@InProceedings{8553551,
  author = {Y. Ji and W. Zhu and B. Champagne},
  booktitle = {2018 26th European Signal Processing Conference (EUSIPCO)},
  title = {Structured Dictionary Learning for Compressive Speech Sensing},
  year = {2018},
  pages = {573-577},
  abstract = {Sparse dictionary learning aims at training appropriate redundant dictionaries for specific tasks of signal processing, such as signal estimation, compression and classification. Most of the existing dictionary learning algorithms for compressive speech sensing only exploit speech samples to construct the dictionary. In this paper, we propose to leverage both the speech signal and its linear prediction coefficients jointly to learn a structured and sparse dictionary. The proposed dictionary is designed based on a new optimization strategy using both l0 and l2 norms to enforce sparsity and structure, respectively. The resulting optimization problem can be solved by a fast iterative algorithm in two stages. Experimental results indicate that our proposed algorithm converges faster than the reference methods while yielding a better objective evaluation performance in terms of segmental signal-to-noise ratio, perceptual evaluation of speech quality and short-time objective intelligibility of the reconstructed speech.},
  keywords = {compressed sensing;dictionaries;iterative methods;learning (artificial intelligence);optimisation;sparse matrices;speech coding;redundant dictionaries;signal compression;signal classification;optimization problem;signal-to-noise ratio;speech reconstruction;sparse dictionary learning;dictionary learning algorithms;optimization strategy;speech processing;speech quality;fast iterative algorithm;linear prediction coefficients;speech signal;signal estimation;signal processing;compressive speech sensing;structured dictionary learning;Dictionaries;Sparse matrices;Machine learning;Signal processing algorithms;Optimization;Speech processing;Training;dictionary learning;speech processing;compressive sensing;optimization},
  doi = {10.23919/EUSIPCO.2018.8553551},
  issn = {2076-1465},
  month = {Sep.},
  url = {https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570437529.pdf},
}

{"_id":"kq9XuMxcAgYDfzh2E","bibbaseid":"ji-zhu-champagne-structureddictionarylearningforcompressivespeechsensing-2018","authorIDs":[],"author_short":["Ji, Y.","Zhu, W.","Champagne, B."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Y."],"propositions":[],"lastnames":["Ji"],"suffixes":[]},{"firstnames":["W."],"propositions":[],"lastnames":["Zhu"],"suffixes":[]},{"firstnames":["B."],"propositions":[],"lastnames":["Champagne"],"suffixes":[]}],"booktitle":"2018 26th European Signal Processing Conference (EUSIPCO)","title":"Structured Dictionary Learning for Compressive Speech Sensing","year":"2018","pages":"573-577","abstract":"Sparse dictionary learning aims at training appropriate redundant dictionaries for specific tasks of signal processing, such as signal estimation, compression and classification. Most of the existing dictionary learning algorithms for compressive speech sensing only exploit speech samples to construct the dictionary. In this paper, we propose to leverage both the speech signal and its linear prediction coefficients jointly to learn a structured and sparse dictionary. The proposed dictionary is designed based on a new optimization strategy using both l0 and l2 norms to enforce sparsity and structure, respectively. The resulting optimization problem can be solved by a fast iterative algorithm in two stages. Experimental results indicate that our proposed algorithm converges faster than the reference methods while yielding a better objective evaluation performance in terms of segmental signal-to-noise ratio, perceptual evaluation of speech quality and short-time objective intelligibility of the reconstructed speech.","keywords":"compressed sensing;dictionaries;iterative methods;learning (artificial intelligence);optimisation;sparse matrices;speech coding;redundant dictionaries;signal compression;signal classification;optimization problem;signal-to-noise ratio;speech reconstruction;sparse dictionary learning;dictionary learning algorithms;optimization strategy;speech processing;speech quality;fast iterative algorithm;linear prediction coefficients;speech signal;signal estimation;signal processing;compressive speech sensing;structured dictionary learning;Dictionaries;Sparse matrices;Machine learning;Signal processing algorithms;Optimization;Speech processing;Training;dictionary learning;speech processing;compressive sensing;optimization","doi":"10.23919/EUSIPCO.2018.8553551","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570437529.pdf","bibtex":"@InProceedings{8553551,\n author = {Y. Ji and W. Zhu and B. Champagne},\n booktitle = {2018 26th European Signal Processing Conference (EUSIPCO)},\n title = {Structured Dictionary Learning for Compressive Speech Sensing},\n year = {2018},\n pages = {573-577},\n abstract = {Sparse dictionary learning aims at training appropriate redundant dictionaries for specific tasks of signal processing, such as signal estimation, compression and classification. Most of the existing dictionary learning algorithms for compressive speech sensing only exploit speech samples to construct the dictionary. In this paper, we propose to leverage both the speech signal and its linear prediction coefficients jointly to learn a structured and sparse dictionary. The proposed dictionary is designed based on a new optimization strategy using both l0 and l2 norms to enforce sparsity and structure, respectively. The resulting optimization problem can be solved by a fast iterative algorithm in two stages. Experimental results indicate that our proposed algorithm converges faster than the reference methods while yielding a better objective evaluation performance in terms of segmental signal-to-noise ratio, perceptual evaluation of speech quality and short-time objective intelligibility of the reconstructed speech.},\n keywords = {compressed sensing;dictionaries;iterative methods;learning (artificial intelligence);optimisation;sparse matrices;speech coding;redundant dictionaries;signal compression;signal classification;optimization problem;signal-to-noise ratio;speech reconstruction;sparse dictionary learning;dictionary learning algorithms;optimization strategy;speech processing;speech quality;fast iterative algorithm;linear prediction coefficients;speech signal;signal estimation;signal processing;compressive speech sensing;structured dictionary learning;Dictionaries;Sparse matrices;Machine learning;Signal processing algorithms;Optimization;Speech processing;Training;dictionary learning;speech processing;compressive sensing;optimization},\n doi = {10.23919/EUSIPCO.2018.8553551},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570437529.pdf},\n}\n\n","author_short":["Ji, Y.","Zhu, W.","Champagne, B."],"key":"8553551","id":"8553551","bibbaseid":"ji-zhu-champagne-structureddictionarylearningforcompressivespeechsensing-2018","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570437529.pdf"},"keyword":["compressed sensing;dictionaries;iterative methods;learning (artificial intelligence);optimisation;sparse matrices;speech coding;redundant dictionaries;signal compression;signal classification;optimization problem;signal-to-noise ratio;speech reconstruction;sparse dictionary learning;dictionary learning algorithms;optimization strategy;speech processing;speech quality;fast iterative algorithm;linear prediction coefficients;speech signal;signal estimation;signal processing;compressive speech sensing;structured dictionary learning;Dictionaries;Sparse matrices;Machine learning;Signal processing algorithms;Optimization;Speech processing;Training;dictionary learning;speech processing;compressive sensing;optimization"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2018url.bib","creationDate":"2021-02-13T15:38:40.481Z","downloads":0,"keywords":["compressed sensing;dictionaries;iterative methods;learning (artificial intelligence);optimisation;sparse matrices;speech coding;redundant dictionaries;signal compression;signal classification;optimization problem;signal-to-noise ratio;speech reconstruction;sparse dictionary learning;dictionary learning algorithms;optimization strategy;speech processing;speech quality;fast iterative algorithm;linear prediction coefficients;speech signal;signal estimation;signal processing;compressive speech sensing;structured dictionary learning;dictionaries;sparse matrices;machine learning;signal processing algorithms;optimization;speech processing;training;dictionary learning;speech processing;compressive sensing;optimization"],"search_terms":["structured","dictionary","learning","compressive","speech","sensing","ji","zhu","champagne"],"title":"Structured Dictionary Learning for Compressive Speech Sensing","year":2018,"dataSources":["yiZioZximP7hphDpY","iuBeKSmaES2fHcEE9"]}