Basque-speaking Smart Speaker based on Mycroft AI

نویسندگان

چکیده

Abstract Speech–driven virtual assistants, known as smart speakers, such Amazon Echo and Google Home, are increasingly used. However, commercial speakers only support a handful of languages. Even languages for which ASR TTS technology is available, many official EU member state languages, not supported due to disinterest derived from their – relatively speaking rather small number speakers. This problem even more crucial minority expected anytime soon, or ever. In this ELG pilot project we developed Basque–speaking speaker, making use the open source speaker Mycroft AI Elhuyar Foundation’s speech technologies Basque. Apart getting it speak Basque, one our goals was make privacy friendly, non–gendered local services, because these usual issues concern. The has also served improve art Basque technology.

برای دانلود باید عضویت طلایی داشته باشید

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

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

SDBM-Based Speaker Recognition for Speaking Style Variations

There are many factors corresponding to performance degradation of an actual speaker recognition system. Mismatch in speaking style of a target speaker during training and testing is an important one. When a client enrolls in a system, it is natural for him/her to speak in a spontaneous way. However, it is difficult to maintain the same speaking style throughout test phases. In view of this sit...

متن کامل

Within-speaker variability due to speaking manners

Some preliminary investigations of within-speaker variations due to voluntary and induced speaking manners have been performed. The ultimate aim of the investigations was to suggest methods to take care of within-speaker variations in automatic speaker verification. Special software was developed to systematically elicit different types of voluntary and involuntary speech variations that might ...

متن کامل

Robust Speech Recognition in Distant Environment Based on Speaker Position and Speaking Direction Detection

In a practical environment, channel distortion may severly degrade speech recognition performance. In this paper, we propose a robust speech recognition method using real-time Cepstral Mean Normalization (CMN) [1] based on speaker position and speaking direction detection. We first estimate the speaker position in a 3-D space based on the time delay of arrival (TDOA) between distinct microphone...

متن کامل

Building a Basque/Spanish bilingual database for speaker verification

Research groups aiming to record new speech databases for minority languages have to face a series of difficulties, such as the lack of previous resources, the scarcity of fluent speakers and the shortage of funding for the project. Sometimes it is possible to take advantage of recording campaigns for other projects, and extend them in order to make some recordings in that language for every co...

متن کامل

Estimation of Gas Mixture Compressibility Factor and Viscosity based on AI and Experimental DataEstimation of Gas Mixture Compressibility Factor and Viscosity based on AI and Experimental Data

Compressibility factor and viscosity of natural gasses are of great importance in petroleum and chemical engineering. To calculate the natural gas properties in the pipelines, storage systems and reservoirs, the exact values of gas compressibility factor and viscosity are required. A new method that allows accurate determination of compressibility factor and gas viscosity for all types of: swee...

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

ژورنال

عنوان ژورنال: Cognitive technologies

سال: 2022

ISSN: ['2197-6635', '1611-2482']

DOI: https://doi.org/10.1007/978-3-031-17258-8_15