arXiv subjects

Axel Roebel

Publications and source records attributed to Axel Roebel.

At least 19 recordsLinked to original sources

arXiv2026

MuScriptor: An Open Model for Multi-Instrument Music Transcription

Existing methods for automatic music transcription are often limited to single-instrument recordings or fail on complex, real music mixes. Although previous work utilizes synthetic training data, the resulting models generalize poorly, leading to largely unusable transcription output in realistic, multi-instrument settings. In this work, we analyze the effectiveness of synthetic data for pre-training while combining it with fine-tuning on real music audio and post-training using reinforcement learning. We further introduce conditioning on instrument presence to customize transcriptions. Finally, we release MuScriptor, an open-weight multi-instrument music transcription model that works on real-world music recordings from across a diverse range of musical genres.

cs.SD↗

arXiv2025

PitchFlower: A flow-based neural audio codec with pitch controllability

We present PitchFlower, a flow-based neural audio codec with explicit pitch controllability. Our approach promotes pitch disentanglement through a simple perturbation: during training, F0 contours are flattened and randomly shifted at the input, while the true F0 is provided as conditioning to regenerate the original audio. A vector-quantization bottleneck prevents pitch recovery, and a flow-based decoder generates high quality audio. Experiments show that PitchFlower achieves accurate pitch control at the level of DSP baselines but at much higher audio quality, and performs on par with state-of-the-art neural approaches. Notably, despite using WORLD-transformed audio for training, our method filters out the vocoder's inherent artifacts, revealing a strong resilience of deep generative modeling to input degradation. This finding suggests that our framework provides a simple and extensible path that could be extended to other speech attributes.

eess.AS↗

arXiv2025

Continuous Audio Language Models

Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy codecs with a limited bitrate. As a consequence, increasing audio quality requires generating more tokens, which imposes a trade-off between fidelity and computational cost. We address this issue by studying Continuous Audio Language Models (CALM). These models instantiate a large Transformer backbone that produces a contextual embedding at every timestep. This sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling. By avoiding lossy compression, CALM achieves higher quality at lower computational cost than their discrete counterpart. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. Samples are available at hf.co/spaces/kyutai/calm-samples. Finally, we release Pocket TTS, an open-source 100M-parameter text-to-speech model that can run faster than real time on a laptop CPU: github.com/kyutai-labs/pocket-tts.

cs.SD↗

arXiv2025

Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters

Precise control over speech characteristics, such as pitch, duration, and speech rate, remains a significant challenge in the field of voice conversion. The ability to manipulate parameters like pitch and syllable rate is an important element for effective identity conversion, but can also be used independently for voice transformation, achieving goals that were historically addressed by vocoder-based methods. In this work, we explore a convolutional neural network-based approach that aims to provide means for modifying fundamental frequency (F0), phoneme sequences, intensity, and speaker identity. Rather than relying on disentanglement techniques, our model is explicitly conditioned on these factors to generate mel spectrograms, which are then converted into waveforms using a universal neural vocoder. Accordingly, during inference, F0 contours, phoneme sequences, and speaker embeddings can be freely adjusted, allowing for intuitively controlled voice transformations. We evaluate our approach on speaker conversion and expressive speech tasks using both perceptual and objective metrics. The results suggest that the proposed method offers substantial flexibility, while maintaining high intelligibility and speaker similarity.

cs.SD↗

arXiv2025

MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling

While most music generation models generate a mixture of stems (in mono or stereo), we propose to train a multi-stem generative model with 3 stems (bass, drums and other) that learn the musical dependencies between them. To do so, we train one specialized compression algorithm per stem to tokenize the music into parallel streams of tokens. Then, we leverage recent improvements in the task of music source separation to train a multi-stream text-to-music language model on a large dataset. Finally, thanks to a particular conditioning method, our model is able to edit bass, drums or other stems on existing or generated songs as well as doing iterative composition (e.g. generating bass on top of existing drums). This gives more flexibility in music generation algorithms and it is to the best of our knowledge the first open-source multi-stem autoregressive music generation model that can perform good quality generation and coherent source editing. Code and model weights will be released and samples are available on https://simonrouard.github.io/musicgenstem/.

cs.SD↗

arXiv2024

Lina-Speech: Gated Linear Attention and Initial-State Tuning for Multi-Sample Prompting Text-To-Speech Synthesis

Neural codec language models, built on transformer architecture, have revolutionized text-to-speech (TTS) synthesis, excelling in voice cloning by treating it as a prefix continuation task. However, their limited context length hinders their effectiveness to short speech samples. As a result, the voice cloning ability is restricted to a limited coverage and diversity of the speaker's prosody and style. Besides, adapting prosody, accent, or appropriate emotion from a short prefix remains a challenging task. Finally, the quadratic complexity of self-attention limits inference throughput. In this work, we introduce Lina-Speech, a TTS model with Gated Linear Attention (GLA) to replace standard self-attention as a principled backbone, improving inference throughput while matching state-of-the-art performance. Leveraging the stateful property of recurrent architecture, we introduce an Initial-State Tuning (IST) strategy that unlocks the possibility of multiple speech sample conditioning of arbitrary numbers and lengths and provides a comprehensive and efficient strategy for voice cloning and out-of-domain speaking style and emotion adaptation. We demonstrate the effectiveness of this approach for controlling fine-grained characteristics such as prosody and emotion. Code, checkpoints, and demo are freely available: https://github.com/theodorblackbird/lina-speech

eess.AS↗

arXiv2024

Audio Conditioning for Music Generation via Discrete Bottleneck Features

While most music generation models use textual or parametric conditioning (e.g. tempo, harmony, musical genre), we propose to condition a language model based music generation system with audio input. Our exploration involves two distinct strategies. The first strategy, termed textual inversion, leverages a pre-trained text-to-music model to map audio input to corresponding "pseudowords" in the textual embedding space. For the second model we train a music language model from scratch jointly with a text conditioner and a quantized audio feature extractor. At inference time, we can mix textual and audio conditioning and balance them thanks to a novel double classifier free guidance method. We conduct automatic and human studies that validates our approach. We will release the code and we provide music samples on https://musicgenstyle.github.io in order to show the quality of our model.

cs.SD↗

arXiv2024

Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis

Recent advancements in text-to-speech (TTS) powered by language models have showcased remarkable capabilities in achieving naturalness and zero-shot voice cloning. Notably, the decoder-only transformer is the prominent architecture in this domain. However, transformers face challenges stemming from their quadratic complexity in sequence length, impeding training on lengthy sequences and resource-constrained hardware. Moreover they lack specific inductive bias with regards to the monotonic nature of TTS alignments. In response, we propose to replace transformers with emerging recurrent architectures and introduce specialized cross-attention mechanisms for reducing repeating and skipping issues. Consequently our architecture can be efficiently trained on long samples and achieve state-of-the-art zero-shot voice cloning against baselines of comparable size. Our implementation and demos are available at https://github.com/theodorblackbird/lina-speech.

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↗

arXiv2023

AI (r)evolution -- where are we heading? Thoughts about the future of music and sound technologies in the era of deep learning

Artificial Intelligence (AI) technologies such as deep learning are evolving very quickly bringing many changes to our everyday lives. To explore the future impact and potential of AI in the field of music and sound technologies a doctoral day was held between Queen Mary University of London (QMUL, UK) and Sciences et Technologies de la Musique et du Son (STMS, France). Prompt questions about current trends in AI and music were generated by academics from QMUL and STMS. Students from the two institutions then debated these questions. This report presents a summary of the student debates on the topics of: Data, Impact, and the Environment; Responsible Innovation and Creative Practice; Creativity and Bias; and From Tools to the Singularity. The students represent the future generation of AI and music researchers. The academics represent the incumbent establishment. The student debates reported here capture visions, dreams, concerns, uncertainties, and contentious issues for the future of AI and music as the establishment is rightfully challenged by the next generation.

cs.CY↗

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

StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks

In this paper we introduce StyleWaveGAN, a style-based drum sound generator that is a variation of StyleGAN, a state-of-the-art image generator. By conditioning StyleWaveGAN on both the type of drum and several audio descriptors, we are able to synthesize waveforms faster than real-time on a GPU directly in CD quality up to a duration of 1.5s while retaining a considerable amount of control over the generation. We also introduce an alternative to the progressive growing of GANs and experimented on the effect of dataset balancing for generative tasks. The experiments are carried out on an augmented subset of a publicly available dataset comprised of different drums and cymbals. We evaluate against two recent drum generators, WaveGAN and NeuroDrum, demonstrating significantly improved generation quality (measured with the Frechet Audio Distance) and interesting results with perceptual features.

cs.SD↗

arXiv2022

Audio Defect Detection in Music with Deep Networks

With increasing amounts of music being digitally transferred from production to distribution, automatic means of determining media quality are needed. Protection mechanisms in digital audio processing tools have not eliminated the need of production entities located downstream the distribution chain to assess audio quality and detect defects inserted further upstream. Such analysis often relies on the received audio and scarce meta-data alone. Deliberate use of artefacts such as clicks in popular music as well as more recent defects stemming from corruption in modern audio encodings call for data-centric and context sensitive solutions for detection. We present a convolutional network architecture following end-to-end encoder decoder configuration to develop detectors for two exemplary audio defects. A click detector is trained and compared to a traditional signal processing method, with a discussion on context sensitivity. Additional post-processing is used for data augmentation and workflow simulation. The ability of our models to capture variance is explored in a detector for artefacts from decompression of corrupted MP3 compressed audio. For both tasks we describe the synthetic generation of artefacts for controlled detector training and evaluation. We evaluate our detectors on the large open-source Free Music Archive (FMA) and genre-specific datasets.

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↗

arXiv2021

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

Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations

Voice conversion (VC) consists of digitally altering the voice of an individual to manipulate part of its content, primarily its identity, while maintaining the rest unchanged. Research in neural VC has accomplished considerable breakthroughs with the capacity to falsify a voice identity using a small amount of data with a highly realistic rendering. This paper goes beyond voice identity and presents a neural architecture that allows the manipulation of voice attributes (e.g., gender and age). Leveraging the latest advances on adversarial learning of structured speech representation, a novel structured neural network is proposed in which multiple auto-encoders are used to encode speech as a set of idealistically independent linguistic and extra-linguistic representations, which are learned adversariarly and can be manipulated during VC. Moreover, the proposed architecture is time-synchronized so that the original voice timing is preserved during conversion which allows lip-sync applications. Applied to voice gender conversion on the real-world VCTK dataset, our proposed architecture can learn successfully gender-independent representation and convert the voice gender with a very high efficiency and naturalness.

cs.SD↗

arXiv2021

Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels

This paper presents a end-to-end framework for the F0 transformation in the context of expressive voice conversion. A single neural network is proposed, in which a first module is used to learn F0 representation over different temporal scales and a second adversarial module is used to learn the transformation from one emotion to another. The first module is composed of a convolution layer with wavelet kernels so that the various temporal scales of F0 variations can be efficiently encoded. The single decomposition/transformation network allows to learn in a end-to-end manner the F0 decomposition that are optimal with respect to the transformation, directly from the raw F0 signal.

eess.AS↗

arXiv2021

Speaker Attentive Speech Emotion Recognition

Speech Emotion Recognition (SER) task has known significant improvements over the last years with the advent of Deep Neural Networks (DNNs). However, even the most successful methods are still rather failing when adaptation to specific speakers and scenarios is needed, inevitably leading to poorer performances when compared to humans. In this paper, we present novel work based on the idea of teaching the emotion recognition network about speaker identity. Our system is a combination of two ACRNN classifiers respectively dedicated to speaker and emotion recognition. The first informs the latter through a Self Speaker Attention (SSA) mechanism that is shown to considerably help to focus on emotional information of the speech signal. Experiments on social attitudes database Att-HACK and IEMOCAP corpus demonstrate the effectiveness of the proposed method and achieve the state-of-the-art performance in terms of unweighted average recall.

eess.AS↗