Latvian speech-to-text transcription service

نویسندگان

  • Askars Salimbajevs
  • Jevgenijs Strigins
چکیده

In this demonstration paper, we introduce the first publicly available Speech-To-Text transcription service for the Latvian language. We present its main features, the details of automatic speech recognition (ASR) system used in this service, software architecture, and an evaluation of recognition quality. The service will provide regular people with the opportunity to transcribe their own audio files for various purposes, such as lectures, meetings, etc. Also, the users will be given an opportunity to give their evaluation and feedback about the quality and usability of this service, which will be used by developers to make changes in the ASR in order to improve it.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

System for Speech Transcription and Post-Editing in Microsoft Word

In this demonstration paper, we introduce a transcription service that can be used for transcription of different meetings, sessions etc. The service performs speaker diarization, automatic speech recognition, punctuation restoration and produces human-readable transcripts as special Microsoft Word documents that have audio and word alignments embedded. Thereby, a widely-used word processor is ...

متن کامل

Development of Text-To-Speech system for Latvian

This paper describes the development of the first text-to-speech (TTS) synthesizer for Latvian language. It provides an overview of the project background and describes the general approach, the choices and particular implementation aspects of the principal TTS components: NLP, prosody and waveform generation. A novelty for waveform synthesis is the combination of corpusbased unit selection met...

متن کامل

Media monitoring system for latvian radio and TV broadcasts

Media monitoring allows to capture media exposure of people, organizations and other important topics. This paper presents a media monitoring system for Latvian radio and television broadcasts. This system uses an automatic speech recognition (ASR) module to convert audio and video files to text and to extract keywords of interest. The system has been developed in close cooperation with Latvian...

متن کامل

Designing the Latvian Speech Recognition Corpus

In this paper the authors present the first Latvian speech corpus designed specifically for speech recognition purposes. The paper outlines the decisions made in the corpus designing process through analysis of related work on speech corpora creation for different languages. The authors provide also guidelines that were used for the creation of the Latvian speech recognition corpus. The corpus ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015