571 citations · 1.1k across the 10 of their papers we have counts for
13 papers
Discrete Audio Tokens: More Than a Survey!
Pooneh Mousavi, Gallil Maimon, Adel Moumen +18
Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and infere…
Unsupervised ASR via Cross-Lingual Pseudo-Labeling
Tatiana Likhomanenko, Loren Lugosch, Ronan Collobert
Recent work has shown that it is possible to train an automatic speech recognition (ASR) system using only unpaired audio and text. Existing unsupervised AS…
Pseudo-Labeling for Massively Multilingual Speech Recognition
Loren Lugosch, Tatiana Likhomanenko, Gabriel Synnaeve +1
Semi-supervised learning through pseudo-labeling has become a staple of state-of-the-art monolingual speech recognition systems. In this work, we extend pseudo-labeling to massivel…
SpeechBrain: A General-Purpose Speech Toolkit
Mirco Ravanelli, Titouan Parcollet, Peter Plantinga +18
SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to facilitate the research and development of neural speech processing technologies by being simple, fle…
Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers
Loren Lugosch, Piyush Papreja, Mirco Ravanelli +2
This paper introduces Timers and Such, a new open source dataset of spoken English commands for common voice control use cases involving numbers. We describe the gap in existing sp…
Surprisal-Triggered Conditional Computation with Neural Networks
Loren Lugosch, Derek Nowrouzezahrai, Brett H. Meyer
Autoregressive neural network models have been used successfully for sequence generation, feature extraction, and hypothesis scoring. This paper presents yet another use for these…
Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models
Loren Lugosch, Brett Meyer, Derek Nowrouzezahrai +1
End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employi…
Speech Model Pre-training for End-to-End Spoken Language Understanding
Loren Lugosch, Mirco Ravanelli, Patrick Ignoto +2
Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single…
DONUT: CTC-based Query-by-Example Keyword Spotting
Loren Lugosch, Samuel Myer, Vikrant Singh Tomar
Keyword spotting--or wakeword detection--is an essential feature for hands-free operation of modern voice-controlled devices. With such devices becoming ubiquitous, users might wan…
Learning from the Syndrome
Loren Lugosch, Warren J. Gross
In this paper, we introduce the syndrome loss, an alternative loss function for neural error-correcting decoders based on a relaxation of the syndrome. The syndrome loss penalizes…
Tone Recognition Using Lifters and CTC
Loren Lugosch, Vikrant Singh Tomar
In this paper, we present a new method for recognizing tones in continuous speech for tonal languages. The method works by converting the speech signal to a cepstrogram, extracting…
Deep Learning Methods for Improved Decoding of Linear Codes
Eliya Nachmani, Elad Marciano, Loren Lugosch +3
The problem of low complexity, close to optimal, channel decoding of linear codes with short to moderate block length is considered. It is shown that deep learning methods can be u…
Neural Offset Min-Sum Decoding
Loren Lugosch, Warren J. Gross
Recently, it was shown that if multiplicative weights are assigned to the edges of a Tanner graph used in belief propagation decoding, it is possible to use deep learning technique…