Search Results for author: Jonathan Le Roux

Found 64 papers, 12 papers with code

Block Coordinate Descent for Sparse NMF

1 code implementation15 Jan 2013 Vamsi K. Potluru, Sergey M. Plis, Jonathan Le Roux, Barak A. Pearlmutter, Vince D. Calhoun, Thomas P. Hayes

However, present algorithms designed for optimizing the mixed norm L$_1$/L$_2$ are slow and other formulations for sparse NMF have been proposed such as those based on L$_1$ and L$_0$ norms.

Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures

no code implementations9 Sep 2014 John R. Hershey, Jonathan Le Roux, Felix Weninger

Deep unfolding of this model yields a new kind of non-negative deep neural network, that can be trained using a multiplicative backpropagation-style update algorithm.

Speech Enhancement

Deep clustering: Discriminative embeddings for segmentation and separation

8 code implementations18 Aug 2015 John R. Hershey, Zhuo Chen, Jonathan Le Roux, Shinji Watanabe

The framework can be used without class labels, and therefore has the potential to be trained on a diverse set of sound types, and to generalize to novel sources.

Clustering Deep Clustering +3

Single-Channel Multi-Speaker Separation using Deep Clustering

2 code implementations7 Jul 2016 Yusuf Isik, Jonathan Le Roux, Zhuo Chen, Shinji Watanabe, John R. Hershey

In this paper we extend the baseline system with an end-to-end signal approximation objective that greatly improves performance on a challenging speech separation.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

Full-Capacity Unitary Recurrent Neural Networks

2 code implementations NeurIPS 2016 Scott Wisdom, Thomas Powers, John R. Hershey, Jonathan Le Roux, Les Atlas

To address this question, we propose full-capacity uRNNs that optimize their recurrence matrix over all unitary matrices, leading to significantly improved performance over uRNNs that use a restricted-capacity recurrence matrix.

Open-Ended Question Answering Sequential Image Classification

Deep Clustering and Conventional Networks for Music Separation: Stronger Together

no code implementations18 Nov 2016 Yi Luo, Zhuo Chen, John R. Hershey, Jonathan Le Roux, Nima Mesgarani

Deep clustering is the first method to handle general audio separation scenarios with multiple sources of the same type and an arbitrary number of sources, performing impressively in speaker-independent speech separation tasks.

Clustering Deep Clustering +3

End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction

no code implementations26 Apr 2018 Zhong-Qiu Wang, Jonathan Le Roux, DeLiang Wang, John R. Hershey

In addition, we train through unfolded iterations of a phase reconstruction algorithm, represented as a series of STFT and inverse STFT layers.

Speech Separation

A Purely End-to-end System for Multi-speaker Speech Recognition

no code implementations ACL 2018 Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey

In this paper, we propose a new sequence-to-sequence framework to directly decode multiple label sequences from a single speech sequence by unifying source separation and speech recognition functions in an end-to-end manner.

speech-recognition Speech Recognition

End-to-End Multi-Lingual Multi-Speaker Speech Recognition

no code implementations27 Sep 2018 Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey

Several multi-lingual ASR systems were recently proposed based on a monolithic neural network architecture without language-dependent modules, showing that modeling of multiple languages is well within the capabilities of an end-to-end framework.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Phasebook and Friends: Leveraging Discrete Representations for Source Separation

no code implementations2 Oct 2018 Jonathan Le Roux, Gordon Wichern, Shinji Watanabe, Andy Sarroff, John R. Hershey

Here, we propose "magbook", "phasebook", and "combook", three new types of layers based on discrete representations that can be used to estimate complex time-frequency masks.

Speaker Separation Speech Enhancement

Bootstrapping single-channel source separation via unsupervised spatial clustering on stereo mixtures

no code implementations6 Nov 2018 Prem Seetharaman, Gordon Wichern, Jonathan Le Roux, Bryan Pardo

These estimates, together with a weighting scheme in the time-frequency domain, based on confidence in the separation quality, are used to train a deep learning model that can be used for single-channel separation, where no source direction information is available.

Clustering Image Segmentation +2

SDR - half-baked or well done?

1 code implementation6 Nov 2018 Jonathan Le Roux, Scott Wisdom, Hakan Erdogan, John R. Hershey

In speech enhancement and source separation, signal-to-noise ratio is a ubiquitous objective measure of denoising/separation quality.

Sound Audio and Speech Processing

Class-conditional embeddings for music source separation

no code implementations7 Nov 2018 Prem Seetharaman, Gordon Wichern, Shrikant Venkataramani, Jonathan Le Roux

Isolating individual instruments in a musical mixture has a myriad of potential applications, and seems imminently achievable given the levels of performance reached by recent deep learning methods.

Clustering Deep Clustering +1

WHAM!: Extending Speech Separation to Noisy Environments

1 code implementation2 Jul 2019 Gordon Wichern, Joe Antognini, Michael Flynn, Licheng Richard Zhu, Emmett McQuinn, Dwight Crow, Ethan Manilow, Jonathan Le Roux

Recent progress in separating the speech signals from multiple overlapping speakers using a single audio channel has brought us closer to solving the cocktail party problem.

Speech Separation

MIMO-SPEECH: End-to-End Multi-Channel Multi-Speaker Speech Recognition

no code implementations15 Oct 2019 Xuankai Chang, Wangyou Zhang, Yanmin Qian, Jonathan Le Roux, Shinji Watanabe

In this work, we propose a novel neural sequence-to-sequence (seq2seq) architecture, MIMO-Speech, which extends the original seq2seq to deal with multi-channel input and multi-channel output so that it can fully model multi-channel multi-speaker speech separation and recognition.

speech-recognition Speech Recognition +1

WHAMR!: Noisy and Reverberant Single-Channel Speech Separation

no code implementations22 Oct 2019 Matthew Maciejewski, Gordon Wichern, Emmett McQuinn, Jonathan Le Roux

While significant advances have been made with respect to the separation of overlapping speech signals, studies have been largely constrained to mixtures of clean, near anechoic speech, not representative of many real-world scenarios.

Sound Audio and Speech Processing

Bootstrapping deep music separation from primitive auditory grouping principles

no code implementations23 Oct 2019 Prem Seetharaman, Gordon Wichern, Jonathan Le Roux, Bryan Pardo

They are trained on synthetic mixtures of audio made from isolated sound source recordings so that ground truth for the separation is known.

Music Source Separation

Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision

no code implementations6 Nov 2019 Fatemeh Pishdadian, Gordon Wichern, Jonathan Le Roux

In this scenario, weak labels are defined in contrast with strong time-frequency (TF) labels such as those obtained from isolated sources, and refer either to frame-level weak labels where one only has access to the time periods when different sources are active in an audio mixture, or to clip-level weak labels that only indicate the presence or absence of sounds in an entire audio clip.

Audio Source Separation

Streaming automatic speech recognition with the transformer model

no code implementations8 Jan 2020 Niko Moritz, Takaaki Hori, Jonathan Le Roux

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

End-to-End Multi-speaker Speech Recognition with Transformer

no code implementations10 Feb 2020 Xuankai Chang, Wangyou Zhang, Yanmin Qian, Jonathan Le Roux, Shinji Watanabe

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios.

speech-recognition Speech Recognition

Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR

no code implementations14 Feb 2020 Leda Sari, Niko Moritz, Takaaki Hori, Jonathan Le Roux

We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers

no code implementations8 Jul 2020 Shijie Geng, Peng Gao, Moitreya Chatterjee, Chiori Hori, Jonathan Le Roux, Yongfeng Zhang, Hongsheng Li, Anoop Cherian

Given an input video, its associated audio, and a brief caption, the audio-visual scene aware dialog (AVSD) task requires an agent to indulge in a question-answer dialog with a human about the audio-visual content.

Answer Generation Graph Representation Learning

AutoClip: Adaptive Gradient Clipping for Source Separation Networks

1 code implementation25 Jul 2020 Prem Seetharaman, Gordon Wichern, Bryan Pardo, Jonathan Le Roux

Clipping the gradient is a known approach to improving gradient descent, but requires hand selection of a clipping threshold hyperparameter.

Audio Source Separation

Multi-Pass Transformer for Machine Translation

no code implementations23 Sep 2020 Peng Gao, Chiori Hori, Shijie Geng, Takaaki Hori, Jonathan Le Roux

In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of later layers.

Machine Translation Neural Architecture Search +1

Transcription Is All You Need: Learning to Separate Musical Mixtures with Score as Supervision

no code implementations22 Oct 2020 Yun-Ning Hung, Gordon Wichern, Jonathan Le Roux

Most music source separation systems require large collections of isolated sources for training, which can be difficult to obtain.

Music Source Separation

Semi-Supervised Speech Recognition via Graph-based Temporal Classification

no code implementations29 Oct 2020 Niko Moritz, Takaaki Hori, Jonathan Le Roux

However, alternative ASR hypotheses of an N-best list can provide more accurate labels for an unlabeled speech utterance and also reflect uncertainties of the seed ASR model.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training

no code implementations26 Nov 2020 Sameer Khurana, Niko Moritz, Takaaki Hori, Jonathan Le Roux

The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Capturing Multi-Resolution Context by Dilated Self-Attention

no code implementations7 Apr 2021 Niko Moritz, Takaaki Hori, Jonathan Le Roux

The restricted self-attention allows attention to neighboring frames of the query at a high resolution, and the dilation mechanism summarizes distant information to allow attending to it with a lower resolution.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers

no code implementations19 Apr 2021 Takaaki Hori, Niko Moritz, Chiori Hori, Jonathan Le Roux

In this paper, we extend our prior work by (1) introducing the Conformer architecture to further improve the accuracy, (2) accelerating the decoding process with a novel activation recycling technique, and (3) enabling streaming decoding with triggered attention.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition

no code implementations16 Jun 2021 Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori

MPL consists of a pair of online and offline models that interact and learn from each other, inspired by the mean teacher method.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition

no code implementations2 Jul 2021 Niko Moritz, Takaaki Hori, Jonathan Le Roux

Attention-based end-to-end automatic speech recognition (ASR) systems have recently demonstrated state-of-the-art results for numerous tasks.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers

no code implementations4 Aug 2021 Chiori Hori, Takaaki Hori, Jonathan Le Roux

A CNN-based timing detector is also trained to detect a proper output timing, where the captions generated by the two Trans-formers become sufficiently close to each other.

Video Captioning

Visual Scene Graphs for Audio Source Separation

no code implementations ICCV 2021 Moitreya Chatterjee, Jonathan Le Roux, Narendra Ahuja, Anoop Cherian

At its core, AVSGS uses a recursive neural network that emits mutually-orthogonal sub-graph embeddings of the visual graph using multi-head attention.

AudioCaps Audio Source Separation

Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy

no code implementations11 Oct 2021 Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori

Pseudo-labeling (PL), a semi-supervised learning (SSL) method where a seed model performs self-training using pseudo-labels generated from untranscribed speech, has been shown to enhance the performance of end-to-end automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning

no code implementations13 Oct 2021 Ankit P. Shah, Shijie Geng, Peng Gao, Anoop Cherian, Takaaki Hori, Tim K. Marks, Jonathan Le Roux, Chiori Hori

In previous work, we have proposed the Audio-Visual Scene-Aware Dialog (AVSD) task, collected an AVSD dataset, developed AVSD technologies, and hosted an AVSD challenge track at both the 7th and 8th Dialog System Technology Challenges (DSTC7, DSTC8).

Region Proposal

The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks

3 code implementations19 Oct 2021 Darius Petermann, Gordon Wichern, Zhong-Qiu Wang, Jonathan Le Roux

The cocktail party problem aims at isolating any source of interest within a complex acoustic scene, and has long inspired audio source separation research.

Audio Source Separation

Sequence Transduction with Graph-based Supervision

no code implementations1 Nov 2021 Niko Moritz, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux

The recurrent neural network transducer (RNN-T) objective plays a major role in building today's best automatic speech recognition (ASR) systems for production.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering

no code implementations18 Feb 2022 Anoop Cherian, Chiori Hori, Tim K. Marks, Jonathan Le Roux

Spatio-temporal scene-graph approaches to video-based reasoning tasks, such as video question-answering (QA), typically construct such graphs for every video frame.

Question Answering Spatio-temporal Scene Graphs +1

Locate This, Not That: Class-Conditioned Sound Event DOA Estimation

no code implementations8 Mar 2022 Olga Slizovskaia, Gordon Wichern, Zhong-Qiu Wang, Jonathan Le Roux

Existing systems for sound event localization and detection (SELD) typically operate by estimating a source location for all classes at every time instant.

Sound Event Localization and Detection

Heterogeneous Target Speech Separation

no code implementations7 Apr 2022 Efthymios Tzinis, Gordon Wichern, Aswin Subramanian, Paris Smaragdis, Jonathan Le Roux

We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e. g., loudness, gender, language, spatial location, etc).

Speech Separation

Late Audio-Visual Fusion for In-The-Wild Speaker Diarization

no code implementations2 Nov 2022 Zexu Pan, Gordon Wichern, François G. Germain, Aswin Subramanian, Jonathan Le Roux

Speaker diarization is well studied for constrained audios but little explored for challenging in-the-wild videos, which have more speakers, shorter utterances, and inconsistent on-screen speakers.

speaker-diarization Speaker Diarization +1

Cold Diffusion for Speech Enhancement

no code implementations4 Nov 2022 Hao Yen, François G. Germain, Gordon Wichern, Jonathan Le Roux

Diffusion models have recently shown promising results for difficult enhancement tasks such as the conditional and unconditional restoration of natural images and audio signals.

Speech Enhancement

Optimal Condition Training for Target Source Separation

1 code implementation11 Nov 2022 Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux

Recent research has shown remarkable performance in leveraging multiple extraneous conditional and non-mutually exclusive semantic concepts for sound source separation, allowing the flexibility to extract a given target source based on multiple different queries.

Reverberation as Supervision for Speech Separation

no code implementations15 Nov 2022 Rohith Aralikatti, Christoph Boeddeker, Gordon Wichern, Aswin Shanmugam Subramanian, Jonathan Le Roux

This paper proposes reverberation as supervision (RAS), a novel unsupervised loss function for single-channel reverberant speech separation.

Speech Separation

Latent Iterative Refinement for Modular Source Separation

1 code implementation22 Nov 2022 Dimitrios Bralios, Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux

During inference, we can dynamically adjust how many processing blocks and iterations of a specific block an input signal needs using a gating module.

Hyperbolic Audio Source Separation

no code implementations9 Dec 2022 Darius Petermann, Gordon Wichern, Aswin Subramanian, Jonathan Le Roux

We introduce a framework for audio source separation using embeddings on a hyperbolic manifold that compactly represent the hierarchical relationship between sound sources and time-frequency features.

Audio Source Separation

Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks

no code implementations14 Dec 2022 Darius Petermann, Gordon Wichern, Aswin Shanmugam Subramanian, Zhong-Qiu Wang, Jonathan Le Roux

In this paper, we focus on the cocktail fork problem, which takes a three-pronged approach to source separation by separating an audio mixture such as a movie soundtrack or podcast into the three broad categories of speech, music, and sound effects (SFX - understood to include ambient noise and natural sound events).

Action Detection Activity Detection +4

TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings

no code implementations7 Mar 2023 Christoph Boeddeker, Aswin Shanmugam Subramanian, Gordon Wichern, Reinhold Haeb-Umbach, Jonathan Le Roux

Since diarization and source separation of meeting data are closely related tasks, we here propose an approach to perform the two objectives jointly.

 Ranked #1 on Speech Recognition on LibriCSS (using extra training data)

Action Detection Activity Detection +1

Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT

no code implementations4 Apr 2023 Ke Chen, Gordon Wichern, François G. Germain, Jonathan Le Roux

In this paper, we propose a self-supervised learning framework for music source separation inspired by the HuBERT speech representation model.

Clustering Music Source Separation +1

Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos

no code implementations27 Jun 2023 Chiori Hori, Puyuan Peng, David Harwath, Xinyu Liu, Kei Ota, Siddarth Jain, Radu Corcodel, Devesh Jha, Diego Romeres, Jonathan Le Roux

This paper introduces a method for robot action sequence generation from instruction videos using (1) an audio-visual Transformer that converts audio-visual features and instruction speech to a sequence of robot actions called dynamic movement primitives (DMPs) and (2) style-transfer-based training that employs multi-task learning with video captioning and weakly-supervised learning with a semantic classifier to exploit unpaired video-action data.

Multi-Task Learning Scene Understanding +3

Generation or Replication: Auscultating Audio Latent Diffusion Models

no code implementations16 Oct 2023 Dimitrios Bralios, Gordon Wichern, François G. Germain, Zexu Pan, Sameer Khurana, Chiori Hori, Jonathan Le Roux

The introduction of audio latent diffusion models possessing the ability to generate realistic sound clips on demand from a text description has the potential to revolutionize how we work with audio.

AudioCaps Memorization +1

Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction

no code implementations30 Oct 2023 Zexu Pan, Gordon Wichern, Yoshiki Masuyama, Francois G. Germain, Sameer Khurana, Chiori Hori, Jonathan Le Roux

Target speech extraction aims to extract, based on a given conditioning cue, a target speech signal that is corrupted by interfering sources, such as noise or competing speakers.

Speaker Separation Speech Enhancement +1

NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection

no code implementations12 Dec 2023 Zexu Pan, Gordon Wichern, Francois G. Germain, Sameer Khurana, Jonathan Le Roux

Neuro-steered speaker extraction aims to extract the listener's brain-attended speech signal from a multi-talker speech signal, in which the attention is derived from the cortical activity.

EEG

GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model

no code implementations9 Feb 2024 Haocheng Liu, Teysir Baoueb, Mathieu Fontaine, Jonathan Le Roux, Gael Richard

Diffusion models are receiving a growing interest for a variety of signal generation tasks such as speech or music synthesis.

NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization

1 code implementation27 Feb 2024 Yoshiki Masuyama, Gordon Wichern, François G. Germain, Zexu Pan, Sameer Khurana, Chiori Hori, Jonathan Le Roux

Existing NF-based methods focused on estimating the magnitude of the HRTF from a given sound source direction, and the magnitude is converted to a finite impulse response (FIR) filter.

Spatial Interpolation

Why does music source separation benefit from cacophony?

no code implementations28 Feb 2024 Chang-Bin Jeon, Gordon Wichern, François G. Germain, Jonathan Le Roux

In music source separation, a standard training data augmentation procedure is to create new training samples by randomly combining instrument stems from different songs.

Data Augmentation Music Source Separation

Cannot find the paper you are looking for? You can Submit a new open access paper.