Open-Source System for Multilingual Translation and Cloned Speech Synthesis

We present an open-source system designed for multilingual translation and speech regeneration, addressing challenges in communication and accessibility across diverse linguistic contexts. The system integrates Whisper for speech recognition with Voice Activity Detection (VAD) to identify speaking intervals, followed by a pipeline of Large Language Models (LLMs). For multilingual applications, the first LLM segments speech into coherent, complete sentences, which a second LLM then translates. For speech regeneration, the system uses a text-to-speech (TTS) module with voice cloning capabilities to replicate the original speaker's voice, maintaining naturalness and speaker identity. The system's open-source components can operate locally or via APIs, offering cost-effective deployment across various use cases. These include real-time multilingual translation in Zoom sessions, speech regeneration for public broadcasts, and Bluetooth-enabled multilingual playback through personal devices. By preserving the speaker's voice, the system ensures a seamless and immersive experience, whether translating or regenerating speech. This open-source project is shared with the community to foster innovation and accessibility. We provide a detailed system performance analysis, including latency and word accuracy, demonstrating its potential to enable inclusive, adaptable communication solutions in real-world multilingual scenarios.

Decoding Vocal Articulations from Acoustic Latent Representations

We present a novel neural encoder system for acoustic-to-articulatory inversion. We leverage the Pink Trombone voice synthesizer that reveals articulatory parameters (e.g tongue position and vocal cord configuration). Our system is designed to identify the articulatory features responsible for producing specific acoustic characteristics contained in a neural latent representation. To generate the necessary latent embeddings, we employed two main methodologies. The first was a self-supervised variational autoencoder trained from scratch to reconstruct the input signal at the decoder stage. We conditioned its bottleneck layer with a subnetwork called the "projector," which decodes the voice synthesizer's parameters. The second methodology utilized two pretrained models: EnCodec and Wav2Vec. They eliminate the need to train the encoding process from scratch, allowing us to focus on training the projector network. This approach aimed to explore the potential of these existing models in the context of acoustic-to-articulatory inversion. By reusing the pretrained models, we significantly simplified the data processing pipeline, increasing efficiency and reducing computational overhead. The primary goal of our project was to demonstrate that these neural architectures can effectively encapsulate both acoustic and articulatory features. This prediction-based approach is much faster than traditional methods focused on acoustic feature-based parameter optimization. We validated our models by predicting six different parameters and evaluating them with objective and ViSQOL subjective-equivalent metric using both synthesizer- and human-generated sounds. The results show that the predicted parameters can generate human-like vowel sounds when input into the synthesizer. We provide the dataset, code, and detailed findings to support future research in this field.

Del Visual al Auditivo: Sonorización de Escenas Guiada por Imagen

Recent advances in image, video, text and audio generative techniques, and their use by the general public, are leading to new forms of content generation. Usually, each modality was approached separately, which poses limitations. The automatic sound recording of visual sequences is one of the greatest challenges for the automatic generation of multimodal content. We present a processing flow that, starting from images extracted from videos, is able to sound them. We work with pre-trained models that employ complex encoders, contrastive learning, and multiple modalities, allowing complex representations of the sequences for their sonorization. The proposed scheme proposes different possibilities for audio mapping and text guidance. We evaluated the scheme on a dataset of frames extracted from a commercial video game and sounds extracted from the Freesound platform. Subjective tests have evidenced that the proposed scheme is able to generate and assign audios automatically and conveniently to images. Moreover, it adapts well to user preferences, and the proposed objective metrics show a high correlation with the subjective ratings.

IA Para el Mantenimiento Predictivo en Canteras: Modelado

Dependence on raw materials, especially in the mining sector, is a key part of today's economy. Aggregates are vital, being the second most used raw material after water. Digitally transforming this sector is key to optimizing operations. However, supervision and maintenance (predictive and corrective) are challenges little explored in this sector, due to the particularities of the sector, machinery and environmental conditions. All this, despite the successes achieved in other scenarios in monitoring with acoustic and contact sensors. We present an unsupervised learning scheme that trains a variational autoencoder model on a set of sound records. This is the first such dataset collected during processing plant operations, containing information from different points of the processing line. Our results demonstrate the model's ability to reconstruct and represent in latent space the recorded sounds, the differences in operating conditions and between different equipment. In the future, this should facilitate the classification of sounds, as well as the detection of anomalies and degradation patterns in the operation of the machinery.

FOLEY-VAE: Generación de efectos de audio para cine con inteligencia artificial

In this research, we present an interface based on Variational Autoencoders trained with a wide range of natural sounds for the innovative creation of Foley effects. The model can transfer new sound features to prerecorded audio or microphone-captured speech in real time. In addition, it allows interactive modification of latent variables, facilitating precise and customized artistic adjustments. Taking as a starting point our previous study on Variational Autoencoders presented at this same congress last year, we analyzed an existing implementation: RAVE [1]. This model has been specifically trained for audio effects production. Various audio effects have been successfully generated, ranging from electromagnetic, science fiction, and water sounds, among others published with this work. This innovative approach has been the basis for the artistic creation of the first Spanish short film with sound effects assisted by artificial intelligence. This milestone illustrates palpably the transformative potential of this technology in the film industry, opening the door to new possibilities for sound creation and the improvement of artistic quality in film productions.

Optimization Techniques for a Physical Model of Human Vocalisation

We present a non-supervised approach to optimize and evaluate the synthesis of non-speech audio effects from a speech production model. We use the Pink Trombone synthesizer as a case study of a simplified production model of the vocal tract to target non-speech human audio signals --yawnings. We selected and optimized the control parameters of the synthesizer to minimize the difference between real and generated audio. We validated the most common optimization techniques reported in the literature and a specifically designed neural network. We evaluated several popular quality metrics as error functions. These include both objective quality metrics and subjective-equivalent metrics. We compared the results in terms of total error and computational demand. Results show that genetic and swarm optimizers outperform least squares algorithms at the cost of executing slower and that specific combinations of optimizers and audio representations offer significantly different results. The proposed methodology could be used in benchmarking other physical models and audio types.