# Estimating Phoneme Class Conditional Probabilities from Raw Speech Signal using Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1304.1018 · HTML: https://mlsanity.com/paper/1304.1018/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2013.

## Built on by (most cited first, 9 of 9)

- [LEAF: A Learnable Frontend for Audio Classification](https://mlsanity.com/paper/2101.08596/) (2021)
- [Opening the Black Box of wav2vec Feature Encoder](https://mlsanity.com/paper/2210.15386/) (2022)
- [emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography](https://mlsanity.com/paper/2410.20081/) (2024)
- [EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use](https://mlsanity.com/paper/2207.05508/) (2022)
- [Interpreting intermediate convolutional layers of generative CNNs trained on waveforms](https://mlsanity.com/paper/2104.09489/) (2021)
- [Interpreting intermediate convolutional layers in unsupervised acoustic word classification](https://mlsanity.com/paper/2110.02375/) (2021)
- [Evaluating raw waveforms with deep learning frameworks for speech emotion recognition](https://mlsanity.com/paper/2307.02820/) (2023)
- [Low-Level Physiological Implications of End-to-End Learning of Speech Recognition](https://mlsanity.com/paper/2208.11700/) (2022)
- [Predicting Individual Depression Symptoms from Acoustic Features During Speech](https://mlsanity.com/paper/2406.16000/) (2024)

## Abstract (arXiv)

In hybrid hidden Markov model/artificial neural networks (HMM/ANN) automatic speech recognition (ASR) system, the phoneme class conditional probabilities are estimated by first extracting acoustic features from the speech signal based on prior knowledge such as, speech perception or/and speech production knowledge, and, then modeling the acoustic features with an ANN. Recent advances in machine learning techniques, more specifically in the field of image processing and text processing, have shown that such divide and conquer strategy (i.e., separating feature extraction and modeling steps) may not be necessary. Motivated from these studies, in the framework of convolutional neural networks (CNNs), this paper investigates a novel approach, where the input to the ANN is raw speech signal and the output is phoneme class conditional probability estimates. On TIMIT phoneme recognition task, we study different ANN architectures to show the benefit of CNNs and compare the proposed approach against conventional approach where, spectral-based feature MFCC is extracted and modeled by a multilayer perceptron. Our studies show that the proposed approach can yield comparable or better phoneme recognition performance when compared to the conventional approach. It indicates that CNNs can learn features relevant for phoneme classification automatically from the raw speech signal.