读一下这本书：《Automatic Speech Recognition A Deep Learning Approach》http://rd.springer.com/book/10.1007%2F978-1-4471-5779-3。另外再读读另一本 http://www.amazon.com/Spoken-Language-Processing-Algorithm-D...。与此同时，上手玩玩开源工具包——cmusphinx、kaldi。直接跑跑教程里的例子，了解实际操作中是怎么回事。
Read the book: Automatic Speech Recognition A Deep Learning Approach http://rd.springer.com/book/10.1007%2F978-1-4471-5779-3. Also read another book http://www.amazon.com/Spoken-Language-Processing-Algorithm-D.... In parallel play with open source toolkits - cmusphinx, kaldi. Just run examples from tutorials to understand how things look in practice.
…识别，有几本非常基础的教科书：* Manning 和 Schuetze 写的《Foundations of Statistical Natural Language Processing》[0] * Jelinek 写的《Statistical Methods for Speech Recognition》[1] * 黄学东（Huang）、Acero 和沈向洋（Hon）合著的《Spoken Language Processing: A Guide to Theory, Algorithm, and System Development》[2] 特别是《Statistical Methods for Speech Recognition》，你几乎可以在大多数做这个领域的人的书架上看到…
…recognition, a few very foundational textbooks are: * Foundations of Statistical Natural Language Processing by Manning and Schuetze [0] * Statistical Methods for Speech Recognition by Jelinek [1] * Spoken Language Processing: A Guide to Theory, Algorithm, and System Development by Huang, Acero and Hon [2] In particular, Statistical Methods for Speech Recognition is a book you could expect to see on the shelves of most people…
纯属闲得蛋疼（for shits and giggles），我从书架上随手抽了一本书，数了数每列的字符数。我抽的书是 Huang、Acero、Hon 写的《Spoken Language Processing》（ISBN 0-13-022616-5），我数出来每行有 88 个字符。尽管超过了很多人声称的书籍/分栏 70 来个字符的上限，这本书读起来依然很顺畅。另一本放在旁边的书…
Just for shits and giggles I grabbed a random book from the shelf and counted characters per column. The book I grabbed was "Spoken Language Processing", Huang Acero, Hon (ISBN 0-13-022616-5) and I counted 88 characters per line. The book is still very readable, despite exceeding the claimed 70-odd character limit for books/columns. Another book sitting…
读一下这本书：《Automatic Speech Recognition A Deep Learning Approach》http://rd.springer.com/book/10.1007%2F978-1-4471-5779-3。另外再读读另一本 http://www.amazon.com/Spoken-Language-Processing-Algorithm-D...。与此同时，上手玩玩开源工具包——cmusphinx、kaldi。直接跑跑教程里的例子，了解实际操作中是怎么回事。
Read the book: Automatic Speech Recognition A Deep Learning Approach http://rd.springer.com/book/10.1007%2F978-1-4471-5779-3. Also read another book http://www.amazon.com/Spoken-Language-Processing-Algorithm-D.... In parallel play with open source toolkits - cmusphinx, kaldi. Just run examples from tutorials to understand how things look in practice.
…识别，有几本非常基础的教科书：* Manning 和 Schuetze 写的《Foundations of Statistical Natural Language Processing》[0] * Jelinek 写的《Statistical Methods for Speech Recognition》[1] * 黄学东（Huang）、Acero 和沈向洋（Hon）合著的《Spoken Language Processing: A Guide to Theory, Algorithm, and System Development》[2] 特别是《Statistical Methods for Speech Recognition》，你几乎可以在大多数做这个领域的人的书架上看到…
…recognition, a few very foundational textbooks are: * Foundations of Statistical Natural Language Processing by Manning and Schuetze [0] * Statistical Methods for Speech Recognition by Jelinek [1] * Spoken Language Processing: A Guide to Theory, Algorithm, and System Development by Huang, Acero and Hon [2] In particular, Statistical Methods for Speech Recognition is a book you could expect to see on the shelves of most people…
纯属闲得蛋疼（for shits and giggles），我从书架上随手抽了一本书，数了数每列的字符数。我抽的书是 Huang、Acero、Hon 写的《Spoken Language Processing》（ISBN 0-13-022616-5），我数出来每行有 88 个字符。尽管超过了很多人声称的书籍/分栏 70 来个字符的上限，这本书读起来依然很顺畅。另一本放在旁边的书…
Just for shits and giggles I grabbed a random book from the shelf and counted characters per column. The book I grabbed was "Spoken Language Processing", Huang Acero, Hon (ISBN 0-13-022616-5) and I counted 88 characters per line. The book is still very readable, despite exceeding the claimed 70-odd character limit for books/columns. Another book sitting…