speech-processing

Real-time Voice Activity Detection (VAD) with some example use case like simple voice bot and live transcription (realtime transcription)

Speaker diarization for Python — "who spoke when?" CPU-only, no API keys, Apache 2.0. ~10.8% DER on VoxConverse, 8x faster than real-time.

ElevateAI - Speech-to-text API Python SDK

Awesome Audio-Visual Intelligence, Survey of Audio-Visual Intelligence

Callytics is an advanced call analytics solution that leverages speech recognition and large language models (LLMs) technologies to analyze phone conversations from customer service and call centers.

A speech-to-text framework and bot for Discord. Take control of your Discord server using speech and voice commands. Can also be useful for hearing impaired and deaf people.

《SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks》Speech processing with prompting paradigm

:white_check_mark: A list of speech recognition learning resources including courses, books, tutorials, papers and toolkits.

Vietnamese speech recognition using Wavenet

A Wyoming protocol ASR proxy that verifies speaker identity and isolates voice commands from background noise before forwarding audio to a downstream speech-to-text service. Designed for Home Assistant voice pipelines to prevent false activations from TVs, radios, and other people - and to deliver clean transcripts even in noisy environments.

Wav2vec 2.0 Self-Supervised Pretraining

Spokestack: give your React Native app a voice interface!

Speaker identification powered by pyannote and resemblyzer

A framework for automatic speech recognition

Links to Belarusian NLP and Speech resources

Spokestack: give your iOS app a voice interface!

Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding

The proposed Voice-based Email System uses AI (voice commands) that will make the email system very easily accessible to visually challenged people and also help society. Accessibility is the most important feature that is considered while developing this system.

Linux Voice Assistant for to Make Your Work Easier

Multimodal Emotion eXpression Capture Amsterdam. Pipeline for capturing emotion expressions from multiple modalities (video, audio, text) in the wild.