Transformer model for ASR/SLU with early-exit mechanism

Collection of Open Source Speech Data

Transformer model for ASR/SLU with early-exit mechanism

An anthology of recent continual learning papers, where people interested in this fascinating topic can start discovering its multidimensional representations.

The aim of this project is to build a multilingual ASR in which phonological syllables are considered as subwords.

Fine-tune wav2vec2-xls-r on data from low-resource-languages

This is the official implementation of " Enhancing Embeddings for Speech Classification in Noisy Conditions"

End-to-End Keyword Spotting (E2E-KWS) using a character level LSTM

End-to-End Keyword Spotting (E2E-KWS) using a character level LSTM

Intent Classification using the Fluent Speech Commands Dataset

Implementation of ConflictNET: End-to-End Learning for Speech-Based Conflict Intensity Estimation - IEEE Signal Processing Letters

A better, faster, stronger version of the unbounded interleaved-state recurrent neural network (UIS-RNN)