383 citations · 1.4k across the 49 of their papers we have counts for
26 papers · 1 filter
OLAC: An Overlapped Lossless Audio Codec in the Time-Domain with MDCT Compatibility
Jean-Marc Valin
Lossless audio coding is a highly mature field of research, with limited potential for significant improvements in pure compression performance. However, emerging real-time wireles…
RADE: A Neural Codec for Transmitting Speech over HF Radio Channels
David Rowe, Jean-Marc Valin
Speech compression is commonly used to send voice over radio channels in applications such as mobile telephony and two-way push-to-talk (PTT) radio. In classical systems, the speec…
Very Low Complexity Speech Synthesis Using Framewise Autoregressive GAN (FARGAN) with Pitch Prediction
Jean-Marc Valin, Ahmed Mustafa, Jan Büthe
Neural vocoders are now being used in a wide range of speech processing applications. In many of those applications, the vocoder can be the most complex component, so finding lower…
Real-time Stereo Speech Enhancement with Spatial-Cue Preservation based on Dual-Path Structure
Masahito Togami, Jean-Marc Valin, Karim Helwani +3
We introduce a real-time, multichannel speech enhancement algorithm which maintains the spatial cues of stereo recordings including two speech sources. Recognizing that each source…
NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping
Jan Büthe, Ahmed Mustafa, Jean-Marc Valin +2
Speech codec enhancement methods are designed to remove distortions added by speech codecs. While classical methods are very low in complexity and add zero delay, their effectivene…
Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity
Krishna Subramani, Jean-Marc Valin, Jan Buethe +2
Pitch estimation is an essential step of many speech processing algorithms, including speech coding, synthesis, and enhancement. Recently, pitch estimators based on deep neural net…
LACE: A light-weight, causal model for enhancing coded speech through adaptive convolutions
Jan Büthe, Jean-Marc Valin, Ahmed Mustafa
Classical speech coding uses low-complexity postfilters with zero lookahead to enhance the quality of coded speech, but their effectiveness is limited by their simplicity. Deep Neu…
A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement
Zhepei Wang, Ritwik Giri, Devansh Shah +3
In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by i…
Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity
Ahmed Mustafa, Jean-Marc Valin, Jan Büthe +2
GAN vocoders are currently one of the state-of-the-art methods for building high-quality neural waveform generative models. However, most of their architectures require dozens of b…
DRED: Deep REDundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder
Jean-Marc Valin, Jan Büthe, Ahmed Mustafa +1
Despite recent advancements in packet loss concealment (PLC) using deep learning techniques, packet loss remains a significant challenge in real-time speech communication. Redundan…
Semi-supervised Time Domain Target Speaker Extraction with Attention
Zhepei Wang, Ritwik Giri, Shrikant Venkataramani +5
In this work, we propose Exformer, a time-domain architecture for target speaker extraction. It consists of a pre-trained speaker embedder network and a separator network based on…
To Dereverb Or Not to Dereverb? Perceptual Studies On Real-Time Dereverberation Targets
Jean-Marc Valin, Ritwik Giri, Shrikant Venkataramani +2
In real life, room effect, also known as room reverberation, and the present background noise degrade the quality of speech. Recently, deep learning-based speech enhancement approa…
Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model
Jean-Marc Valin, Ahmed Mustafa, Christopher Montgomery +4
As deep speech enhancement algorithms have recently demonstrated capabilities greatly surpassing their traditional counterparts for suppressing noise, reverberation and echo, atten…
End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation
Krishna Subramani, Jean-Marc Valin, Umut Isik +2
Neural vocoders have recently demonstrated high quality speech synthesis, but typically require a high computational complexity. LPCNet was proposed as a way to reduce the complexi…
Improved singing voice separation with chromagram-based pitch-aware remixing
Siyuan Yuan, Zhepei Wang, Umut Isik +4
Singing voice separation aims to separate music into vocals and accompaniment components. One of the major constraints for the task is the limited amount of training data with sepa…
Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet
Jean-Marc Valin, Umut Isik, Paris Smaragdis +1
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so. In previous work, we introduced LPCNet, which uses…
Multi-channel Opus compression for far-field automatic speech recognition with a fixed bitrate budget
Lukas Drude, Jahn Heymann, Andreas Schwarz +1
Automatic speech recognition (ASR) in the cloud allows the use of larger models and more powerful multi-channel signal processing front-ends compared to on-device processing. Howev…
Personalized PercepNet: Real-time, Low-complexity Target Voice Separation and Enhancement
Ritwik Giri, Shrikant Venkataramani, Jean-Marc Valin +2
The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size a…
Semi-Supervised Singing Voice Separation with Noisy Self-Training
Zhepei Wang, Ritwik Giri, Umut Isik +2
Recent progress in singing voice separation has primarily focused on supervised deep learning methods. However, the scarcity of ground-truth data with clean musical sources has bee…
Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders
Jonah Casebeer, Vinjai Vale, Umut Isik +3
Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech output…
Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet
Jean-Marc Valin, Srikanth Tenneti, Karim Helwani +2
Speech enhancement algorithms based on deep learning have greatly surpassed their traditional counterparts and are now being considered for the task of removing acoustic echo from…
A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech
Jean-Marc Valin, Umut Isik, Neerad Phansalkar +3
Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of…
PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss
Umut Isik, Ritwik Giri, Neerad Phansalkar +3
Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to t…
Improving Opus Low Bit Rate Quality with Neural Speech Synthesis
Jan Skoglund, Jean-Marc Valin
The voice mode of the Opus audio coder can compress wideband speech at bit rates ranging from 6 kb/s to 40 kb/s. However, Opus is at its core a waveform matching coder, and as the…