{"id":10745,"date":"2023-07-18T11:25:13","date_gmt":"2023-07-18T09:25:13","guid":{"rendered":"https:\/\/gemino.de\/?p=10745"},"modified":"2023-07-18T11:30:59","modified_gmt":"2023-07-18T09:30:59","slug":"voiced-by-darth-vader","status":"publish","type":"post","link":"https:\/\/gemino.de\/en\/voiced-by-darth-vader\/","title":{"rendered":"Voiced by Darth Vader"},"content":{"rendered":"

Opportunities and limitations of speech synthesis<\/span><\/h3>\n

Digital media is changing the way knowledge is transferred from pure text to images and spoken language. Because in many areas, spoken language is better suited for communicating content than pure text.<\/p>\n

Sounds good. But does it deliver?<\/strong><\/p>\n

Especially for videos and e-learning, spoken language in the form of dubbing (lip-sync if necessary) or voice-over (off-screen) is often the better choice. Up to now, dubbing and voice-over have been produced elaborately in a sound studio with voice actors, sound engineers and sometimes even directors.<\/p>\n

Speech synthesis is an alternative here, i.e. the software-based generation of a synthesized and, at the same time, human-sounding speaking voice. This technology (also known as text-to-speech, TTS) has evolved greatly in recent years \u2013 not least due to the increasing availability of deep learning, or artificial intelligence (AI).<\/p>\n

The evolution of speech synthesis:<\/p>\n\n\n\n\n\n\n
Approach<\/strong><\/td>\nFeatures<\/strong><\/td>\n<\/tr>\n
Phoneme-based speech synthesis<\/td>\nOften mechanical or artificial sound, less voice selection<\/td>\n<\/tr>\n
Speech synthesis based on AI (machine learning)<\/td>\nLargely natural sounding voices, few adjustment options<\/td>\n<\/tr>\n
Speech synthesis based on AI with SSML capability<\/td>\nSSML markup language allows much better fine-tuning of many aspects<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

While narrators are still the gold standard for high-quality marketing videos, speech synthesis \u2013 now also based on trained AI speech models \u2013 offers a serious alternative for a number of areas.<\/p>\n

Less expensive. And what else?<\/strong><\/p>\n

One advantage of speech synthesis is reduced costs and production times. This makes the use of spoken language possible even in places where it was previously inconceivable. Subtitles no longer have to be used as a stopgap for dubbing. What\u2019s more, speech synthesis makes things possible that are not feasible in a recording studio. For example, you can create a voice model with any voice and dub your e-learning session with it.<\/p>\n

The advantages and disadvantages of voice recordings versus speech synthesis:<\/p>\n\n\n\n\n\n\n\n\n\n\n
Aspect<\/strong><\/td>\nVoice actor<\/strong><\/td>\nSpeech synthesis<\/strong><\/td>\n<\/tr>\n
Optimal possibilities to determine the effect of the voice in detail (pronunciation, intonation, sentence melody, etc.)<\/td>\nyes<\/td>\nno<\/td>\n<\/tr>\n
Quick production<\/td>\nmostly no<\/td>\nyes<\/td>\n<\/tr>\n
Manageable costs (especially with multiple languages)<\/td>\nno<\/td>\nyes<\/td>\n<\/tr>\n
Simple, inexpensive retakes<\/td>\nno<\/td>\nyes<\/td>\n<\/tr>\n
Voices mostly available all the time<\/td>\nno<\/td>\nyes<\/td>\n<\/tr>\n
Simple, low-cost licensing models<\/td>\nno<\/td>\nyes<\/td>\n<\/tr>\n
Creation of own speech synthesis models with any voice (e.g., Darth Vader)<\/td>\nno<\/td>\nyes<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

As always: It depends.<\/strong><\/p>\n

However, depending on the intended use, target audience and quality requirements, speech synthesis also has limitations. In certain application scenarios, the goal of the communication can still only be achieved with a recording by a professional voice actor. This is especially true in image and product videos, where the type of speech and the associated emotionality in the voice are an essential part of the marketing message.<\/p>\n

One should decide carefully whether to use speech synthesis or not after considering the content to be dubbed and the languages and speech varieties required.<\/p>\n

Here are some decision criteria:<\/p>\n\n\n\n\n\n\n\n\n
Type of content or general conditions<\/strong><\/td>\nImplementation possible through<\/strong><\/td>\n<\/tr>\n
Glossy image video with a voice that significantly contributes to atmosphere and emotionality in the video<\/td>\nStudio recording with voice actor<\/td>\n<\/tr>\n
Technical how-to video<\/td>\nSpeech synthesis<\/td>\n<\/tr>\n
Product video<\/td>\nStudio recording with voice actor or speech synthesis<\/td>\n<\/tr>\n
E-learning<\/td>\nSpeech synthesis<\/td>\n<\/tr>\n
If no speech synthesis model exists for a particular language<\/td>\nStudio recording with voice actor<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Synthesized voices also have a number of peculiarities. These should also be considered when deciding for or against speech synthesis:<\/p>\n