{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:29:54Z","timestamp":1782966594997,"version":"3.54.5"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17492-2","type":"journal-article","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T05:01:29Z","timestamp":1699246889000},"page":"50289-50305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Real time speech enhancement using densely connected neural networks and Squeezed temporal convolutional modules"],"prefix":"10.1007","volume":"83","author":[{"given":"Sunny Dayal","family":"Vanambathina","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manaswini","family":"Burra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhumika","family":"Edupalli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eswar Reddy","family":"Vallem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Venkata Sravani","family":"Nellore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,6]]},"reference":[{"key":"17492_CR1","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","volume":"26","author":"D Wang","year":"2018","unstructured":"Wang D, Chen J (2018) Supervised speech separation based on deep learning: An overview. IEEE\/ACM Trans Audio Speech Lang Process 26:1702\u20131726","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"17492_CR2","doi-asserted-by":"crossref","unstructured":"Erdogan H, Hershey JR, Watanabe S, Le Roux J (2015) Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks. In: ICASSP, pp 708\u2013712","DOI":"10.1109\/ICASSP.2015.7178061"},{"issue":"12","key":"17492_CR3","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"Y Wang","year":"2014","unstructured":"Wang Y, Narayanan A, Wang D (2014) On training targets for supervised speech separation. IEEE\/ACM Trans Audio Speech Lang Process 22(12):1849\u20131858","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"3","key":"17492_CR4","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","volume":"24","author":"DS Williamson","year":"2016","unstructured":"Williamson DS, Wang Y, Wang D (2016) Complex ratio masking for monaural speech separation. IEEE\/ACM Trans Audio Speech Lang Process 24(3):483\u2013492","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"4","key":"17492_CR5","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TASSP.1982.1163920","volume":"30","author":"D Wang","year":"1982","unstructured":"Wang D, Lim J (1982) The unimportance of phase in speech enhancement. IEEE Trans Acoust Speech Signal Process 30(4):679\u2013681","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"4","key":"17492_CR6","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/j.specom.2010.12.003","volume":"53","author":"K Paliwal","year":"2011","unstructured":"Paliwal K, W\u00b4ojcicki K, Shannon B (2011) The importance of phase in speech enhancement. Speech Commun 53(4):465\u2013494","journal-title":"Speech Commun"},{"key":"17492_CR7","doi-asserted-by":"crossref","unstructured":"Fu S-W, Hu T-y, Tsao Y, Lu X (2017) Complex spectrogram enhancement by convolutional neural network with multi-metrics learning. In: International Workshop on Machine Learning for Signal Processing, pp 1\u20136","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"17492_CR8","doi-asserted-by":"crossref","unstructured":"Tan K, Wang D (2019) Complex spectral mapping with a convolutional recurrent network for monaural speech enhancement. In: ICASSP, pp 6865\u20136869","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"17492_CR9","unstructured":"Choi H-S, Kim J-H, Huh J, Kim A, Ha J-W, Lee K (2019) Phase-aware speech enhancement with deep complex U-Net. arXiv preprint arXiv:1903.03107"},{"key":"17492_CR10","doi-asserted-by":"crossref","unstructured":"Pandey A, Wang D (2019) Exploring deep complex networks for complex spectrogram enhancement. In: ICASSP, pp 6885\u20136889","DOI":"10.1109\/ICASSP.2019.8682169"},{"key":"17492_CR11","doi-asserted-by":"crossref","unstructured":"Pandey A, Wang D (2018) A new framework for supervised speech enhancement in the time domain in INTERSPEECH, pp 1136\u20131140","DOI":"10.21437\/Interspeech.2018-1223"},{"issue":"9","key":"17492_CR12","doi-asserted-by":"publisher","first-page":"1570","DOI":"10.1109\/TASLP.2018.2821903","volume":"26","author":"S-W Fu","year":"2018","unstructured":"Fu S-W, Wang T-W, Tsao Y, Lu X, Kawai H (2018) End-to-end waveform utterance enhancement for direct evaluation metrics optimization by fully convolutional neural networks. IEEE\/ACM Trans on Audio Speech Lang Process 26(9):1570\u20131584","journal-title":"IEEE\/ACM Trans on Audio Speech Lang Process"},{"key":"17492_CR13","doi-asserted-by":"crossref","unstructured":"Pandey A, Wang D (2019) TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain. In: ICASSP, pp 6875\u20136879","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"17492_CR14","unstructured":"van den Oord A et al (2016) WaveNet: A generative model for raw audio. In: Proc. Int. Sci. Commun. Assoc. Speech Synth. Workshop, Sunnyvale, p 125"},{"key":"17492_CR15","doi-asserted-by":"crossref","unstructured":"Pandey A, Wang D (2019) TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain. In: Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, Brighton, pp 6875\u20136879","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"17492_CR16","unstructured":"Zhang Q, Nicolson A, Wang M, Paliwal KK, Wang C (2019) Monaural speech enhancement using a multi-branch temporal convolutional network. arXiv:1912.12023"},{"key":"17492_CR17","unstructured":"Koyama Y, Vuong T, Uhlich S, Raj B (2020) Exploring the best loss function for DNN-based low-latency speech enhancement with temporal convolutional networks. arXiv:2005.11611"},{"key":"17492_CR18","doi-asserted-by":"crossref","unstructured":"Kishore V, Tiwari N, Paramasivam P (2020) Improved speech enhancement using TCN with multiple encoder-decoder layers. In: Proc. Interspeech, Shanghai, pp 4531\u20134535","DOI":"10.21437\/Interspeech.2020-3122"},{"key":"17492_CR19","doi-asserted-by":"publisher","first-page":"1888","DOI":"10.1109\/TASLP.2020.2976193","volume":"28","author":"C-L Liu","year":"2019","unstructured":"Liu C-L, Fu S-W, Li Y-J, Huang J-W, Wang H-M, Tsao Y (2019) \u201cMultichannel speech enhancement by raw waveform-mapping using fully convolutional networks.\u201d IEEE\/ACM Trans Audio Speech Lang Process 28:1888\u20131900","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"8","key":"17492_CR20","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Y Luo","year":"2019","unstructured":"Luo Y, Mesgarani N (2019) Conv-TasNet: Surpassing ideal time-frequency magnitude masking for speech separation. IEEE\/ACM Trans Audio, Speech, Lang Process 27(8):1256\u20131266","journal-title":"IEEE\/ACM Trans Audio, Speech, Lang Process"},{"issue":"12","key":"17492_CR21","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"Y Wang","year":"2014","unstructured":"Wang Y, Narayanan A, Wang D (2014) On training targets for supervised speech separation. IEEE\/ACM Trans Audio, Speech, Lang Process 22(12):1849\u20131858","journal-title":"IEEE\/ACM Trans Audio, Speech, Lang Process"},{"key":"17492_CR22","doi-asserted-by":"crossref","unstructured":"Chen Z, Huang Y, Li J, Gong Y (2017) Improving mask learning based speech enhancement system with restoration layers and residual connection. In: Proc. Interspeech, Stockholm, pp 3632\u20133636","DOI":"10.21437\/Interspeech.2017-515"},{"issue":"4","key":"17492_CR23","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1109\/TASLP.2014.2305833","volume":"22","author":"A Narayanan","year":"2014","unstructured":"Narayanan A, Wang D (2014) \u201cInvestigation of speech separation as a frontend for noise robust speech recognition.\u201d IEEE\/ACM Trans Audio Speech Lang Process 22(4):826\u2013835","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"17492_CR24","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.1109\/TASLP.2021.3079813","volume":"29","author":"A Li","year":"2021","unstructured":"Li A, Liu W, Zheng C, Fan C, Li X (2021) Two heads are better than one: A two-stage complex spectral mapping approach for monaural speech enhancement. IEEE\/ACM Trans Audio Speech Lang Process 29:1829\u20131843","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"17492_CR25","doi-asserted-by":"crossref","unstructured":"Panayotov V, Chen G, Povey D, Khudanpur S (2015) Librispeech: an ASR corpus based on public domain audio books. In: IEEE International Conference on Acoustics. Speech and Signal Processing (ICASSP), pp 5206\u20135210","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"17492_CR26","doi-asserted-by":"crossref","unstructured":"CKA Reddy et al (2021) ICASSP 2021 deep noise suppression challenge in Proc. IEEE Int Conf Acoust Speech Signal Process 6623\u20136627","DOI":"10.1109\/ICASSP39728.2021.9415105"},{"issue":"3","key":"17492_CR27","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga A, Steeneken HJ (1993) Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun 12(3):247\u2013251","journal-title":"Speech Commun"},{"issue":"5","key":"17492_CR28","doi-asserted-by":"publisher","first-page":"3591","DOI":"10.1121\/1.4806631","volume":"133","author":"J Thiemann","year":"2013","unstructured":"Thiemann J, Ito N, Vincent E (2013) The diverse environments multi-channel acoustic noise database: A database of multichannel environ- mental noise recordings. J Acoust Soc Am 133(5):3591\u20133591","journal-title":"J Acoust Soc Am"},{"key":"17492_CR29","first-page":"588","volume":"49","author":"P Loizou","year":"2017","unstructured":"Loizou P (2017) NOIZEUS: A noisy speech corpus for evaluation of speech enhancement algorithms. Speech Commun 49:588\u2013601","journal-title":"Speech Commun"},{"key":"17492_CR30","doi-asserted-by":"crossref","unstructured":"Scalart P et al (1996) Speech enhancement based on a priori signal to noise estimation IEEE International Conference on Acoustics, Speech, and Signal Processing Conference 629\u2013663","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"17492_CR31","doi-asserted-by":"crossref","unstructured":"Pascual S, Bonafonte A, Serra J (2017) Segan: Speech enhancement generative adversarial network arXiv preprint arXiv:1703.09452","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"17492_CR32","unstructured":"Macartney WT (2018) Improved speech enhancement with the wave-u-net. arXiv preprint arXiv:1811.11307"},{"key":"17492_CR33","doi-asserted-by":"crossref","unstructured":"Tan K, Wang D (2018) A convolutional recurrent neural network for real time speech enhancement. In: Proc. Interspeech, Hyderabad, pp 3229\u20133233","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"17492_CR34","doi-asserted-by":"crossref","unstructured":"Li A, Zheng C, Fan C, Peng R, Li X (2020) A Recursive network with dynamic attention for monaural speech enhancement. In: Proc. Interspeech, Shangai, pp 2422\u20132426","DOI":"10.21437\/Interspeech.2020-1513"},{"issue":"20","key":"17492_CR35","doi-asserted-by":"publisher","first-page":"7782","DOI":"10.3390\/s22207782","volume":"22","author":"R Ullah","year":"2022","unstructured":"Ullah R et al (2022) End-to-End Deep Convolutional Recurrent Models for Noise Robust Waveform Speech Enhancement. Sensors 22(20):7782","journal-title":"Sensors"},{"key":"17492_CR36","doi-asserted-by":"crossref","unstructured":"Wang K, He B, Zhu W-P (2021) TSTNN: Two-stage transformer based neural network for speech enhancement in the time domain. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"17492_CR37","unstructured":"Wang Q et al (2017) Voicefilter: Targeted voice separation by speaker-conditioned spectrogram masking. In: Proc. Interspeech, Graz, pp 2728\u20132732"},{"key":"17492_CR38","doi-asserted-by":"crossref","unstructured":"D\u00e9fossez A, Synnaeve G, Adi Y (2020) Real time speech enhancement in the waveform domain. In: Proc. Interspeech, Shanghai. 3291\u20133295","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"17492_CR39","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1109\/TASLP.2021.3064421","volume":"29","author":"A Pandey","year":"2021","unstructured":"Pandey A, Wang D (2021) Dense CNN with self-attention for time-domain speech enhancement. IEEE\/ACM Trans Audio Speech Lang Process 29:1270\u20131279","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"17492_CR40","unstructured":"Kingma DP, Ba JL (2021) Adam: A method for stochastic optimization. In: International conference on learning representations, San Diego, pp 1\u201315"},{"issue":"7","key":"17492_CR41","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"Taal CH, Hendriks RC, Heusdens R, Jensen J (2011) An algorithm for intelligibility prediction of time\u2013 frequency weighted noisy speech. IEEE Trans Audio Speech Lang Processs 19(7):2125\u20132136","journal-title":"IEEE Trans Audio Speech Lang Processs"},{"key":"17492_CR42","doi-asserted-by":"crossref","unstructured":"Rix W, Beerends JG, Hollier MP, Hekstra AP (2001) Perceptual evaluation of speech quality (PESQ) - a new method for speech quality assessment of telephone networks and codecs. In: ICASSP, pp 749\u2013752","DOI":"10.1109\/ICASSP.2001.941023"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17492-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17492-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17492-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T12:12:34Z","timestamp":1730463154000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17492-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,6]]},"references-count":42,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["17492"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17492-2","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,6]]},"assertion":[{"value":"7 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest\/Competing interests"}}]}}