@article{bb335100, AUTHOR = "Savchenko, A.V. and Savchenko, L.V.", TITLE = "Towards the creation of reliable voice control system based on a fuzzy approach", JOURNAL = PRL, VOLUME = "65", YEAR = "2015", NUMBER = "1", PAGES = "145-151", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329398"} @article{bb335101, AUTHOR = "Suh, Y.J. and Kim, H.", TITLE = "Probabilistic Class Histogram Equalization Based on Posterior Mean Estimation for Robust Speech Recognition", JOURNAL = SPLetters, VOLUME = "22", YEAR = "2015", NUMBER = "12", MONTH = "December", PAGES = "2421-2424", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329399"} @article{bb335102, AUTHOR = "Wang, X.Y. and Yamamoto, S.", TITLE = "Speech Recognition of English by Japanese Using Lexicon Represented by Multiple Reduced Phoneme Sets", JOURNAL = IEICE, VOLUME = "E98-D", YEAR = "2015", NUMBER = "12", MONTH = "December", PAGES = "2271-2279", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329400"} @article{bb335103, AUTHOR = "Tohidypour, H.R. and Banitalebi Dehkordi, A.", TITLE = "Speech frame recognition based on less shift sensitive wavelet filter banks", JOURNAL = SIViP, VOLUME = "10", YEAR = "2016", NUMBER = "4", MONTH = "April", PAGES = "633-637", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329401"} @article{bb335104, AUTHOR = "Chung, Y.J.", TITLE = "Vector Taylor series based model adaptation using noisy speech trained hidden Markov models", JOURNAL = PRL, VOLUME = "75", YEAR = "2016", NUMBER = "1", PAGES = "36-40", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329402"} @article{bb335105, AUTHOR = "Ansari, J.A. and Sathyamurthy, A. and Balasubramanyam, R.", TITLE = "An Open Voice Command Interface Kit", JOURNAL = HMS, VOLUME = "46", YEAR = "2016", NUMBER = "3", MONTH = "June", PAGES = "467-473", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329403"} @article{bb335106, AUTHOR = "Cho, B.J. and Kwon, H. and Cho, J.W. and Kim, C. and Stern, R.M. and Park, H.M.", TITLE = "A Subband-Based Stationary-Component Suppression Method Using Harmonics and Power Ratio for Reverberant Speech Recognition", JOURNAL = SPLetters, VOLUME = "23", YEAR = "2016", NUMBER = "6", MONTH = "June", PAGES = "780-784", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329404"} @article{bb335107, AUTHOR = "Ren, H. and Yan, Y.", TITLE = "Structural Optimization and Online Evolutionary Learning for Spoken Dialog Management", JOURNAL = SPLetters, VOLUME = "23", YEAR = "2016", NUMBER = "7", MONTH = "July", PAGES = "1013-1017", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329405"} @article{bb335108, AUTHOR = "Khoubrouy, S.A. and Hansen, J.H.L.", TITLE = "Microphone Array Processing Strategies for Distant-Based Automatic Speech Recognition", JOURNAL = SPLetters, VOLUME = "23", YEAR = "2016", NUMBER = "10", MONTH = "October", PAGES = "1344-1348", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329406"} @article{bb335109, AUTHOR = "Lamberti, F. and Manuri, F. and Paravati, G. and Piumatti, G. and Sanna, A.", TITLE = "Using Semantics to Automatically Generate Speech Interfaces for Wearable Virtual and Augmented Reality Applications", JOURNAL = HMS, VOLUME = "47", YEAR = "2017", NUMBER = "1", MONTH = "February", PAGES = "152-164", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329407"} @article{bb335110, AUTHOR = "Ganapathy, S.", TITLE = "Multivariate Autoregressive Spectrogram Modeling for Noisy Speech Recognition", JOURNAL = SPLetters, VOLUME = "24", YEAR = "2017", NUMBER = "9", MONTH = "September", PAGES = "1373-1377", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329408"} @article{bb335111, AUTHOR = "Shahnawazuddin, S. and Adiga, N. and Kathania, H.K.", TITLE = "Effect of Prosody Modification on Children's ASR", JOURNAL = SPLetters, VOLUME = "24", YEAR = "2017", NUMBER = "11", MONTH = "November", PAGES = "1749-1753", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329409"} @article{bb335112, AUTHOR = "Monroe, D.", TITLE = "Digital Hearing", JOURNAL = CACM, VOLUME = "60", YEAR = "2017", NUMBER = "10", MONTH = "October", PAGES = "18-20", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329410"} @article{bb335113, AUTHOR = "Kim, J. and Hahn, M.", TITLE = "Voice Activity Detection Using an Adaptive Context Attention Model", JOURNAL = SPLetters, VOLUME = "25", YEAR = "2018", NUMBER = "8", MONTH = "August", PAGES = "1181-1185", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329411"} @article{bb335114, AUTHOR = "Edwards, J.", TITLE = "Something to Talk About: Signal Processing in Speech and Audiology Research: Promising Investigations Explore New Opportunities in Human Communication", JOURNAL = SPMag, VOLUME = "35", YEAR = "2018", NUMBER = "6", MONTH = "November", PAGES = "8-12", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329412"} @article{bb335115, AUTHOR = "Baltrusaitis, T. and Ahuja, C. and Morency, L.P.", TITLE = "Multimodal Machine Learning: A Survey and Taxonomy", JOURNAL = PAMI, VOLUME = "41", YEAR = "2019", NUMBER = "2", MONTH = "February", PAGES = "423-443", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329413"} @article{bb335116, AUTHOR = "Shin, Y. and Yoo, K.M. and Lee, S.", TITLE = "Utterance Generation With Variational Auto-Encoder for Slot Filling in Spoken Language Understanding", JOURNAL = SPLetters, VOLUME = "26", YEAR = "2019", NUMBER = "3", MONTH = "March", PAGES = "505-509", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329414"} @article{bb335117, AUTHOR = "Yang, B.H. and Yao, Z.P. and Lu, H. and Zhou, Y.Q. and Xu, J.K.", TITLE = "In-classroom learning analytics based on student behavior, topic and teaching characteristic mining", JOURNAL = PRL, VOLUME = "129", YEAR = "2020", PAGES = "224-231", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329415"} @article{bb335118, AUTHOR = "Chandrakala, S. and Jayalakshmi, S.L.", TITLE = "Generative Model Driven Representation Learning in a Hybrid Framework for Environmental Audio Scene and Sound Event Recognition", JOURNAL = MultMed, VOLUME = "22", YEAR = "2020", NUMBER = "1", MONTH = "January", PAGES = "3-14", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329416"} @article{bb335119, AUTHOR = "Yadav, I.C. and Pradhan, G.", TITLE = "Significance of Pitch-Based Spectral Normalization for Children's Speech Recognition", JOURNAL = SPLetters, VOLUME = "26", YEAR = "2019", NUMBER = "12", MONTH = "December", PAGES = "1822-1826", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329417"} @article{bb335120, AUTHOR = "Shahnawazuddin, S. and Adiga, N. and Kathania, H.K. and Sai, B.T.", TITLE = "Creating speaker independent ASR system through prosody modification based data augmentation", JOURNAL = PRL, VOLUME = "131", YEAR = "2020", PAGES = "213-218", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329418"} @article{bb335121, AUTHOR = "Park, T.J. and Han, K.J. and Kumar, M. and Narayanan, S.", TITLE = "Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap", JOURNAL = SPLetters, VOLUME = "27", YEAR = "2020", PAGES = "381-385", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329419"} @article{bb335122, AUTHOR = "Deb, S. and Dandapat, S. and Krajewski, J.", TITLE = "Analysis and Classification of Cold Speech Using Variational Mode Decomposition", JOURNAL = AffCom, VOLUME = "11", YEAR = "2020", NUMBER = "2", MONTH = "April", PAGES = "296-307", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329420"} @article{bb335123, AUTHOR = "Sanchez Junquera, J. and Villasenor Pineda, L. and Montes y Gomez, M. and Rosso, P. and Stamatatos, E.", TITLE = "Masking domain-specific information for cross-domain deception detection", JOURNAL = PRL, VOLUME = "135", YEAR = "2020", PAGES = "122-130", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329421"} @inproceedings{bb335124, AUTHOR = "Rill Garcia, R. and Villasenor Pineda, L. and Reyes Meza, V. and Escalante, H.J.", TITLE = "From Text to Speech: A Multimodal Cross-Domain Approach for Deception Detection", BOOKTITLE = MIPPSNA18, YEAR = "2018", PAGES = "164-177", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329422"} @article{bb335125, AUTHOR = "Lim, H. and Kim, Y. and Kim, H.", TITLE = "Cross-Informed Domain Adversarial Training for Noise-Robust Wake-Up Word Detection", JOURNAL = SPLetters, VOLUME = "27", YEAR = "2020", PAGES = "1769-1773", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329423"} @article{bb335126, AUTHOR = "Zhao, L. and Zhang, A. and Liu, Y. and Fei, H.", TITLE = "Encoding multi-granularity structural information for joint Chinese word segmentation and POS tagging", JOURNAL = PRL, VOLUME = "138", YEAR = "2020", PAGES = "163-169", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329424"} @article{bb335127, AUTHOR = "Hsiao, R. and Can, D. and Ng, T. and Travadi, R. and Ghoshal, A.", TITLE = "Online Automatic Speech Recognition With Listen, Attend and Spell Model", JOURNAL = SPLetters, VOLUME = "27", YEAR = "2020", PAGES = "1889-1893", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329425"} @article{bb335128, AUTHOR = "Bang, J. and Han, S. and Lee, J.H.", TITLE = "Listening-oriented response generation by exploiting user responses", JOURNAL = PRL, VOLUME = "140", YEAR = "2020", PAGES = "230-237", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329426"} @article{bb335129, AUTHOR = "Zhou, J.T.Y. and Zhang, H. and Jin, D. and Peng, X.", TITLE = "Dual Adversarial Transfer for Sequence Labeling", JOURNAL = PAMI, VOLUME = "43", YEAR = "2021", NUMBER = "2", MONTH = "February", PAGES = "434-446", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329427"} @article{bb335130, AUTHOR = "Qiu, J.Y. and Wang, X.C. and Fua, P. and Tao, D.C.", TITLE = "Matching Seqlets: An Unsupervised Approach for Locality Preserving Sequence Matching", JOURNAL = PAMI, VOLUME = "43", YEAR = "2021", NUMBER = "2", MONTH = "February", PAGES = "745-752", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329428"} @article{bb335131, AUTHOR = "Chen, N. and Watanabe, S. and Villalba, J. and Zelasko, P. and Dehak, N.", TITLE = "Non-Autoregressive Transformer for Speech Recognition", JOURNAL = SPLetters, VOLUME = "28", YEAR = "2021", PAGES = "121-125", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329429"} @article{bb335132, AUTHOR = "Haeb Umbach, R. and Heymann, J. and Drude, L. and Watanabe, S. and Delcroix, M. and Nakatani, T.", TITLE = "Far-Field Automatic Speech Recognition", JOURNAL = PIEEE, VOLUME = "109", YEAR = "2021", NUMBER = "2", MONTH = "February", PAGES = "124-148", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329430"} @article{bb335133, AUTHOR = "Fritsch, J. and Magimai Doss, M.", TITLE = "Utterance Verification-Based Dysarthric Speech Intelligibility Assessment Using Phonetic Posterior Features", JOURNAL = SPLetters, VOLUME = "28", YEAR = "2021", PAGES = "224-228", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329431"} @article{bb335134, AUTHOR = "Lu, L. and Kanda, N. and Li, J. and Gong, Y.F.", TITLE = "Streaming End-to-End Multi-Talker Speech Recognition", JOURNAL = SPLetters, VOLUME = "28", YEAR = "2021", PAGES = "803-807", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329432"} @article{bb335135, AUTHOR = "Yi, C. and Zhou, S.Y. and Xu, B.", TITLE = "Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-Resource Speech Recognition", JOURNAL = SPLetters, VOLUME = "28", YEAR = "2021", PAGES = "788-792", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329433"} @article{bb335136, AUTHOR = "Xu, P. and Huang, Y. and Yuan, T. and Xiang, T. and Hospedales, T.M. and Song, Y.Z. and Wang, L.", TITLE = "On Learning Semantic Representations for Large-Scale Abstract Sketches", JOURNAL = CirSysVideo, VOLUME = "31", YEAR = "2021", NUMBER = "9", MONTH = "September", PAGES = "3366-3379", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329434"} @article{bb335137, AUTHOR = "Kim, J. and Lee, Y.", TITLE = "Improving End-to-End Contextual Speech Recognition via a Word-Matching Algorithm With Backward Search", JOURNAL = SPLetters, VOLUME = "28", YEAR = "2021", PAGES = "2087-2091", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329435"} @article{bb335138, AUTHOR = "Zhu, S. and Zhang, Y. and He, K. and Zhao, L.", TITLE = "Acoustic Word Embedding Based on Multi-Head Attention Quadruplet Network", JOURNAL = SPLetters, VOLUME = "29", YEAR = "2022", PAGES = "184-188", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329436"} @article{bb335139, AUTHOR = "Tiwari, R. and Sharma, V. and Sahoo, R.C.", TITLE = "Isolated spoken word recognition using packed-MFCC on padded-voice signal for unscripted languages", JOURNAL = IJCVR, VOLUME = "12", YEAR = "2022", NUMBER = "2", PAGES = "120-140", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329437"} @article{bb335140, AUTHOR = "Tian, Z.K. and Yi, J. and Tao, J.H. and Zhang, S. and Wen, Z.Q.", TITLE = "Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition", JOURNAL = SPLetters, VOLUME = "29", YEAR = "2022", PAGES = "762-766", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329438"} @article{bb335141, AUTHOR = "Xiao, F.Y. and Guan, J. and Lan, H.Y. and Zhu, Q. and Wang, W.W.", TITLE = "Local Information Assisted Attention-Free Decoder for Audio Captioning", JOURNAL = SPLetters, VOLUME = "29", YEAR = "2022", PAGES = "1604-1608", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329439"} @article{bb335142, AUTHOR = "de Souza, D.B. and Bakri, K.J. and de Souza Ferreira, F. and Inacio, J.", TITLE = "Multitaper-Mel Spectrograms for Keyword Spotting", JOURNAL = SPLetters, VOLUME = "29", YEAR = "2022", PAGES = "2028-2032", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329440"} @article{bb335143, AUTHOR = "Perochon, S.", TITLE = "A Presentation and Short Discussion of rVAD-fast, a Fast Voice Activity Detector", JOURNAL = IPOL, VOLUME = "12", YEAR = "2022", PAGES = "404-419", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329441"} @article{bb335144, AUTHOR = "Huang, H.J. and Huang, P.J. and Zhu, Z.B. and Li, J. and Lin, P.", TITLE = "CLID: A Chunk-Level Intent Detection Framework for Multiple Intent Spoken Language Understanding", JOURNAL = SPLetters, VOLUME = "29", YEAR = "2022", PAGES = "2123-2127", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329442"} @article{bb335145, AUTHOR = "Du, X. and Pun, C.M.", TITLE = "Robust Audio Patch Attacks Using Physical Sample Simulation and Adversarial Patch Noise Generation", JOURNAL = MultMed, VOLUME = "24", YEAR = "2022", PAGES = "4381-4393", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329443"} @article{bb335146, AUTHOR = "Kim, H. and Park, J. and Lee, J.W.", TITLE = "Generating Transferable Adversarial Examples for Speech Classification", JOURNAL = PR, VOLUME = "137", YEAR = "2023", PAGES = "109286", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329444"} @article{bb335147, AUTHOR = "Wei, G.Y. and Duan, Z.K. and Li, S. and Yu, X.M. and Yang, G.G.", TITLE = "LFEformer: Local Feature Enhancement Using Sliding Window With Deformability for Automatic Speech Recognition", JOURNAL = SPLetters, VOLUME = "30", YEAR = "2023", PAGES = "180-184", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329445"} @article{bb335148, AUTHOR = "Xiao, F.Y. and Guan, J. and Zhu, Q. and Wang, W.W.", TITLE = "Graph Attention for Automated Audio Captioning", JOURNAL = SPLetters, VOLUME = "30", YEAR = "2023", PAGES = "413-417", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329446"} @article{bb335149, AUTHOR = "Chang, C.M. and Lee, C.C.", TITLE = "Learning Enhanced Acoustic Latent Representation for Small Scale Affective Corpus with Adversarial Cross Corpora Integration", JOURNAL = AffCom, VOLUME = "14", YEAR = "2023", NUMBER = "2", MONTH = "April", PAGES = "1308-1321", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329447"} @article{bb335150, AUTHOR = "Qu, H.L. and Su, X.D. and Wang, Y. and Hao, X. and Gao, G.L.", TITLE = "Noise-Separated Adaptive Feature Distillation for Robust Speech Recognition", JOURNAL = SPLetters, VOLUME = "30", YEAR = "2023", PAGES = "763-767", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329448"} @article{bb335151, AUTHOR = "Nga, C.H. and Vu, D.Q. and Luong, H.H. and Huang, C.L. and Wang, J.C.", TITLE = "Cyclic Transfer Learning for Mandarin-English Code-Switching Speech Recognition", JOURNAL = SPLetters, VOLUME = "30", YEAR = "2023", PAGES = "1387-1391", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329449"} @article{bb335152, AUTHOR = "Dong, F. and Qian, Y.Y. and Wang, T.L. and Liu, P. and Cao, J.W.", TITLE = "A Transformer-Based End-to-End Automatic Speech Recognition Algorithm", JOURNAL = SPLetters, VOLUME = "30", YEAR = "2023", PAGES = "1592-1596", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329450"} @article{bb335153, AUTHOR = "Fan, P. and Shan, C. and Sun, S. and Yang, Q. and Zhang, J.W.", TITLE = "Key Frame Mechanism for Efficient Conformer Based End-to-End Speech Recognition", JOURNAL = SPLetters, VOLUME = "30", YEAR = "2023", PAGES = "1612-1616", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329451"} @article{bb335154, AUTHOR = "Mahmoudi, H. and Camboim, S. and Brovelli, M.A.", TITLE = "Development of a Voice Virtual Assistant for the Geospatial Data Visualization Application on the Web", JOURNAL = IJGI, VOLUME = "12", YEAR = "2023", NUMBER = "11", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329452"} @article{bb335155, AUTHOR = "Vitolo, P. and Liguori, R. and di Benedetto, L. and Rubino, A. and Licciardo, G.D.", TITLE = "Automatic Audio Feature Extraction for Keyword Spotting", JOURNAL = SPLetters, VOLUME = "31", YEAR = "2024", PAGES = "161-165", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329453"} @article{bb335156, AUTHOR = "Li, J. and Duan, Z.K. and Li, S. and Yu, X. and Yang, G.", TITLE = "ESAformer: Enhanced Self-Attention for Automatic Speech Recognition", JOURNAL = SPLetters, VOLUME = "31", YEAR = "2024", PAGES = "471-475", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329454"} @article{bb335157, AUTHOR = "Nie, W.Z. and Bao, Y. and Zhao, Y. and Liu, A.", TITLE = "Long Dialogue Emotion Detection Based on Commonsense Knowledge Graph Guidance", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "514-528", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329455"} @article{bb335158, AUTHOR = "Sun, T.L. and Chen, H.N. and Hu, G.S. and He, L.H. and Zhao, C.R.", TITLE = "Explainability of Speech Recognition Transformers via Gradient-Based Attention Visualization", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "1395-1406", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329456"} @article{bb335159, AUTHOR = "Jacobs, C. and Kamper, H.", TITLE = "Leveraging Multilingual Transfer for Unsupervised Semantic Acoustic Word Embeddings", JOURNAL = SPLetters, VOLUME = "31", YEAR = "2024", PAGES = "311-315", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329457"} @article{bb335160, AUTHOR = "Wang, F.Y. and Xu, B. and Xu, B.", TITLE = "SSCFormer: Push the Limit of Chunk-Wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution", JOURNAL = SPLetters, VOLUME = "31", YEAR = "2024", PAGES = "421-425", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329458"} @article{bb335161, AUTHOR = "Fan, R. and Shankar, N.B. and Alwan, A.", TITLE = "UniEnc-CASSNAT: An Encoder-Only Non-Autoregressive ASR for Speech SSL Models", JOURNAL = SPLetters, VOLUME = "31", YEAR = "2024", PAGES = "711-715", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329459"} @article{bb335162, AUTHOR = "Xing, B. and Tsang, I.W.", TITLE = "Co-Guiding for Multi-Intent Spoken Language Understanding", JOURNAL = PAMI, VOLUME = "46", YEAR = "2024", NUMBER = "5", MONTH = "May", PAGES = "2965-2980", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329460"} @article{bb335163, AUTHOR = "Hwang, K. and Jung, I.H. and Lee, J.M.", TITLE = "An implementation of searchable video player", JOURNAL = IJCVR, VOLUME = "14", YEAR = "2024", NUMBER = "3", PAGES = "325-337", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329461"} @article{bb335164, AUTHOR = "Lin, J. and Ge, M. and Wang, W. and Li, H.Z. and Feng, M.L.", TITLE = "Selective HuBERT: Self-Supervised Pre-Training for Target Speaker in Clean and Mixture Speech", JOURNAL = SPLetters, VOLUME = "31", YEAR = "2024", PAGES = "1014-1018", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329462"} @inproceedings{bb335165, AUTHOR = "Feng, Y. and Liu, Z.Y. and Luo, S. and Ling, Y. and Dong, S. and Wang, S.Y. and Ferry, B.", TITLE = "Noise-Free Audio Signal Processing in Noisy Environment: A Hardware and Algorithm Solution", BOOKTITLE = VAQuality24, YEAR = "2024", PAGES = "368-373", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329463"} @inproceedings{bb335166, AUTHOR = "Ng, H.W. and Guan, C.T.", TITLE = "Efficient Representation Learning for Inner Speech Domain Generalization", BOOKTITLE = CAIP23, YEAR = "2023", PAGES = "I:131-141", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329464"} @inproceedings{bb335167, AUTHOR = "Oneata, D. and Cucu, H.", TITLE = "Improving Multimodal Speech Recognition by Data Augmentation and Speech Representations", BOOKTITLE = MULA22, YEAR = "2022", PAGES = "4578-4587", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329465"} @inproceedings{bb335168, AUTHOR = "Tapia, L.S. and Gomez, A. and Esparza, M. and Jatla, V. and Pattichis, M. and Celedon Pattichis, S. and Lopez Leiva, C.", TITLE = "Bilingual Speech Recognition by Estimating Speaker Geometry from Video Data", BOOKTITLE = CAIP21, YEAR = "2021", PAGES = "I:79-89", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329466"} @inproceedings{bb335169, AUTHOR = "Qiao, F.C. and Peng, X.", TITLE = "Uncertainty-guided Model Generalization to Unseen Domains", BOOKTITLE = CVPR21, YEAR = "2021", PAGES = "6786-6796", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329467"} @inproceedings{bb335170, AUTHOR = "Ngantcha, P. and Amith, M. and Tao, C. and Roberts, K.", TITLE = "Patient-Provider Communication Training Models for Interactive Speech Devices", BOOKTITLE = DHM21, YEAR = "2021", PAGES = "I:250-268", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329468"} @inproceedings{bb335171, AUTHOR = "Wu, Y.C. and Liao, W.H.", TITLE = "Toward Text-independent Cross-lingual Speaker Recognition Using English-Mandarin-Taiwanese Dataset", BOOKTITLE = ICPR21, YEAR = "2021", PAGES = "8515-8522", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329469"} @inproceedings{bb335172, AUTHOR = "Chen, Y. and Ma, Y. and Ko, T. and Wang, J.P. and Li, Q.", TITLE = "MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization", BOOKTITLE = ICPR21, YEAR = "2021", PAGES = "407-414", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329470"} @inproceedings{bb335173, AUTHOR = "Zhou, L.X. and Zhang, J.", TITLE = "From Bottom to Top: A Coordinated Feature Representation Method for Speech Recognition", BOOKTITLE = MMDLCA20, YEAR = "2020", PAGES = "396-403", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329471"} @inproceedings{bb335174, AUTHOR = "Zhao, J. and Parry, C.J. and dos Anjos, R. and Anslow, C. and Rhee, T.", TITLE = "Voice Interaction for Augmented Reality Navigation Interfaces with Natural Language Understanding", BOOKTITLE = IVCNZ20, YEAR = "2020", PAGES = "1-6", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329472"} @inproceedings{bb335175, AUTHOR = "Ezzine, A. and Satori, H. and Hamidi, M. and Satori, K.", TITLE = "Moroccan Dialect Speech Recognition System Based on CMU SphinxTools", BOOKTITLE = ISCV20, YEAR = "2020", PAGES = "1-5", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329473"} @inproceedings{bb335176, AUTHOR = "ABAKARIM, F. and ABENAOU, A.", TITLE = "Amazigh isolated word speech recognition system using the Adaptive Orthogonal Transform Method.", BOOKTITLE = ISCV20, YEAR = "2020", PAGES = "1-6", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329474"} @inproceedings{bb335177, AUTHOR = "Perez, A.F. and Sanguineti, V. and Morerio, P. and Murino, V.", TITLE = "Audio-Visual Model Distillation Using Acoustic Images", BOOKTITLE = WACV20, YEAR = "2020", PAGES = "2843-2852", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329475"} @inproceedings{bb335178, AUTHOR = "Tapu, R. and Mocanu, B. and Zaharia, T.", TITLE = "Dynamic Subtitles: A Multimodal Video Accessibility Enhancement Dedicated to Deaf and Hearing Impaired Users", BOOKTITLE = ACVR19, YEAR = "2019", PAGES = "2558-2566", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329476"} @inproceedings{bb335179, AUTHOR = "Roberto, A. and Saggese, A. and Vento, M.", TITLE = "A Challenging Voice Dataset for Robotic Applications in Noisy Environments", BOOKTITLE = CAIP19, YEAR = "2019", PAGES = "II:354-364", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329477"} @inproceedings{bb335180, AUTHOR = "Naszadi, K. and Oualil, Y. and Klakow, D.", TITLE = "Image-Sensitive Language Modeling for Automatic Speech Recognition", BOOKTITLE = VL18, YEAR = "2018", PAGES = "IV:173-179", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329478"} @inproceedings{bb335181, AUTHOR = "Gauvain, J. and Lamel, L. and Le, V.B. and Despres, J. and Gauvain, J.L. and Messaoudi, A. and Vieru, B. and Ben Kheder, W.", TITLE = "Challenges in Audio Processing of Terrorist-Related Data", BOOKTITLE = "MMMod19", YEAR = "2019", PAGES = "II:80-92", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329479"} @inproceedings{bb335182, AUTHOR = "Jorrin, J. and Buera, L.", TITLE = "DANTE Speaker Recognition Module. An Efficient and Robust Automatic Speaker Searching Solution for Terrorism-Related Scenarios", BOOKTITLE = "MMMod19", YEAR = "2019", PAGES = "I:704-715", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329480"} @inproceedings{bb335183, AUTHOR = "Galanopoulos, D. and Mezaris, V.", TITLE = "Temporal Lecture Video Fragmentation Using Word Embeddings", BOOKTITLE = "MMMod19", YEAR = "2019", PAGES = "II:254-265", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329481"} @inproceedings{bb335184, AUTHOR = "Shahin, M. and Ji, J.X. and Ahmed, B.", TITLE = "One-Class SVMs Based Pronunciation Verification Approach", BOOKTITLE = ICPR18, YEAR = "2018", PAGES = "2881-2886", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329482"} @inproceedings{bb335185, AUTHOR = "Mukherjee, H. and Obaidullah, S.M. and Phadikar, S. and Roy, K.", TITLE = "A Dravidian Language Identification System", BOOKTITLE = ICPR18, YEAR = "2018", PAGES = "2654-2657", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329483"} @inproceedings{bb335186, AUTHOR = "Galiotou, E. and Karanikolas, N. and Ralli, A.", TITLE = "Preservation and Management of Greek Dialectal Data", BOOKTITLE = EuroMed18, YEAR = "2018", PAGES = "I:752-761", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329484"} @inproceedings{bb335187, AUTHOR = "Li, R. and Yu, J.", TITLE = "Multimodal 3D visible articulation system for syllable based Mandarin Chinese training", BOOKTITLE = VCIP17, YEAR = "2017", PAGES = "1-4", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329485"} @inproceedings{bb335188, AUTHOR = "Le, N. and Odobez, J.M.", TITLE = "Improving Speaker Turn Embedding by Crossmodal Transfer Learning from Face Embedding", BOOKTITLE = CVAVM17, YEAR = "2017", PAGES = "428-437", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329486"} @inproceedings{bb335189, AUTHOR = "Arandjelovic, R. and Zisserman, A.", TITLE = "Look, Listen and Learn", BOOKTITLE = ICCV17, YEAR = "2017", PAGES = "609-617", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329487"} @inproceedings{bb335190, AUTHOR = "Muniandy, T. and Alvar, T.A. and Boon, C.J.", TITLE = "Mandarin Language Learning System for Nasal Voice User", BOOKTITLE = IVIC17, YEAR = "2017", PAGES = "376-388", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329488"} @inproceedings{bb335191, AUTHOR = "Madhavi, M.C. and Patil, H.A. and Bhendawade, N.", TITLE = "Spoken Keyword Retrieval Using Source and System Features", BOOKTITLE = PReMI17, YEAR = "2017", PAGES = "333-341", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329489"} @inproceedings{bb335192, AUTHOR = "Addarrazi, I. and Satori, H. and Satori, K.", TITLE = "Amazigh audiovisual speech recognition system design", BOOKTITLE = ISCV17, YEAR = "2017", PAGES = "1-5", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329490"} @inproceedings{bb335193, AUTHOR = "Wu, C. and Ng, R.W.M. and Torralba, O.S. and Hain, T.", TITLE = "Analysing acoustic model changes for active learning in automatic speech recognition", BOOKTITLE = WSSIP17, YEAR = "2017", PAGES = "1-5", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329491"} @inproceedings{bb335194, AUTHOR = "Kacprzak, S.", TITLE = "Spoken language clustering in the i-vectors space", BOOKTITLE = WSSIP17, YEAR = "2017", PAGES = "1-5", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329492"} @inproceedings{bb335195, AUTHOR = "Pironkov, G. and Dupont, S. and Dutoit, T.", TITLE = "Speaker-aware Multi-Task Learning for automatic speech recognition", BOOKTITLE = ICPR16, YEAR = "2016", PAGES = "2900-2905", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329493"} @inproceedings{bb335196, AUTHOR = "Zhao, Y. and Zhao, R. and Wang, X.Y. and Ji, Q.", TITLE = "Multilingual articulatory features augmentation learning", BOOKTITLE = ICPR16, YEAR = "2016", PAGES = "2895-2899", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329494"} @inproceedings{bb335197, AUTHOR = "Ogawa, T. and Mallidi, S.H. and Dupoux, E. and Cohen, J. and Feldman, N.H. and Hermansky, H.", TITLE = "A new efficient measure for accuracy prediction and its application to multistream-based unsupervised adaptation", BOOKTITLE = ICPR16, YEAR = "2016", PAGES = "2222-2227", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329495"} @inproceedings{bb335198, AUTHOR = "Mzah, Y. and Ahfir, M. and Jaidane, M.", TITLE = "Late pre-dereverberation for speech intelligibility enhancement in public address systems", BOOKTITLE = ISIVC16, YEAR = "2016", PAGES = "291-296", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329496"} @inproceedings{bb335199, AUTHOR = "Montalvo, A. and Calvo, J.R.", TITLE = "Discriminative Capacity and Phonetic Information of Bottleneck Features in Speech", BOOKTITLE = CIARP16, YEAR = "2016", PAGES = "134-141", BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT329497"}