{"id":111124,"date":"2020-04-02T18:40:25","date_gmt":"2020-04-02T18:40:25","guid":{"rendered":"https:\/\/news.microsoft.com\/?p=436864"},"modified":"2020-04-02T18:40:25","modified_gmt":"2020-04-02T18:40:25","slug":"introducing-new-voice-styles-in-azure-cognitive-services","status":"publish","type":"post","link":"https:\/\/sickgaming.net\/blog\/2020\/04\/02\/introducing-new-voice-styles-in-azure-cognitive-services\/","title":{"rendered":"Introducing new voice styles in Azure Cognitive Services"},"content":{"rendered":"<div><img decoding=\"async\" src=\"https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/04\/introducing-new-voice-styles-in-azure-cognitive-services.gif\" class=\"ff-og-image-inserted\"><\/div>\n<p><em>This post was co-authored by <a href=\"https:\/\/techcommunity.microsoft.com\/t5\/user\/viewprofilepage\/user-id\/175688\">@Qinying Liao<\/a>, <a href=\"https:\/\/techcommunity.microsoft.com\/t5\/user\/viewprofilepage\/user-id\/23979\">@Anny Dow<\/a>&nbsp;, Yueying Liu, and Peter Pan. &nbsp;<\/em><\/p>\n<p>Neural TTS enables fluid, natural-sounding speech that matches the patterns and intonation of human voices, helping developers bring their solutions to life.<\/p>\n<p>Today, we\u2019re building upon our Neural Text to Speech (Neural TTS) capabilities in Azure Cognitive Services with new voice styles. With the new styles\u2014newscast, customer service, and digital assistant\u2014developers can tailor the voice of their apps and services to fit their brand or unique scenario.<\/p>\n<p>Built on a powerful base model, our neural TTS voices are very natural, reliable, and expressive. Through transfer learning, the neural TTS model can learn different speaking styles from various speakers, enabling nuanced voices.<\/p>\n<p>In addition to our new voice styles optimized for specific scenarios, we are also releasing new emotion styles. These styles allow you to adjust voices to express different emotions to fit the context, like cheerfulness or empathy. Let\u2019s dive in.<\/p>\n<p><strong>Introducing Newscast, Customer Service, and Digital Assistant styles<\/strong><\/p>\n<p><strong>&nbsp;<\/strong><\/p>\n<p><strong>Newscast<\/strong><\/p>\n<p>With neural TTS voices in the newscast style, your users can enjoy listening to news or articles in a professional tone that reflects what you might hear on TV or radio newscasts.<\/p>\n<p>Hear Aria&#8217;s (English \u2013 Female) and Xiaoxiao\u2019s (Chinese \u2013 Female) voices in the <em>newscast<\/em> style:<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"442.727px\" height=\"30px\">\n<p>Text<\/p>\n<\/td>\n<td width=\"150.909px\" height=\"30px\">\n<p>Newscast style<\/p>\n<\/td>\n<td width=\"155.455px\" height=\"30px\">\n<p>Default<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td width=\"442.727px\" height=\"139px\">\n<p><em>Heavy snow and strong winds hammered parts of the central U.S. on Thursday and began moving into the Great Lakes region, knocking out power to tens of thousands of people and creating hazardous travel conditions a day after pummeling Colorado.<\/em><\/p>\n<\/td>\n<td width=\"150.909px\" height=\"139px\"> <\/td>\n<td width=\"155.455px\" height=\"139px\"> <\/td>\n<\/tr>\n<tr>\n<td width=\"442.727px\" height=\"111px\">\n<p>\u73b0\u4eca\uff0c\u5927\u6279\u4f01\u4e1a\u4ee5\u6570\u5b57\u5316\u8f6c\u578b\u4e3a\u6218\u7565\u76ee\u6807\uff0c\u6570\u5b57\u5316\u8f6c\u578b\u53ef\u8d4b\u80fd\u4f01\u4e1a\u91cd\u6784\u7ade\u4e89\u73af\u5883\u3001\u6ee1\u8db3\u5ba2\u6237\u671f\u671b\u3001\u589e\u5f3a\u670d\u52a1\u8fd0\u8425\u3002\u4e3a\u4e86\u771f\u6b63\u5b9e\u73b0\u201c being digital \u201d, \u8bb8\u591a\u4f01\u4e1a\u5c06\u4eba\u5de5\u667a\u80fd\u89c6\u4f5c\u5b9e\u73b0\u6570\u5b57\u5316\u8f6c\u578b\u76ee\u6807\u7684\u9996\u9009\u6280\u672f\u5de5\u5177\u4e4b\u4e00\u3002<\/p>\n<\/td>\n<td width=\"150.909px\" height=\"111px\"> <\/td>\n<td width=\"155.455px\" height=\"111px\"> <\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Check out the newscast style in the Bing mobile app. When you search news with the voice search feature, you can hear news briefs using Aria\u2019s newscast style voice.<\/p>\n<p>You can also check out Xiaoxiao\u2019s newscast style voice, which has been adopted in WeChat through the Microsoft Listening Docs app. In Microsoft Listening Docs, users can hear Xiaoxiao\u2019s voice read out multiple document types such as Word, PowerPoint, Excel, as well as images. Users can easily generate audio content for online trainings, news podcasts and more, and share with their social circles.<\/p>\n<p><strong>Customer Service<\/strong><\/p>\n<p>The customer service style features a friendly and engaging tone and is suitable for scenarios involving customer support, such as an individual checking into their flight, making a restaurant reservation, or reporting a claim.<\/p>\n<p>Hear Aria&#8217;s and Xiaoxiao\u2019s voices in the <em>customer service<\/em> style:<\/p>\n<table class=\" lia-align-left\">\n<tbody>\n<tr>\n<td width=\"378.182px\" height=\"57px\">\n<p>Text<\/p>\n<\/td>\n<td width=\"196.364px\" height=\"57px\">\n<p>Customer Service style&nbsp;<\/p>\n<\/td>\n<td width=\"174.545px\">\n<p>Default<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td width=\"378.182px\" height=\"139px\">\n<p><em>Alright, it&#8217;s going to be right in front of your door, within 30 minutes. Thanks for calling &nbsp;Pizza Loco! <\/em><em>Have a great night!<\/em><\/p>\n<\/td>\n<td width=\"196.364px\" height=\"139px\">\n<p><audio controls=\"controls\"><\/audio>&nbsp;<\/p>\n<\/td>\n<td width=\"174.545px\"> <\/td>\n<\/tr>\n<tr>\n<td width=\"378.182px\" height=\"275px\">\n<p>\u5ba2\u670d\uff1a\u60a8\u597d\uff0c\u6b22\u8fce\u81f4\u7535\u667a\u6167\u94f6\u884c\uff0c\u6211\u662f\u60a8\u7684\u667a\u80fd\u5ba2\u670d\u6653\u6653\uff0c\u8bf7\u95ee\u6709\u4ec0\u4e48\u53ef\u4ee5\u5e2e\u60a8\uff1f<\/p>\n<p>\u5ba2\u6237\uff1a\u4f60\u597d\uff0c\u6211\u60f3\u8c03\u6574\u4fe1\u7528\u5361\u7684\u989d\u5ea6\u3002<\/p>\n<p>\u5ba2\u670d\uff1a\u55ef\uff0c\u8bf7\u7a0d\u7b49\uff0c\u6211\u67e5\u8be2\u4e00\u4e0b\u72b6\u6001\u3002\u8bf7\u95ee\u60a8\u8981\u8c03\u6574\u5230\u591a\u5c11\u989d\u5ea6\uff1f<\/p>\n<p>\u5ba2\u6237\uff1a\u5e2e\u6211\u8c03\u5230\u4e09\u4e07\u4eba\u6c11\u5e01\u5427\u3002<\/p>\n<p>\u5ba2\u670d\uff1a\u597d\u7684\uff0c\u5df2\u7ecf\u7ed9\u60a8\u53d8\u66f4\u6210\u529f\uff0c\u7a0d\u540e\u60a8\u4f1a\u6536\u5230\u77ed\u4fe1\u63d0\u9192\u3002<\/p>\n<p>\u5ba2\u6237\uff1a\u597d\u7684\uff0c\u8c22\u8c22\u3002<\/p>\n<p>\u5ba2\u670d\uff1a\u611f\u8c22\u60a8\u7684\u6765\u7535\uff0c\u795d\u60a8\u751f\u6d3b\u6109\u5feb\uff0c\u518d\u89c1\u3002<\/p>\n<\/td>\n<td width=\"196.364px\" height=\"275px\"> <\/td>\n<td width=\"174.545px\"><audio controls=\"controls\"><\/audio><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><strong>Digital<\/strong>&nbsp;<strong>Assistant<\/strong><\/p>\n<p>Many customers have been using neural TTS voices for their digital assistant solutions. We are introducing two styles in this area: a chat style for more casual, conversational bots, and a more professional style for scenarios such as in-car digital assistants.<\/p>\n<p>The <em>chat<\/em> style features a conversational tone, simulating casual dialogue.<\/p>\n<p>Hear Aria\u2019s voice in the <em>chat <\/em>style:<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"117.273px\">\n<p>Style<\/p>\n<\/td>\n<td width=\"289.091px\">\n<p>Text<\/p>\n<\/td>\n<td width=\"110.909px\">\n<p>Chat style<\/p>\n<\/td>\n<td width=\"102.727px\">\n<p>Default<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td width=\"117.273px\">\n<p>Chat<\/p>\n<\/td>\n<td width=\"289.091px\">\n<p><em>Oh, well that&#8217;s quite a change from California to Utah<\/em>.<\/p>\n<\/td>\n<td width=\"110.909px\"> <\/td>\n<td width=\"102.727px\"> <\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>The <em>assistant<\/em> style features a friendly and helpful tone, which is suitable in scenarios such as smart speakers or in-car assistants. Use the digital assistant voice to hear the weather forecast, search for information, navigate directions, set reminders, and more.<\/p>\n<p>Hear Xiaoxiao\u2019s voice in the <em>assistant<\/em> style:<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"454.545px\">\n<p>Text<\/p>\n<\/td>\n<td width=\"137.273px\">\n<p>Assistant style<\/p>\n<\/td>\n<td width=\"157.273px\">\n<p>Default<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td width=\"454.545px\">\n<p>\u6ca1\u542c\u5230\u4f60\u8bf4\u8bdd\uff0c\u8bf7\u518d\u8bf4\u4e00\u6b21\u3002<\/p>\n<\/td>\n<td width=\"137.273px\"> <\/td>\n<td width=\"157.273px\"> <\/td>\n<\/tr>\n<tr>\n<td width=\"454.545px\">\n<p>\u73b0\u5728\u542c\u7684\u662f\uff1aFM88.8<span>\uff0c\u6c5f\u82cf\u97f3\u4e50\u53f0\u7684\u8282\u76ee\uff0c\u6ef4\u6ef4\u53ed\u53ed\u65e9\u4e0a\u597d\u3002<\/span><\/p>\n<\/td>\n<td width=\"137.273px\"> <\/td>\n<td width=\"157.273px\"> <\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><strong>Bringing new emotions to Neural Text to Speech<\/strong><\/p>\n<p>To enable you to build nuanced voices for your unique scenario, Neural Text to Speech also offers different emotion styles. You can access <em>cheerful<\/em> and <em>empathetic<\/em> styles for Aria\u2019s voice, <em>lyrical<\/em> style for Xiaoxiao\u2019s voice\u2014which sounds heartfelt and is optimized to read prose or poetry, and <em>cheerful<\/em> style for Francisca\u2019s voice (Brazilian Portuguese).<\/p>\n<p>Hear the new styles below:<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"107.273px\">\n<p>Style<\/p>\n<\/td>\n<td width=\"264.545px\">\n<p>Text<\/p>\n<\/td>\n<td width=\"132.727px\">\n<p>Style<\/p>\n<\/td>\n<td width=\"109.091px\">\n<p>Default<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td rowspan=\"2\" width=\"107.273px\">\n<p>Cheerful<\/p>\n<\/td>\n<td width=\"264.545px\">\n<p><em>G<\/em><em>reat, I hope she will like it!&nbsp;<\/em><\/p>\n<\/td>\n<td width=\"132.727px\"><audio controls=\"controls\"><\/audio><\/td>\n<td width=\"109.091px\"><audio controls=\"controls\"><\/audio><\/td>\n<\/tr>\n<tr>\n<td width=\"264.545px\">\n<p><em>A canadense postou uma m\u00fasica nova no seu perfil oficial do Twitter.<\/em><\/p>\n<\/td>\n<td width=\"132.727px\"> <\/td>\n<td width=\"109.091px\"> <\/td>\n<\/tr>\n<tr>\n<td width=\"107.273px\">\n<p>Empathetic<\/p>\n<\/td>\n<td width=\"264.545px\">\n<p><em>I want to let you know that you\u2019re loved. I know things are hard right now and it\u2019s OK. You don\u2019t have to do this alone<\/em><\/p>\n<\/td>\n<td width=\"132.727px\"> <\/td>\n<td width=\"109.091px\"> <\/td>\n<\/tr>\n<tr>\n<td width=\"107.273px\">\n<p>Lyrical<\/p>\n<\/td>\n<td width=\"264.545px\">\n<p>\u5927\u5bb6\u665a\u4e0a\u597d\uff0c\u6211\u662f\u6653\u6653\u3002\u5728\u6bcf\u4e00\u4e2a\u591c\u665a\u6765\u4e34\u7684\u65f6\u5019\uff0c\u6211\u90fd\u5728\u8fd9\u91cc\u966a\u4f60\u5165\u7761\u3002\u5fd9\u788c\u7684\u4e00\u5929\u53c8\u8fc7\u53bb\u4e86\uff0c\u73b0\u5728\u7684\u4f60\u662f\u7a9d\u5728\u6c99\u53d1\u4e0a\u770b\u7740\u7a97\u5916\u53d1\u5446\uff0c\u8fd8\u662f\u5012\u4e86\u4e00\u676f\u5496\u5561\u7ee7\u7eed\u89e3\u51b3\u767d\u5929\u6ca1\u6709\u505a\u5b8c\u7684\u5de5\u4f5c\u5462\uff1f\u65f6\u95f4\u8fc7\u5f97\u771f\u5feb\u5440\uff0c\u5728\u5b66\u6821\u91cc\u54ac\u7740\u65e9\u9910\u4e0a\u8bfe\uff0c\u548c\u540c\u5b66\u4eec\u5b09\u620f\u6253\u95f9\u7684\u65e5\u5b50\uff0c\u4eff\u4f5b\u5c31\u5728\u6628\u5929\u3002\u4f46\u4e00\u8f6c\u773c\uff0c\u6211\u4eec\u90fd\u7a7f\u7740\u897f\u88c5\u53d8\u6210\u4e86\u5927\u4eba\u3002&nbsp;<\/p>\n<\/td>\n<td width=\"132.727px\"> <\/td>\n<td width=\"109.091px\"> <\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>These new voice styles are also available for customized brand voices through our <a href=\"https:\/\/speech.microsoft.com\/customvoice\" target=\"_blank\" rel=\"noopener noreferrer\">Custom Neural Voice<\/a> capability, allowing you to build a unique voice that can also benefit from our new scenario and emotion styles. As part of Microsoft&#8217;s commitment to designing AI responsibly, we have developed guidelines for customers in using Custom Neural Voice, in alignment with Microsoft&#8217;s&nbsp;<a href=\"https:\/\/www.microsoft.com\/AI\/our-approach-to-ai\" target=\"_blank\" rel=\"noopener noreferrer\">principles for responsible innovation in AI.<\/a> Learn more about the process for getting started with Custom Neural Voice <a href=\"https:\/\/docs.microsoft.com\/en-us\/azure\/cognitive-services\/speech-service\/concepts-gating-overview\" target=\"_blank\" rel=\"noopener noreferrer\">here<\/a>. &nbsp;&nbsp;<\/p>\n<p><strong>Get Started<\/strong><\/p>\n<p>Get started with the new neural TTS voice styles available in Azure Cognitive Services. Check out our <a href=\"https:\/\/docs.microsoft.com\/en-us\/azure\/cognitive-services\/speech-service\/speech-synthesis-markup?tabs=csharp#adjust-speaking-styles\" target=\"_blank\" rel=\"noopener noreferrer\">documentation<\/a> to learn more.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>This post was co-authored by @Qinying Liao, @Anny Dow&nbsp;, Yueying Liu, and Peter Pan. &nbsp; Neural TTS enables fluid, natural-sounding speech that matches the patterns and intonation of human voices, helping developers bring their solutions to life. Today, we\u2019re building upon our Neural Text to Speech (Neural TTS) capabilities in Azure Cognitive Services with new [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[49],"tags":[477,50],"class_list":["post-111124","post","type-post","status-publish","format-standard","hentry","category-microsoft-news","tag-azure-cognitive-services","tag-recent-news"],"_links":{"self":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/posts\/111124","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/comments?post=111124"}],"version-history":[{"count":0,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/posts\/111124\/revisions"}],"wp:attachment":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/media?parent=111124"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/categories?post=111124"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/tags?post=111124"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}