LDC Forced Aligner
نویسنده
چکیده
This paper describes the LDC forced aligner which is designed to align audio and transcripts. Unlike existing forced aligners, LDC forced aligner can align partially transcribed audio files, and also audio files with large chunks of non-speech segments, such as noise, music, silence etc, by inserting optional wildcard phoneme sequences between sentence or paragraph boundaries. Based on the HTK tool kit, LDC forced aligner can align audio and transcript on sentence or word level. This paper also reports its usage on English and Mandarin Chinese data.
منابع مشابه
Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi
We present the Montreal Forced Aligner (MFA), a new opensource system for speech-text alignment. MFA is an update to the Prosodylab-Aligner, and maintains its key functionality of trainability on new data, as well as incorporating improved architecture (triphone acoustic models and speaker adaptation), and other features. MFA uses Kaldi instead of HTK, allowing MFA to be distributed as a stand-...
متن کاملCorpus Support for Machine Translation at LDC
This paper describes LDC's efforts in collecting, creating and processing different types of linguistic data, including lexicons, parallel text, multiple translation corpora, and human assessment of translation quality, to support the research and development in Machine Translation. Through a combination of different procedures and core technologies, the LDC was able to create very large, high ...
متن کاملAutomatic Tools for Analyzing Spoken Hebrew
This work summarizes our project to propose a set of automatic tools for analyzing the phonetic and phonological content of spoken Hebrew. The goal of the project is to provide a set of resources to scientists and engineers who work on research and engineering problems related to the acoustics and linguistics of the modern Hebrew language. The set of tools includes: (i) a transcribed corpus of ...
متن کاملMeaning Representations in Statistical Word Alignment
As a testbed of statistical word aligner, we implemented the prototype of statistical word aligner by graphical models [2, 10]. The advantage of using graphical method resides in its extensibility compared to the traditional approach for statistical word alignment [3, 22, 14]. Although there are semi-supervised word aligner [6], we only talk about unsupervised word aligner [3, 22, 14]. The capa...
متن کاملAutomatic detection of "g-dropping" in American English using forced alignment
This study investigated the use of forced alignment for automatic detection of “g-dropping” in American English (e.g., walkin'). Two acoustic models were trained, one for -in' and the other for -ing. The models were added to the Penn Phonetics Lab Forced Aligner, and forced alignment will choose the more probable pronunciation from the two alternatives. The agreement rates between the forced al...
متن کامل