Reviews
I bought it because I was interested, and I was getting help because I had to use it. We need to deal with both the theory and the formula and the code, which we think is a suitable textbook. I was sorry that when we first bought it, we thought it was more important to use the typiermic for the use of the lingi than for the theoretical background of voice recognition, but I think we did well because we had to use it for work.
It's good to explain what you want to do with your voice recognition, not using the CT of cloud service. But it's a little bit sad because it'll seem a little more critical on the side of kaldi than on the theoretical background.
I bought it because of the public open source kaldi interest that was being encountered by voice recognition, but it seemed a little difficult for me to understand it, but I was still well-explained. It's been with sauce. I've seen it in a long time. It's the first time in my history, so it's great.
Chen Guoguo et al.: Learning Speech Recognition with Kaldi
For the past 20 years, voice recognition markets have been unable to find a place in the market as necessary business, seemingly expanding and shrinking rapidly. The reason is that voice recognition technology has gone wrong with public standards. Over a decade ago, the advances of neural networks have led to a golden age of voice recognition. Now voice recognition technology is increasingly becoming an industry's essential technology, and it is not yet perfect, but it is meeting the needs of the public, so the scale of the speech recognition industry is growing progressively. The forward development of voice recognition technology and the subsequent scale of business will grow faster than anyone could have expected. In this situation, the speech recognition textbook that provides the necessary information and information for speech-aware developers is an essential element. The book is based on the open source of the latest voice recognition technology, the typology of speech recognition, which gives a detailed description of the background of voice recognition and the actual application of it. In the text, the author paid attention to the example analysis, avoided the official derive, and focused on explaining the key problem and the intuitive meaning of the algorithm. We also focused on the interpretation of examples to help readers quickly establish a macro-size view of speech technology and understand even the details of the lydi tool set. Readers who lack background knowledge about voice can quickly start voice development using this book as an introduction.
Korean title: 칼디로 배우는 음성인식
Korean author: 천궈궈 외
Korean publisher: 지니북스
ISBN-13: 9791196278878
Reviews
I bought it because I was interested, and I was getting help because I had to use it. We need to deal with both the theory and the formula and the code, which we think is a suitable textbook. I was sorry that when we first bought it, we thought it was more important to use the typiermic for the use of the lingi than for the theoretical background of voice recognition, but I think we did well because we had to use it for work.
It's good to explain what you want to do with your voice recognition, not using the CT of cloud service. But it's a little bit sad because it'll seem a little more critical on the side of kaldi than on the theoretical background.
I bought it because of the public open source kaldi interest that was being encountered by voice recognition, but it seemed a little difficult for me to understand it, but I was still well-explained. It's been with sauce. I've seen it in a long time. It's the first time in my history, so it's great.
