Aalto Speech Research's repositories
Wav2vec2Interpretation
scripts and images for article "Investigating wav2vec2 context representations and the effects of fine-tuning, a case-study of a Finnish model"
speechbrain-cl
Implementation of different curriculum learning (CL) methods for speechbrain's ASR recipes.
fi-parliament-tools
Tools for downloading and processing Finnish parliament data
kaldi-sb-north-sme
Kaldi + SpeechBrain + W2V2 models for Northern Sami
aalto-asr-preprocessor
Aalto ASR preprocessing tool for preparing texts.
Compare2020
Aalto's solutions for the 2020 Computational Paralinguistics Challenges: Breathing & Masks
ComParE2023
Code repository for the experiments conducted for the ComParE 2023 challenge.
fin-parl-lahjoita-puhetta-s5
Speech Recognition experiments combining Lahjoita Puhetta with Finnish Parliament
l2-speech-scoring-tools
Implementation of automatic speech rating systems for second language (L2) learners of Finnish and Finland Swedish
lahjoita-puhetta-resources
A collection of resources related to the Lahjoita puhetta speech corpus.
multitask-wav2vec2
Custom 🤗 Transformers for training multi-task wav2vec2 models that perform ASR and speech classification tasks simultaneously as described in Getman, Y., Al-Ghezi, R., Grósz, T., Kurimo, M. (2023) Multi-task wav2vec2 Serving as a Pronunciation Training System for Children.
attn-hmm-jrnl-analysis-notebook
A notebook that looks at results from HMM and AED ASR systems.
AUUH-SegmentationST
The AUUH implementations for the SIGMOPRHON 2022 Shared Task on Morpheme Segmentation
colloquial-Finnish-wav2vec2
Scripts for training colloquial Finnish wav2vec2 models
equal-data-matched-encoder-experiments
Implementations for the Matched Encoder and Equal Data comparisons of HMM/DNN and Attention-based ASR systems
ite-typing-dataset
Scripts and jupyter notebooks to process and analyse ITE typing dataset
lahjoita-puhetta-baseline-kaldi
Kaldi ASR system for Lahjoita puhetta corpus
northern-sami-asr
Scripts for adapting large speech foundation models for Northern Sámi ASR
run-nemo-on-puhti
This directory runs NeMo on Puhti
sb-2015-2020-kevat_e2e
AED implementations for Finnish parliament Train20 (Includes Train16 and Train Comb as well)
sb-fin-parl-2015-2020-kevat
SpeechBrain recipes for Finnish Parliament data - HMM/DNN
sb-libri-hmmdnn
Librispeech HMM/DNN and AED SpeechBrain experiments
setup-asr-on-csc
How to setup a Kaldi and SpeechBrain environment on CSC Puhti