CMU Multilingual NLP 2022 - Speech
Explore the fundamentals of speech processing and its applications in this comprehensive lecture by Shinji Watanabe. Delve into the nature of speech, its various applications, and the importance of speech databases. Examine the hierarchical structure of speech and gain insights into key topics such as speech waveforms, coding, and the information contained within speech sounds. Learn about Automatic Speech Recognition (ASR), Text-to-Speech (TTS) synthesis, and speech translation. Discuss privacy concerns in speech technology and explore speech enhancement techniques. Investigate different types of speech variations, including speaking styles and environments, with examples of read and spontaneous speech. Discover the sources of speech data used in research and development. Access accompanying slides and references for further study.