Speaker dependent Acoustic-to-Articulatory Inversion Model
Model Overview
This model performs speaker dependent Acoustic-to-Articulatory Inversion (AAI), predicting articulatory trajectories from acoustic features. This model trained in the simultaneously recorded speech and Electromagnetic Articulography (EMA) datasets of one speakers (80%) and tested in unseen speech (remaining 20%) of the same speaker. The neural network is built using PyTorch and leverages BiLSTM (Bidirectional Long Short-Term Memory) layers to capture temporal dependencies in the acoustic data. CNN is used used to smooth the predicted trajectories to make it natural. The input is composed of multi-frame MFCC (Mel-Frequency Cepstral Coefficients) features, and the output is a set of predicted articulatory positions over time.
Intended Use
The model is designed for speech researchers and professionals who are interested in understanding the relationship between speech acoustics and articulatory movements. It can be applied in linguistic research, speech synthesis, and speech therapy.
Use Cases
- Speech Analysis: To study how different speech sounds relate to articulatory positions.
- Speech Synthesis: As a part of systems generating speech from articulatory features.
- Speech Therapy: Analyzing articulatory trajectories for individuals with speech disorders.
Dependencies
- python 3.7.3
- numpy 1.16.3
- pytorch 1.1.0
- scipy 1.2.1
- librosa 0.6.3
- matplotlib
- psutil
Trained Datasets
Being Speaker dependent this model trained on one particular speaker:
Model Architecture
- Hidden Dimension: 400
- Input Dimension: 429 (acoustic features per frame)
- Output Dimension: 16 (articulatory trajectories)
- Batch Size: 8
- BiLSTM Layers: 2 bidirectional LSTM layers
- CNN: 1DCNN
- Linear Layers: Input and output layers with batch normalization
The architecture is designed to accommodate smoothing of articulatory in preprocessing with customizable cutoff frequencies.
Model Training
- Optimizer: Adam
- Loss Functions: Combination of RMSE and Pearson correlation to capture both error minimization and correlation maximization.
- Training Procedure: Early stopping based on validation loss was employed to prevent overfitting, with periodic adjustments of learning rate if the validation loss increased.
- Epochs: Trained over multiple epochs with batch updates and dynamic learning rate adjustments.
Evaluation
The model was evaluated on the 20% sample of the same speaker, with metrics such as RMSE (Root Mean Square Error) and Pearson correlation used to quantify performance.
The evaluation result is:
- RMSE: 0.761
- PCC: 0.810
Citation Information
Paper link: https://doi.org/10.3233/JIFS-219386
@article{pillaibilstm,
title={BiLSTM-CNN with fixed weight approach for tracking speech articulatory features},
author={Pillai, Leena G and Muhammad Noorul Mubarak, D and Sherly, Elizabeth},
journal={Journal of Intelligent and Fuzzy Systems},
pages={1--14},
publisher={IOS Press},
DOI={https://doi.org/10.3233/JIFS-219386 }
}