Search Results for "front-end"

Omnilingual-ASR is a research codebase exploring automatic speech recognition that generalizes across a very large number of languages using shared modeling and training recipes. It focuses on leveraging self-supervised audio pretraining and scalable fine-tuning so low-resource languages can benefit from high-resource data. The project provides data preparation pipelines, training scripts, decoding utilities, and evaluation tools so researchers can reproduce results and extend to new...

...It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains. SpeechBrain supports state-of-the-art methods for end-to-end speech recognition, including models based on CTC, CTC+attention, transducers, transformers, and neural language models relying on recurrent neural networks and transformers. Speaker recognition is already deployed in a wide variety of realistic applications. SpeechBrain provides different models for speaker recognition, including X-vector, ECAPA-TDNN, PLDA, and contrastive learning. ...

FireRedASR is an industrial-grade family of open-source automatic speech recognition models designed to provide high-precision speech-to-text performance across languages including Mandarin, English, and various Chinese dialects, achieving new state-of-the-art benchmarks on public test sets. The project includes multiple model variants to meet different application needs, such as high-accuracy end-to-end interaction using an encoder-adapter-LLM framework and efficient real-time recognition using attention-based encoder-decoder architectures, giving developers flexibility in balancing performance and resource constraints. FireRedASR not only excels in traditional speech recognition tasks but also demonstrates strong capability in challenging scenarios like singing lyrics recognition, where accurate transcription is often difficult for conventional models.

Note about this image This image contains a system based on Linux MX, which was created to improve accessibility within the Linux environment. The distribution uses the Cinnamon desktop interface, which is configured to be operated using voice commands and outputs. The user interface and the control of your own devices and home automation systems can be customized and extended. The voice control program MiceStTM.py was developed to enable easy adaptation to other languages. However, only...

MAIA (MyApp Intelligence Artificial) is designed to provide a foundation for building your own voice-controlled assistant with Python. It uses various libraries and modules for speech recognition, text-to-speech synthesis, and custom functionality.

ASRT is an end-to-end deep-learning Chinese ASR system built with TensorFlow/Keras, using convolution + CTC and a Max-Entropy HMM language model. It provides a REST/gRPC server backend and client SDKs in multiple languages (Python, Java, Go, Windows). Notably lightweight, it performs well without needing GPU acceleration and runs across platforms, targeting developers and researchers building Chinese voice interfaces.

This product recognizes oral commands and translates them to domotic orders for a domotic system. This product does not implement a domotic system. This product is an interface to be plugged to a domotic system. The speech recognition is done by an arduino UNO board and an EasyVR shield. Available oral commands are generated from a house description file in XML format. The oral commands have to be trained for a specific users. For this purpose 2 interfaces are provided: a command line...

Pythia is a natural language question answering system, which uses Speech Recognition and Text To Speech technologies to communicate with the user.

Orcus smartHome is a voice/sensor/web-interactive home automation, streaming media, security monitoring system with voice recognition, speech synthesis, scheduling via Google calendar, and web interface.

Voice Conference Manager uses VoiceXML and CCXML to control speech recognition, text to speech, and voice biometrics for a telephone conference service. Say the names or numbers of people and VCM places them into the call. Can be hosted on public servers

GoMad is a speech recognition system that allows you to control windows-based applications using your voice as input, instead of your mouse and keyboard.

Provides a voice interface for applications via a plug in system. Allows the inclusion of voice recognition in an application with a minimum of effort.