (q-bio.QM)
                [ total of 131 entries: 1-25 | 26-50 | 51-75 | 76-100 | ... | 126-131 ]
                [ showing 25 entries per page: fewer | more | all ]
                ƴϷ