arXiv subjects

Frederik Bous

Publications and source records attributed to Frederik Bous.

8 recordsLinked to original sources

arXiv2026

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching

While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment. We propose RobustSpeechFlow, a training strategy that improves alignment robustness by extending contrastive flow matching with length-preserving repeat and skip latent augmentations. Requiring no external aligners or preference data, our method directly penalizes realistic failure modes and readily integrates into existing pipelines. On Seed-TTS-eval, it reduces the word error rate (WER) from 1.44 to 1.38 using only 0.06B parameters. On our ZERO500 benchmark, it delivers consistent intelligibility improvements across diverse speaker and prosody conditions; at NFE=24, it reduces English character error rate (CER) from 0.48\% to 0.35\% and Korean CER from 0.81\% to 0.57\%. Audio samples: https://robustspeechflow.github.io/

cs.SD↗

arXiv2025

SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System

We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent module leveraging flow-matching for text-to-latent mapping, and an utterance-level duration predictor. To enable a lightweight architecture, we employ a low-dimensional latent space, temporal compression of latents, and ConvNeXt blocks. The TTS pipeline is further simplified by operating directly on raw character-level text and employing cross-attention for text-speech alignment, thus eliminating the need for grapheme-to-phoneme (G2P) modules and external aligners. In addition, we propose context-sharing batch expansion that accelerates loss convergence and stabilizes text-speech alignment with minimal memory and I/O overhead. Experimental results demonstrate that SupertonicTTS delivers performance comparable to contemporary zero-shot TTS models with only 44M parameters, while significantly reducing architectural complexity and computational cost. Audio samples are available at: https://supertonictts.github.io/.

eess.AS↗

arXiv2023

VaSAB: The variable size adaptive information bottleneck for disentanglement on speech and singing voice

The information bottleneck auto-encoder is a tool for disentanglement commonly used for voice transformation. The successful disentanglement relies on the right choice of bottleneck size. Previous bottleneck auto-encoders created the bottleneck by the dimension of the latent space or through vector quantization and had no means to change the bottleneck size of a specific model. As the bottleneck removes information from the disentangled representation, the choice of bottleneck size is a trade-off between disentanglement and synthesis quality. We propose to build the information bottleneck using dropout which allows us to change the bottleneck through the dropout rate and investigate adapting the bottleneck size depending on the context. We experimentally explore into using the adaptive bottleneck for pitch transformation and demonstrate that the adaptive bottleneck leads to improved disentanglement of the F0 parameter for both, speech and singing voice leading to improved synthesis quality. Using the variable bottleneck size, we were able to achieve disentanglement for singing voice including extremely high pitches and create a universal voice model, that works on both speech and singing voice with improved synthesis quality.

eess.AS↗

arXiv2022

Analysis and transformations of voice level in singing voice

We introduce a neural auto-encoder that transforms the musical dynamic in recordings of singing voice via changes in voice level. Since most recordings of singing voice are not annotated with voice level we propose a means to estimate the voice level from the signal's timbre using a neural voice level estimator. We introduce the recording factor that relates the voice level to the recorded signal power as a proportionality constant. This unknown constant depends on the recording conditions and the post-processing and may thus be different for each recording (but is constant across each recording). We provide two approaches to estimate the voice level without knowing the recording factor. The unknown recording factor can either be learned alongside the weights of the voice level estimator, or a special loss function based on the scalar product can be used to only match the contour of the recorded signal's power. The voice level models are used to condition a previously introduced bottleneck auto-encoder that disentangles its input, the mel-spectrogram, from the voice level. We evaluate the voice level models on recordings annotated with musical dynamic and by their ability to provide useful information to the auto-encoder. A perceptive test is carried out that evaluates the perceived change in voice level in transformed recordings and the synthesis quality. The perceptive test confirms that changing the conditional input changes the perceived voice level accordingly thus suggesting that the proposed voice level models encode information about the true voice level.

eess.AS↗

arXiv2022

Voice Reenactment with F0 and timing constraints and adversarial learning of conversions

This paper introduces voice reenactement as the task of voice conversion (VC) in which the expressivity of the source speaker is preserved during conversion while the identity of a target speaker is transferred. To do so, an original neural- VC architecture is proposed based on sequence-to-sequence voice conversion (S2S-VC) in which the speech prosody of the source speaker is preserved during conversion. First, the S2S-VC architecture is modified so as to synchronize the converted speech with the source speech by mean of phonetic duration encoding; second, the decoder is conditioned on the desired sequence of F0- values and an explicit F0-loss is formulated between the F0 of the source speaker and the one of the converted speech. Besides, an adversarial learning of conversions is integrated within the S2S-VC architecture so as to exploit both advantages of reconstruction of original speech and converted speech with manipulated attributes during training and then reducing the inconsistency between training and conversion. An experimental evaluation on the VCTK speech database shows that the speech prosody can be efficiently preserved during conversion, and that the proposed adversarial learning consistently improves the conversion and the naturalness of the reenacted speech.

cs.SD↗

arXiv2021

Towards Universal Neural Vocoding with a Multi-band Excited WaveNet

This paper introduces the Multi-Band Excited WaveNet a neural vocoder for speaking and singing voices. It aims to advance the state of the art towards an universal neural vocoder, which is a model that can generate voice signals from arbitrary mel spectrograms extracted from voice signals. Following the success of the DDSP model and following the development of the recently proposed excitation vocoders we propose a vocoder structure consisting of multiple specialized DNN that are combined with dedicated signal processing components. All components are implemented as differentiable operators and therefore allow joined optimization of the model parameters. To prove the capacity of the model to reproduce high quality voice signals we evaluate the model on single and multi speaker/singer datasets. We conduct a subjective evaluation demonstrating that the models support a wide range of domain variations (unseen voices, languages, expressivity) achieving perceptive quality that compares with a state of the art universal neural vocoder, however using significantly smaller training datasets and significantly less parameters. We also demonstrate remaining limits of the universality of neural vocoders e.g. the creation of saturated singing voices.

eess.AS↗

arXiv2020

Semi-supervised learning of glottal pulse positions in a neural analysis-synthesis framework

This article investigates into recently emerging approaches that use deep neural networks for the estimation of glottal closure instants (GCI). We build upon our previous approach that used synthetic speech exclusively to create perfectly annotated training data and that had been shown to compare favourably with other training approaches using electroglottograph (EGG) signals. Here we introduce a semi-supervised training strategy that allows refining the estimator by means of an analysis-synthesis setup using real speech signals, for which GCI ground truth does not exist. Evaluation of the analyser is performed by means of comparing the GCI extracted from the glottal flow signal generated by the analyser with the GCI extracted from EGG on the CMU arctic dataset, where EGG signals were recorded in addition to speech. We observe that (1.) the artificial increase of the diversity of pulse shapes that has been used in our previous construction of the synthetic database is beneficial, (2.) training the GCI network in the analysis-synthesis setup allows achieving a very significant improvement of the GCI analyser, (3.) additional regularisation strategies allow improving the final analysis network when trained in the analysis-synthesis setup.

eess.AS↗

arXiv2019

Analysing Deep Learning-Spectral Envelope Prediction Methods for Singing Synthesis

We conduct an investigation on various hyper-parameters regarding neural networks used to generate spectral envelopes for singing synthesis. Two perceptive tests, where the first compares two models directly and the other ranks models with a mean opinion score, are performed. With these tests we show that when learning to predict spectral envelopes, 2d-convolutions are superior over previously proposed 1d-convolutions and that predicting multiple frames in an iterated fashion during training is superior over injecting noise to the input data. An experimental investigation whether learning to predict a probability distribution vs.\ single samples was performed but turned out to be inconclusive. A network architecture is proposed that incorporates the improvements which we found to be useful and we show in our experiments that this network produces better results than other stat-of-the-art methods.

eess.AS↗