no code implementations • 5 Feb 2024 • Álvaro Martín-Cortinas, Daniel Sáez-Trigueros, Iván Vallés-Pérez, Biel Tura-Vecino, Piotr Biliński, Mateusz Lajszczak, Grzegorz Beringer, Roberto Barra-Chicote, Jaime Lorenzo-Trueba
Using speaker-disentangled codes to train LLMs for text-to-speech (TTS) allows the LLM to generate the content and the style of the speech only from the text, similarly to humans, while the speaker identity is provided by the decoder of the VC model.
1 code implementation • 15 Jan 2023 • Iván Vallés-Pérez, Emilio Soria-Olivas, Marcelino Martínez-Sober, Antonio J. Serrano-López, Joan Vila-Francés, Juan Gómez-Sanchís
In this work we propose a new non-monotonic activation function: the modulus.
no code implementations • 4 Nov 2022 • Xin Zhang, Iván Vallés-Pérez, Andreas Stolcke, Chengzhu Yu, Jasha Droppo, Olabanji Shonibare, Roberto Barra-Chicote, Venkatesh Ravichandran
By fine-tuning an ASR model on synthetic stuttered speech we are able to reduce word error by 5. 7% relative on stuttered utterances, with only minor (<0. 2% relative) degradation for fluent utterances.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 16 Apr 2022 • Iván Vallés-Pérez, Emilio Soria-Olivas, Marcelino Martínez-Sober, Antonio J. Serrano-López, Juan Gómez-Sanchís, Fernando Mateo
Accurate and fast demand forecast is one of the hot topics in supply chain for enabling the precise execution of the corresponding downstream processes (inbound and outbound planning, inventory placement, network planning, etc).
1 code implementation • 9 Oct 2021 • Iván Vallés-Pérez, Juan Gómez-Sanchis, Marcelino Martínez-Sober, Joan Vila-Francés, Antonio J. Serrano-López, Emilio Soria-Olivas
The field of conversational agents is growing fast and there is an increasing need for algorithms that enhance natural interaction.
no code implementations • 10 Jun 2021 • Iván Vallés-Pérez, Julian Roth, Grzegorz Beringer, Roberto Barra-Chicote, Jasha Droppo
This paper proposes a new neural text-to-speech model that approaches the disentanglement problem by conditioning a Tacotron2-like architecture on flow-normalized speaker embeddings, and by substituting the reference encoder with a new learned latent distribution responsible for modeling the intra-sentence variability due to the prosody.