2 citations · 6 across the 8 of their papers we have counts for
17 papers
LMCodec: A Low Bitrate Speech Codec With Causal Transformer Models
Teerapat Jenrungrot, Michael Chinen, W. Bastiaan Kleijn +4
We introduce LMCodec, a causal neural speech codec that provides high quality audio at very low bitrates. The backbone of the system is a causal convolutional codec that encodes au…
Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset
Michael Chinen, Jan Skoglund, Chandan K A Reddy +2
Non-reference speech quality models are important for a growing number of applications. The VoiceMOS 2022 challenge provided a dataset of synthetic voice conversion and text-to-spe…
Ultra-Low-Bitrate Speech Coding with Pretrained Transformers
Ali Siahkoohi, Michael Chinen, Tom Denton +2
Speech coding facilitates the transmission of speech over low-bandwidth networks with minimal distortion. Neural-network based speech codecs have recently demonstrated significant…
A Comparison of Deep Learning MOS Predictors for Speech Synthesis Quality
Alessandro Ragano, Emmanouil Benetos, Michael Chinen +4
Speech synthesis quality prediction has made remarkable progress with the development of supervised and self-supervised learning (SSL) MOS predictors but some aspects related to th…
SoundStream: An End-to-End Neural Audio Codec
Neil Zeghidour, Alejandro Luebs, Ahmed Omran +2
We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStrea…
Handling Background Noise in Neural Speech Generation
Tom Denton, Alejandro Luebs, Felicia S. C. Lim +4
Recent advances in neural-network based generative modeling of speech has shown great potential for speech coding. However, the performance of such models drops when the input is n…
WARP-Q: Quality Prediction For Generative Neural Speech Codecs
Wissam A. Jassim, Jan Skoglund, Michael Chinen +1
Good speech quality has been achieved using waveform matching and parametric reconstruction coders. Recently developed very low bit rate generative codecs can reconstruct high qual…
Generative Speech Coding with Predictive Variance Regularization
W. Bastiaan Kleijn, Andrew Storus, Michael Chinen +5
The recent emergence of machine-learning based generative models for speech suggests a significant reduction in bit rate for speech codecs is possible. However, the performance of…
ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric
Michael Chinen, Felicia S. C. Lim, Jan Skoglund +3
Estimation of perceptual quality in audio and speech is possible using a variety of methods. The combined v3 release of ViSQOL and ViSQOLAudio (for speech and audio, respectively,)…
Speech Quality Factors for Traditional and Neural-Based Low Bit Rate Vocoders
Wissam A. Jassim, Jan Skoglund, Michael Chinen +1
This study compares the performances of different algorithms for coding speech at low bit rates. In addition to widely deployed traditional vocoders, a selection of recently develo…
Generative Speech Enhancement Based on Cloned Networks
Michael Chinen, W. Bastiaan Kleijn, Felicia S. C. Lim +1
We propose to implement speech enhancement by the regeneration of clean speech from a salient representation extracted from the noisy signal. The network that extracts salient feat…
Salient Speech Representations Based on Cloned Networks
W. Bastiaan Kleijn, Felicia S. C. Lim, Michael Chinen +1
We define salient features as features that are shared by signals that are defined as being equivalent by a system designer. The definition allows the designer to contribute qualit…
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…
A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet
Jean-Marc Valin, Jan Skoglund
Neural speech synthesis algorithms are a promising new approach for coding speech at very low bitrate. They have so far demonstrated quality that far exceeds traditional vocoders,…
Exploring Tradeoffs in Models for Low-latency Speech Enhancement
Kevin Wilson, Michael Chinen, Jeremy Thorpe +5
We explore a variety of neural networks configurations for one- and two-channel spectrogram-mask-based speech enhancement. Our best model improves on previous state-of-the-art perf…
LPCNet: Improving Neural Speech Synthesis Through Linear Prediction
Jean-Marc Valin, Jan Skoglund
Neural speech synthesis models have recently demonstrated the ability to synthesize high quality speech for text-to-speech and compression applications. These new models often requ…
Wavenet based low rate speech coding
W. Bastiaan Kleijn, Felicia S. C. Lim, Alejandro Luebs +4
Traditional parametric coding of speech facilitates low rate but provides poor reconstruction quality because of the inadequacy of the model used. We describe how a WaveNet generat…