{"id":709261,"date":"2020-09-29T00:00:23","date_gmt":"2020-09-29T07:00:23","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&p=709261"},"modified":"2020-12-01T17:43:24","modified_gmt":"2020-12-02T01:43:24","slug":"recent-efforts-towards-efficient-and-scalable-neural-waveform-coding","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/recent-efforts-towards-efficient-and-scalable-neural-waveform-coding\/","title":{"rendered":"Recent Efforts Towards Efficient And Scalable Neural Waveform Coding"},"content":{"rendered":"
Acoustic signal compression techniques, converting the floating-point waveform into the bitstream representation, serve a cornerstone in the current data storage and telecommunication infrastructure. The rise of data-driven approaches for acoustic coding systems brings in not only potentials but also challenges, among which the model complexity is a major concern: on the one hand, this general-purpose computational paradigm features the performance superiority; on the other hand, most codecs are deployed on low power devices which barely afford the overwhelming computational overhead. In this talk, I will introduce several of our recent efforts towards a better trade-off between performance and efficiency for neural speech\/audio coding. I will present on cascaded cross-module residual learning to conduct multistage quantization in deep learning techniques; in addition, a collaborative quantization scheme will be talked about to simultaneously binarize linear predictive coefficients and the corresponding residuals. If time permits, a novel perceptually salient objective function with a psychoacoustical calibration will also be discussed.<\/p>\n","protected":false},"excerpt":{"rendered":"
Acoustic signal compression techniques, converting the floating-point waveform into the bitstream representation, serve a cornerstone in the current data storage and telecommunication infrastructure. The rise of data-driven approaches for acoustic coding systems brings in not only potentials but also challenges, among which the model complexity is a major concern: on the one hand, this general-purpose […]<\/p>\n","protected":false},"featured_media":709264,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556,243062,13553],"msr-video-type":[206954],"msr-locale":[268875],"msr-post-option":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-709261","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-research-area-audio-acoustics","msr-research-area-medical-health-genomics","msr-video-type-microsoft-research-talks","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/ybEwJKTaY0k","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/709261"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/709261\/revisions"}],"predecessor-version":[{"id":709270,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/709261\/revisions\/709270"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/709264"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=709261"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=709261"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=709261"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=709261"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=709261"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=709261"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=709261"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}