Issues in automatic transcription of historical audio data
نویسندگان
چکیده
This work deals with some interesting issues that arose when the ITC-irst broadcast news transcription system was applied to transcribe the audio track of historical documentary films. Due to an evident acoustic and linguistic mismatch between the broadcast news and the new application domain, the initial word error rate was of 46.4%. By exploiting a limited amount of manually annotated training data, adaptation of all components of the transcription system was performed, namely the audio partitioner, the acoustic model, and the language model. This permitted to achieve a word error rate of 30%, which makes automatic transcription of documentary films effective for information retrieval applications.
منابع مشابه
The Role of Azeri Radio World Service in Explaining the Common History of Iran and The Republic of Azerbaijan
The current politico-cultural trends in the Republic of Azerbaijan, focused on "historical strangeness with Iran", have led to its divergence from Iran. One of the missions of Iranian Radio Azeri World Service is to explain the historical connections and raptures to the public opinion of its northern neighbor. Applying agenda setting and framing theories, the aim of this article is to evaluate ...
متن کاملAutomatic Spoken Document Processing for Retrieval and Browsing
Ever increasing computing power and connectivity bandwidth together with falling storage costs is resulting in overwhelming amounts of multimedia data being produced, exchanged, and stored. One key application area in this realm is the search and retrieval of spoken audio documents. As storage becomes cheaper, the availability and usefulness of large collections of spoken documents is limited s...
متن کاملCombining pattern recognition and deep-learning-based algorithms to automatically detect commercial quadcopters using audio signals (Research Article)
Commercial quadcopters with many private, commercial, and public sector applications are a rapidly advancing technology. Currently, there is no guarantee to facilitate the safe operation of these devices in the community. Three different automatic commercial quadcopters identification methods are presented in this paper. Among these three techniques, two are based on deep neural networks in whi...
متن کاملAutomatic Alignment and Error Correction of Human Generated Transcripts for Long Speech Recordings
In this paper we examine the issues of aligning and correcting approximate human generated transcripts for long audio files. Accurate time-aligned transcriptions help provide easier access to audio materials by aiding downstream applications such as the indexing, summarizing and retrieving of audio segments. Accurate time alignments are also necessary when incorporating audio data into the trai...
متن کاملAnalysis of Musical Audio for Polyphonic Transcription 1st Year Report
This report centres around some of this issues involved in automatic transcription of polyphonic musical audio signals. That is, representing the information contained in the audio in such a way as to be recognisable and usable by a musician. First, a review of the various fields which have a bearing on the subject is put forward, including music, music psychology, auditory psychology and signa...
متن کامل