{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:45:56Z","timestamp":1740177956935,"version":"3.37.3"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T00:00:00Z","timestamp":1601942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T00:00:00Z","timestamp":1601942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Qual User Exp"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1007\/s41233-020-00040-3","type":"journal-article","created":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T22:03:03Z","timestamp":1602021783000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Non-intrusive speech quality prediction based on the blind estimation of clean speech and the i-vector framework"],"prefix":"10.1007","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3088-5116","authenticated-orcid":false,"given":"Anderson R.","family":"Avila","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Douglas","family":"O\u2019Shaughnessy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiago H.","family":"Falk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,6]]},"reference":[{"issue":"7","key":"40_CR1","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/MCOM.2015.7158278","volume":"53","author":"E Liotou","year":"2015","unstructured":"Liotou E et al (2015) Quality of experience management in mobile cellular networks: key issues and design challenges. IEEE Commun Mag 53(7):145\u2013153","journal-title":"IEEE Commun Mag"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Cauchi B et al (2016) Perceptual and instrumental evaluation of the perceived level of reverberation. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 629\u2013633. IEE","DOI":"10.1109\/ICASSP.2016.7471751"},{"issue":"1","key":"40_CR3","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1186\/1687-5281-2013-54","volume":"2013","author":"P Gastaldo","year":"2013","unstructured":"Gastaldo P, Zunino R, Redi J (2013) Supporting visual quality assessment with machine learning. EURASIP J Image Video Process 2013(1):54","journal-title":"EURASIP J Image Video Process"},{"key":"40_CR4","unstructured":"Issa O et al (2012) Quality-of-experience perception for video streaming services: Preliminary subjective and objective results. In Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, pp 1\u20139. IEEE"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Jin C, Kubichek R (1996) Vector quantization techniques for output-based objective speech quality. In 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, vol.\u00a01, pp 491\u2013494. IEEE","DOI":"10.1109\/ICASSP.1996.541140"},{"issue":"6","key":"40_CR6","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MSP.2011.942469","volume":"28","author":"S M\u00f6ller","year":"2011","unstructured":"M\u00f6ller S et al (2011) Speech quality estimation: models and trends. IEEE Signal Process Mag 28(6):18\u201328","journal-title":"IEEE Signal Process Mag"},{"key":"40_CR7","unstructured":"ITU-T\u00a0Recommendation P.563. (2004) Single-ended method for objective speech quality assessment in narrow-band telphony applications"},{"issue":"2","key":"40_CR8","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1109\/MSP.2014.2358871","volume":"32","author":"TH Falk","year":"2015","unstructured":"Falk TH et al (2015) Objective quality and intelligibility prediction for users of assistive listening devices: advantages and limitations of existing tools. IEEE Signal Process Mag 32(2):114\u2013124","journal-title":"IEEE Signal Process Mag"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Avila AR et al (2019) Non-intrusive speech quality assessment using neural networks. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 631\u2013635. IEEE","DOI":"10.1109\/ICASSP.2019.8683175"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Gamper H et al (2019) Intrusive and non-intrusive perceptual speech quality assessment using a convolutional neural network. In 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp 85\u201389. IEEE","DOI":"10.1109\/WASPAA.2019.8937202"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Soni MH, Patil HA (2016) Novel subband autoencoder features for non-intrusive quality assessment of noise suppressed speech. In INTERSPEECH, pp 3708\u20133712","DOI":"10.21437\/Interspeech.2016-693"},{"issue":"7","key":"40_CR12","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1109\/TASLP.2019.2912123","volume":"27","author":"B Cauchi","year":"2019","unstructured":"Cauchi B et al (2019) Non-intrusive speech quality prediction using modulation energies and lstm-network. IEEE\/ACM Trans Audio Speech Lang Process 27(7):1151\u20131163","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Avila AR et al (2019) Blind channel response estimation for replay attack detection. Proc. Interspeech 2893\u20132897","DOI":"10.21437\/Interspeech.2019-2956"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Avila AR et al (2019) Intrusive quality measurement of noisy and enhanced speech based on i-vector similarity. In Eleventh International Conference on Quality of Multimedia Experience (QoMEX), pp 1\u20135. IEEE","DOI":"10.1109\/QoMEX.2019.8743285"},{"issue":"4","key":"40_CR15","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H Hermansky","year":"1994","unstructured":"Hermansky H, Morgan N (1994) Rasta processing of speech. IEEE Trans Speech Audio Process 2(4):578\u2013589","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"6","key":"40_CR16","doi-asserted-by":"publisher","first-page":"1935","DOI":"10.1109\/TASL.2006.883253","volume":"14","author":"TH Falk","year":"2006","unstructured":"Falk TH, Chan W-Y (2006) Single-ended speech quality measurement using machine learning methods. IEEE Trans Audio Speech Lang Process 14(6):1935\u20131947","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"10","key":"40_CR17","doi-asserted-by":"publisher","first-page":"2162","DOI":"10.1109\/TASL.2013.2270406","volume":"21","author":"ND Gaubitch","year":"2013","unstructured":"Gaubitch ND, Brookes M, Naylor AA (2013) Blind channel magnitude response estimation in speech using spectrum classification. IEEE Trans Audio Speech Lang Process 21(10):2162\u20132171","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"4","key":"40_CR18","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1109\/TASL.2006.881693","volume":"15","author":"P Kenny","year":"2007","unstructured":"Kenny P et al (2007) Joint factor analysis versus eigenchannels in speaker recognition. IEEE Trans Audio Speech Lang Process 15(4):1435\u20131447","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"4","key":"40_CR19","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak N et al (2011) Front-end factor analysis for speaker verification. IEEE Trans Audio Speech Lang Process 19(4):788\u2013798","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"6","key":"40_CR20","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/MSP.2015.2462851","volume":"32","author":"JHL Hansen","year":"2015","unstructured":"Hansen JHL, Hasan T (2015) Speaker recognition by machines and humans: a tutorial review. IEEE Signal Process Mag 32(6):74\u201399","journal-title":"IEEE Signal Process Mag"},{"issue":"3","key":"40_CR21","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1109\/TSA.2004.840940","volume":"13","author":"P Kenny","year":"2005","unstructured":"Kenny P, Boulianne G, Dumouchel P (2005) Eigenvoice modeling with sparse training data. IEEE Trans Speech Audio Process 13(3):345\u2013354","journal-title":"IEEE Trans Speech Audio Process"},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Garcia-Romero D, Espy-Wilson CY (2011) Analysis of i-vector length normalization in speaker recognition systems. In Twelfth Annual Conference of the International Speech Communication Association","DOI":"10.21437\/Interspeech.2011-53"},{"key":"40_CR23","unstructured":"Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. Journal of Machine Learning Research 9(Nov)"},{"key":"40_CR24","unstructured":"Series B (2014) Recommendation itu-r bs. 1534-3 method for the subjective assessment of intermediate quality level of audio systems. International Telecommunication Union Radio Communication Assembly"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Santos JF, Falk TH (2019) Towards the development of a non-intrusive objective quality measure for dnn-enhanced speech. In 2019 Eleventh International Conference on Quality of Multimedia Experience (QoMEX), pp 1\u20136. IEEE","DOI":"10.1109\/QoMEX.2019.8743156"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Schoeffler M et al (2018) webmushra-a comprehensive framework for web-based listening tests. J Open Res Softw 6(1)","DOI":"10.5334\/jors.187"},{"key":"40_CR27","unstructured":"Valentini-Botinhao C et al (2017) Noisy speech database for training speech enhancement algorithms and tts models. University of Edinburgh. School of Informatics, Centre for Speech Technology Research (CSTR)"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Pascual S, Bonafonte A, Serr\u00e0 J (2017) Segan: Speech enhancement generative adversarial network. arXiv preprint arXiv:1703.09452","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Veaux C, Yamagishi J, King S (2013) The voice bank corpus: Design, collection and data analysis of a large regional accent speech database. In 2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA\/CASLRE), pp 1\u20134. IEEE","DOI":"10.1109\/ICSDA.2013.6709856"},{"issue":"3","key":"40_CR30","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 HJM (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":"7","key":"40_CR31","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1109\/TASLP.2018.2821899","volume":"26","author":"JF Santos","year":"2018","unstructured":"Santos JF, Falk TH (2018) Speech dereverberation with context-aware recurrent neural networks. IEEE\/ACM Trans Audio Speech Lang Process 26(7):1236\u20131246","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"7","key":"40_CR32","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1109\/TASLP.2017.2696307","volume":"25","author":"DS Williamson","year":"2017","unstructured":"Williamson DS, Wang D (2017) Time-frequency masking in the complex domain for speech dereverberation and denoising. IEEE\/ACM Trans Audio Speech Lang Processing 25(7):1492\u20131501","journal-title":"IEEE\/ACM Trans Audio Speech Lang Processing"},{"issue":"1","key":"40_CR33","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1109\/TASLP.2016.2623559","volume":"25","author":"B Wu","year":"2016","unstructured":"Wu B et al (2016) A reverberation-time-aware approach to speech dereverberation based on deep neural networks. IEEE\/ACM Trans Audio Speech Lang Process 25(1):102\u2013111","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"40_CR34","unstructured":"ITU-T\u00a0Recommendation P.862. Perceptual evaluation of speech quality (PESQ), an objective method for end-to-end speech quality assessment of narrowband telephone networks and speech codecs, February 2001"},{"key":"40_CR35","doi-asserted-by":"crossref","unstructured":"Rix A, Beerends J, Hollier M, Hekstra A (2001) Perceptual evaluation of speech quality (PESQ) - a new method for speech quality assessment of telephone networks and codecs. pp 749\u2013752","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"40_CR36","unstructured":"ITU-T\u00a0Recommendation P.863. (2008) Perceptual objective listening quality assessment: An advanced objective perceptual method for end-to-end listening speech quality evaluation of fixed, mobile, and IP-based networks and speech codecs covering narrowband, wideband, and super-wideband signals. Technical report"},{"key":"40_CR37","unstructured":"Beerends J et al (2013) Perceptual objective listening quality assessment (polqa), the third generation itu-t standard for end-to-end speech quality measurement part ii: Perceptual model. Audio Eng Soc 61(6)"},{"issue":"5","key":"40_CR38","doi-asserted-by":"publisher","first-page":"3387","DOI":"10.1121\/1.3097493","volume":"125","author":"J Ma","year":"2009","unstructured":"Ma J, Hu Y, Loizou PC (2009) Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions. J Acoust Soc Am 125(5):3387\u20133405","journal-title":"J Acoust Soc Am"},{"issue":"5","key":"40_CR39","first-page":"305","volume":"7","author":"JH Janssen","year":"1957","unstructured":"Janssen JH (1957) A method for the calculation of the speech intelligibility under conditions of reverberation and noise. Acta Acustica united with Acustica 7(5):305\u2013310","journal-title":"Acta Acustica united with Acustica"},{"key":"40_CR40","doi-asserted-by":"crossref","unstructured":"Taal CH et al (2010) A short-time objective intelligibility measure for time-frequency weighted noisy speech. pp 4214\u20134217","DOI":"10.1109\/ICASSP.2010.5495701"},{"issue":"6","key":"40_CR41","doi-asserted-by":"publisher","first-page":"1924","DOI":"10.1109\/TASL.2006.883177","volume":"14","author":"L Malfait","year":"2006","unstructured":"Malfait L, Berger J, Kastner M (2006) P.563 - the ITU-T standard for single-ended speech quality assessment. IEEE Trans Audio Speech Lang Process 14(6):1924\u20131934","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"40_CR42","unstructured":"ITU-T\u00a0Recommendation P.830. (1996) Subjective performance assessment of telephone-band and wideband digital codecs"},{"issue":"7","key":"40_CR43","doi-asserted-by":"publisher","first-page":"1766","DOI":"10.1109\/TASL.2010.2052247","volume":"18","author":"TH Falk","year":"2010","unstructured":"Falk TH, Zheng C, Chan W-Y (2010) A non-intrusive quality and intelligibility measure of reverberant and dereverberated speech. IEEE Trans Audio Speech Lang Process 18(7):1766\u20131774","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"40_CR44","doi-asserted-by":"crossref","unstructured":"Santos JF, Senoussaoui M, Falk TH (2014) An improved non-intrusive intelligibility metric for noisy and reverberant speech. pp 55\u201359","DOI":"10.1109\/IWAENC.2014.6953337"},{"key":"40_CR45","doi-asserted-by":"crossref","unstructured":"Fu SW et al (2018) Quality-net: An end-to-end non-intrusive speech quality assessment model based on blstm. arXiv preprint arXiv:1808.05344","DOI":"10.21437\/Interspeech.2018-1802"},{"issue":"7553","key":"40_CR46","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436","journal-title":"Nature"},{"key":"40_CR47","unstructured":"ITU-T\u00a0Recommendation P.800. (1998) Recommendation P.800: Methods for subjectiuve determination of transmission quality"},{"key":"40_CR48","unstructured":"Rix AW (2003) Comparison between subjective listening quality and p. 862 pesq score. Proc. Measurement of Speech and Audio Quality in Networks (MESAQIN\u201903), Prague, Czech Republic"},{"issue":"24","key":"40_CR49","first-page":"171","volume":"24","author":"MV Shcherbakov","year":"2013","unstructured":"Shcherbakov MV et al (2013) A survey of forecast error measures. World Appl Sci J 24(24):171\u2013176","journal-title":"World Appl Sci J"},{"key":"40_CR50","unstructured":"ITU-T\u00a0Recommendation P.862.1. (2003) Mapping function for transforming p.862 raw result scores to mos-lq"},{"issue":"4","key":"40_CR51","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TIM.2009.2024697","volume":"59","author":"TH Falk","year":"2010","unstructured":"Falk TH, Chan W-Y (2010) Temporal dynamics for blind measurement of room acoustical parameters. IEEE Trans Instrum Meas 59(4):978\u2013989","journal-title":"IEEE Trans Instrum Meas"},{"issue":"5","key":"40_CR52","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1109\/TASL.2008.925147","volume":"16","author":"P Kenny","year":"2008","unstructured":"Kenny P et al (2008) A study of interspeaker variability in speaker verification. IEEE Trans Audio Speech Lang Process 16(5):980\u2013988","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"40_CR53","unstructured":"ITU-T\u00a0Recommendation P.835. (2003) Subjective test methodology for evaluating speech communication systems that include noise suppression algorithm. International Telecommunication Union, Geneva"},{"key":"40_CR54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13634-015-0242-x","volume":"2015","author":"B Cauchi","year":"2015","unstructured":"Cauchi B et al (2015) Combination of MVDR beamforming and single-channel spectral processing for enhancing noisy and reverberant speech. EURASIP J Adv Signal Process 2015:1\u201312","journal-title":"EURASIP J Adv Signal Process"},{"issue":"1","key":"40_CR55","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13634-016-0314-6","volume":"2016","author":"J Thiemann","year":"2016","unstructured":"Thiemann J et al (2016) Speech enhancement for multimicrophone binaural hearing aids aiming to preserve the spatial auditory scene. EURASIP J Adv Signal Process 2016(1):12","journal-title":"EURASIP J Adv Signal Process"}],"container-title":["Quality and User Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41233-020-00040-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41233-020-00040-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41233-020-00040-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T16:06:23Z","timestamp":1723737983000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41233-020-00040-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,6]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["40"],"URL":"https:\/\/doi.org\/10.1007\/s41233-020-00040-3","relation":{},"ISSN":["2366-0139","2366-0147"],"issn-type":[{"type":"print","value":"2366-0139"},{"type":"electronic","value":"2366-0147"}],"subject":[],"published":{"date-parts":[[2020,10,6]]},"assertion":[{"value":"19 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2020","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"11"}}