Mirco Ravanelli

Dehestani Amirali

Collaborateur·rice de recherche - Concordia University

Seina Assadian

Collaborateur·rice de recherche - Concordia University

Cordelle Briac

Collaborateur·rice de recherche - Concordia University

Gallegati Caterina

Stagiaire de recherche - Concordia

Victor Cruz

Maîtrise recherche - Concordia

Luca Della Libera

Doctorat - Concordia

Wagner Drew

Maîtrise recherche - Concordia

Gianfranco Dumoulin Bertucci

Maîtrise recherche - Concordia

Site web

nadine.el-mufti@mila.quebec

Nadine El-Mufti

Maîtrise recherche - Concordia

Site web

Maab Elrashid Ahmed Mohamed

Google Scholar

Doctorat - Concordia

Bonzi Francesco

Doctorat - Concordia

Alessio Giuseppe Alessio

Collaborateur·rice de recherche - International School for Advanced Studies (Trieste, Italy)

Salman Sami Hussain Ali

Collaborateur·rice de recherche - Concordia University

Eleonora Mancini

Collaborateur·rice alumni - UdeM

SpeechBrain 1.0 : rendre l’IA conversationnelle accessible à tout le monde

Google Scholar

Jama Mohamud

Doctorat - UdeM

Co-superviseur⋅e :

Doctorat - Concordia

Doctorat - Concordia

Co-superviseur⋅e :

Peter Peter

Postdoctorat - McGill

Doctorat - UdeM

Billets de blogue

13 juin 2024

par

Mirco Ravanelli

Lire l'article

Introducing SpeechBrain: A general-purpose PyTorch speech processing toolkit

28 avril 2021

Voici SpeechBrain : Une boîte à outils polyvalente de traitement de la parole basée sur PyTorch

par

Mirco Ravanelli

Loren Lugosch

Lire l'article

Publications

Multi-Task Self-Supervised Learning for Robust Speech Recognition

Jianyuan Zhong

Santiago Pascual

Pawel Swietojanski

Joao Monteiro

Jan Trmal

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To t… (voir plus)ake a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that combines a convolutional encoder followed by multiple neural networks, called workers, tasked to solve self-supervised problems (i.e., ones that do not require manual annotations as ground truth). PASE was shown to capture relevant speech information, including speaker voice-print and phonemes. This paper proposes PASE+, an improved version of PASE for robust speech recognition in noisy and reverberant environments. To this end, we employ an online speech distortion module, that contaminates the input signals with a variety of random disturbances. We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks. Finally, we refine the set of workers used in self-supervision to encourage better cooperation.Results on TIMIT, DIRHA and CHiME-5 show that PASE+ significantly outperforms both the previous version of PASE as well as common acoustic features. Interestingly, PASE+ learns transferable representations suitable for highly mismatched acoustic conditions.

2020-05-04

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)

Retrieving Signals with Deep Complex Extractors

Chiheb Trabelsi

Olexa Bilaniuk

Ousmane Dia

Ying Zhang

Jonathan Binas

Negar Rostamzadeh

Chris Pal

Recent advances have made it possible to create deep complex-valued neural networks. Despite this progress, many challenging learning tasks … (voir plus)have yet to leverage the power of complex representations. Building on recent advances, we propose a new deep complex-valued method for signal retrieval and extraction in the frequency domain. As a case study, we perform audio source separation in the Fourier domain. Our new method takes advantage of the convolution theorem which states that the Fourier transform of two convolved signals is the elementwise product of their Fourier transforms. Our novel method is based on a complex-valued version of Feature-Wise Linear Modulation (FiLM) and serves as the keystone of our proposed signal extraction method. We also introduce a new and explicit amplitude and phase-aware loss, which is scale and time invariant, taking into account the complex-valued components of the spectrogram. Using the Wall Street Journal Dataset, we compared our phase-aware loss to several others that operate both in the time and frequency domains and demonstrate the effectiveness of our proposed signal extraction method and proposed loss.

2019-10-21

NeurIPS.cc/2019/Workshop/Deep_Inverse (poster)

openreview.net

Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks

Santiago Pascual

Joan Parets I Serra

Antonio Bonafonte

Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech sig… (voir plus)nals, which are often characterized by long sequences with a complex hierarchical structure. Some recent works, however, have shown that it is possible to derive useful speech representations by employing a self-supervised encoder-discriminator approach. This paper proposes an improved self-supervised method, where a single neural encoder is followed by multiple workers that jointly solve different self-supervised tasks. The needed consensus across different tasks naturally imposes meaningful constraints to the encoder, contributing to discover general representations and to minimize the risk of learning superficial ones. Experiments show that the proposed approach can learn transferable, robust, and problem-agnostic features that carry on relevant information from the speech signal, such as speaker identity, phonemes, and even higher-level features such as emotional cues. In addition, a number of design choices make the encoder easily exportable, facilitating its direct usage or adaptation to different problems.

2019-09-15

Interspeech 2019 (publié)

Learning Speaker Representations with Mutual Information

Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependen… (voir plus)ce are promising tools for learning these representations in an unsupervised way. Even though the mutual information between two random variables is hard to measure directly in high dimensional spaces, some recent studies have shown that an implicit optimization of MI can be achieved with an encoder-discriminator architecture similar to that of Generative Adversarial Networks (GANs). In this work, we learn representations that capture speaker identities by maximizing the mutual information between the encoded representations of chunks of speech randomly sampled from the same sentence. The proposed encoder relies on the SincNet architecture and transforms raw speech waveform into a compact feature vector. The discriminator is fed by either positive samples (of the joint distribution of encoded chunks) or negative samples (from the product of the marginals) and is trained to separate them. We report experiments showing that this approach effectively learns useful speaker representations, leading to promising results on speaker identification and verification tasks. Our experiments consider both unsupervised and semi-supervised settings and compare the performance achieved with different objective functions.

2019-09-15

Interspeech 2019 (publié)

Speech Model Pre-training for End-to-End Spoken Language Understanding

Loren Lugosch

Patrick Ignoto

Vikrant Singh Tomar

Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map spe… (voir plus)ech directly to intent through a single trainable model. Achieving high accuracy with these end-to-end models without a large amount of training data is difficult. We propose a method to reduce the data requirements of end-to-end SLU in which the model is first pre-trained to predict words and phonemes, thus learning good features for SLU. We introduce a new SLU dataset, Fluent Speech Commands, and show that our method improves performance both when the full dataset is used for training and when only a small subset is used. We also describe preliminary experiments to gauge the model's ability to generalize to new phrases not heard during training.

2019-09-15

Interspeech 2019 (publié)

The Pytorch-kaldi Speech Recognition Toolkit

Titouan Parcollet

The availability of open-source software is playing a remarkable role in the popularization of speech recognition and deep learning. Kaldi, … (voir plus)for instance, is nowadays an established framework used to develop state-of-the-art speech recognizers. PyTorch is used to build neural networks with the Python language and has recently spawn tremendous interest within the machine learning community thanks to its simplicity and flexibility.The PyTorch-Kaldi project aims to bridge the gap between these popular toolkits, trying to inherit the efficiency of Kaldi and the flexibility of PyTorch. PyTorch-Kaldi is not only a simple interface between these software, but it embeds several useful features for developing modern speech recognizers. For instance, the code is specifically designed to naturally plug-in user-defined acoustic models. As an alternative, users can exploit several pre-implemented neural networks that can be customized using intuitive configuration files. PyTorch-Kaldi supports multiple feature and label streams as well as combinations of neural networks, enabling the use of complex neural architectures. The toolkit is publicly-released along with a rich documentation and is designed to properly work locally or on HPC clusters.Experiments, that are conducted on several datasets and tasks, show that PyTorch-Kaldi can effectively be used to develop modern state-of-the-art speech recognizers.

2019-05-12

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)

Quaternion Recurrent Neural Networks

Titouan Parcollet

Mohamed Morchid

Georges Linarès

Chiheb Trabelsi

Renato De Mori

Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term d… (voir plus)ependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or images recognition, involve multi-dimensional input features that are characterized by strong internal dependencies between the dimensions of the input vector. We propose a novel quaternion recurrent neural network (QRNN), alongside with a quaternion long-short term memory neural network (QLSTM), that take into account both the external relations and these internal structural dependencies with the quaternion algebra. Similarly to capsules, quaternions allow the QRNN to code internal dependencies by composing and processing multidimensional features as single entities, while the recurrent operation reveals correlations between the elements composing the sequence. We show that both QRNN and QLSTM achieve better performances than RNN and LSTM in a realistic application of automatic speech recognition. Finally, we show that QRNN and QLSTM reduce by a maximum factor of 3.3x the number of free parameters needed, compared to real-valued RNNs and LSTMs to reach better results, leading to a more compact representation of the relevant information.

2019-01-01

ICLR.cc/2019/Conference (poster)

openreview.net

Speaker Recognition from Raw Waveform with SincNet

Deep learning is progressively gaining popularity as a viable alternative to i-vectors for speaker recognition. Promising results have been … (voir plus)recently obtained with Convolutional Neural Networks (CNNs) when fed by raw speech samples directly. Rather than employing standard hand-crafted features, the latter CNNs learn low-level speech representations from waveforms, potentially allowing the network to better capture important narrow-band speaker characteristics such as pitch and formants. Proper design of the neural network is crucial to achieve this goal.This paper proposes a novel CNN architecture, called SincNet, that encourages the first convolutional layer to discover more meaningful filters. SincNet is based on parametrized sinc functions, which implement band-pass filters. In contrast to standard CNNs, that learn all elements of each filter, only low and high cutoff frequencies are directly learned from data with the proposed method. This offers a very compact and efficient way to derive a customized filter bank specifically tuned for the desired application.Our experiments, conducted on both speaker identification and speaker verification tasks, show that the proposed architecture converges faster and performs better than a standard CNN on raw waveforms.

2018-12-18

2018 IEEE Spoken Language Technology Workshop (SLT) (publié)

Speech and Speaker Recognition from Raw Waveform with SincNet

Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones. A recent tre… (voir plus)nd in speech and speaker recognition consists in discovering these representations starting from raw audio samples directly. Differently from standard hand-crafted features such as MFCCs or FBANK, the raw waveform can potentially help neural networks discover better and more customized representations. The high-dimensional raw inputs, however, can make training significantly more challenging. This paper summarizes our recent efforts to develop a neural architecture that efficiently processes speech from audio waveforms. In particular, we propose SincNet, a novel Convolutional Neural Network (CNN) that encourages the first layer to discover meaningful filters by exploiting parametrized sinc functions. In contrast to standard CNNs, which learn all the elements of each filter, only low and high cutoff frequencies of band-pass filters are directly learned from data. This inductive bias offers a very compact way to derive a customized front-end, that only depends on some parameters with a clear physical meaning. Our experiments, conducted on both speaker and speech recognition, show that the proposed architecture converges faster, performs better, and is more computationally efficient than standard CNNs.

2018-12-13

ArXiv (prépublication)

Interpretable Convolutional Filters with SincNet

Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to l… (voir plus)earn complex and abstract representations, that are progressively obtained by combining simpler ones. Nevertheless, the internal "black-box" representations automatically discovered by current neural architectures often suffer from a lack of interpretability, making of primary interest the study of explainable machine learning techniques. This paper summarizes our recent efforts to develop a more interpretable neural model for directly processing speech from the raw waveform. In particular, we propose SincNet, a novel Convolutional Neural Network (CNN) that encourages the first layer to discover more meaningful filters by exploiting parametrized sinc functions. In contrast to standard CNNs, which learn all the elements of each filter, only low and high cutoff frequencies of band-pass filters are directly learned from data. This inductive bias offers a very compact way to derive a customized filter-bank front-end, that only depends on some parameters with a clear physical meaning. Our experiments, conducted on both speaker and speech recognition, show that the proposed architecture converges faster, performs better, and is more interpretable than standard CNNs.

2018-11-23

ArXiv (prépublication)

Twin Regularization for online speech recognition

Dmitriy Serdyuk

Online speech recognition is crucial for developing natural human-machine interfaces. This modality, however, is significantly more challeng… (voir plus)ing than off-line ASR, since real-time/low-latency constraints inevitably hinder the use of future information, that is known to be very helpful to perform robust predictions. A popular solution to mitigate this issue consists of feeding neural acoustic models with context windows that gather some future frames. This introduces a latency which depends on the number of employed look-ahead features. This paper explores a different approach, based on estimating the future rather than waiting for it. Our technique encourages the hidden representations of a unidirectional recurrent network to embed some useful information about the future. Inspired by a recently proposed technique called Twin Networks, we add a regularization term that forces forward hidden states to be as close as possible to cotemporal backward ones, computed by a "twin" neural network running backwards in time. The experiments, conducted on a number of datasets, recurrent architectures, input features, and acoustic conditions, have shown the effectiveness of this approach. One important advantage is that our method does not introduce any additional computation at test time if compared to standard unidirectional recurrent networks.

2018-09-02

Interspeech 2018 (publié)

Light Gated Recurrent Units for Speech Recognition

Philemon Brakel

Maurizio Omologo

A field that has directly benefited from the recent advances in deep learning is automatic speech recognition (ASR). Despite the great achie… (voir plus)vements of the past decades, however, a natural and robust human–machine speech interaction still appears to be out of reach, especially in challenging environments characterized by significant noise and reverberation. To improve robustness, modern speech recognizers often employ acoustic models based on recurrent neural networks (RNNs) that are naturally able to exploit large time contexts and long-term speech modulations. It is thus of great interest to continue the study of proper techniques for improving the effectiveness of RNNs in processing speech signals. In this paper, we revise one of the most popular RNN models, namely, gated recurrent units (GRUs), and propose a simplified architecture that turned out to be very effective for ASR. The contribution of this work is twofold: First, we analyze the role played by the reset gate, showing that a significant redundancy with the update gate occurs. As a result, we propose to remove the former from the GRU design, leading to a more efficient and compact single-gate model. Second, we propose to replace hyperbolic tangent with rectified linear unit activations. This variation couples well with batch normalization and could help the model learn long-term dependencies without numerical issues. Results show that the proposed architecture, called light GRU, not only reduces the per-epoch training time by more than 30% over a standard GRU, but also consistently improves the recognition accuracy across different tasks, input features, noisy conditions, as well as across different ASR paradigms, ranging from standard DNN-HMM speech recognizers to end-to-end connectionist temporal classification models.

2018-04-01

IEEE Transactions on Emerging Topics in Computational Intelligence (publié)