Convolutional Neural Networks-based continuous speech recognition using raw speech signal

By Dimitri Palaz, Mathew Magimai-Doss, Ronan Collobert. 2015

179 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

A Wavenet for Speech Denoising (2017, methodology): “To this end, discriminative models have been used in an end-to-end learning fashion for speech classification [6, 7, 8].”
Analysis of CNN-based speech recognition system using raw speech as input (2015, background): “We showed that these filters respond to different frequency bandwidths [16], and that they show some level of invariance across databases [17].”
Listening while speaking: Speech chain by deep learning (2017, background): “Many state-of-the-art performances in ASR [13, 14, 15] and TTS [16, 17, 18] tasks have been successfully constructed based on neural network frameworks.”
RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification (2019, methodology): “In speech recognition, studies such as those of Palaz et al. , Sainath et al. , and Hoshen et al. deal with raw waveforms as input [1–3].”
Fully Convolutional Speech Recognition (2018, background): “Nonetheless, convolutional architectures are prevalent when learning from the raw waveform [15, 16, 17, 14, 18], because they naturally model the computation of standard features such as mel-filterbanks.”
Raw waveform-based speech enhancement by fully convolutional networks (2017, background): “Therefore, most studies have employed the CNN model for analyzing raw waveforms [22-26, 28].”
Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms (2017, methodology): “There are some works that use 0.6 ms (10 samples at 16 kHz audio) as a stride length [6, 7], but they used a CNN model only with three convolution layers, which is not sufﬁcient to learn the complex structure of musical signals.”
Attention-based Wav2Text with feature transfer learning (2017, background): “[2, 3] proposed a convolutional neural network (CNN) to directly train an acoustic model from the raw speech waveform.”
FLOP: Federated Learning on Medical Datasets using Partial Networks (2021, methodology): “The model architectures in this paper are based on Convolutional Neural Networks (CNNs), which have achieved great empirical success in computer vision [12, 18], natural language processing [15, 37] and speech recognition [2, 23].”
XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging (2020, methodology): “One example is audio/speech in which raw audio signals [60] can be combined with its derived representations, such as mel-scale spectrogram [61] and gammatone spectrogram [62], for recognition tasks.”
Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks (2016, methodology): “Again, there are characteristic examples from speech and acoustics in [6, 19, 27, 20, 10].”