Search Results for author: Jordi Luque

Found 20 papers, 5 papers with code

Recycle Your Wav2Vec2 Codebook: A Speech Perceiver for Keyword Spotting

no code implementations COLING 2022 Guillermo Cámbara, Jordi Luque, Mireia Farrús

We do so by transferring the codebook as weights for the latent bottleneck of a Keyword Spotting Perceiver, thus initializing such model with phonetic embeddings already.

Small-Footprint Keyword Spotting

Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles

1 code implementation17 Oct 2023 Fernando López, Jordi Luque, Carlos Segura, Pablo Gómez

It employs two models: a lightweight on-device model for real-time processing of the audio stream and a verification model on the server-side, which is an ensemble of heterogeneous architectures that refine detection.

Data Augmentation for Low-Resource Quechua ASR Improvement

no code implementations14 Jul 2022 Rodolfo Zevallos, Nuria Bel, Guillermo Cámbara, Mireia Farrús, Jordi Luque

In this paper we describe our data augmentation approach to improve the results of ASR models for low-resource and agglutinative languages.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Voice Quality and Pitch Features in Transformer-Based Speech Recognition

no code implementations21 Dec 2021 Guillermo Cámbara, Jordi Luque, Mireia Farrús

Jitter and shimmer measurements have shown to be carriers of voice quality and prosodic information which enhance the performance of tasks like speaker recognition, diarization or automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Influence of ASR and Language Model on Alzheimer's Disease Detection

no code implementations20 Sep 2021 Joan Codina-Filbà, Guillermo Cámbara, Jordi Luque, Mireia Farrús

Furthermore, we study the influence of a language model -- which tends to correct non-standard sequences of words -- with the lack of language model to decode the hypothesis from the ASR.

Alzheimer's Disease Detection Language Modelling

English Accent Accuracy Analysis in a State-of-the-Art Automatic Speech Recognition System

no code implementations9 May 2021 Guillermo Cámbara, Alex Peiró-Lilja, Mireia Farrús, Jordi Luque

Nowadays, research in speech technologies has gotten a lot out thanks to recently created public domain corpora that contain thousands of recording hours.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Efficient Keyword Spotting by capturing long-range interactions with Temporal Lambda Networks

1 code implementation16 Apr 2021 Biel Tura, Santiago Escuder, Ferran Diego, Carlos Segura, Jordi Luque

This work explores the application of Lambda networks, an alternative framework for capturing long-range interactions without attention, for the keyword spotting task.

Keyword Spotting speech-recognition +1

Convolutional Speech Recognition with Pitch and Voice Quality Features

no code implementations2 Sep 2020 Guillermo Cámbara, Jordi Luque, Mireia Farrús

Up to our knowledge, this is the first work combining such pitch and voice quality features with modern convolutional architectures, showing improvements up to 7% and 3% relative WER points, for the publicly available Spanish Common Voice and LibriSpeech 100h datasets, respectively.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Transcription-Enriched Joint Embeddings for Spoken Descriptions of Images and Videos

no code implementations1 Jun 2020 Benet Oriol, Jordi Luque, Ferran Diego, Xavier Giro-i-Nieto

In this work, we propose an effective approach for training unique embedding representations by combining three simultaneous modalities: image and spoken and textual narratives.


Detection of speech events and speaker characteristics through photo-plethysmographic signal neural processing

no code implementations12 Nov 2019 Guillermo Cámbara, Jordi Luque, Mireia Farrús

The use of photoplethysmogram signal (PPG) for heart and sleep monitoring is commonly found nowadays in smartphones and wrist wearables.

Emergence of linguistic laws in human voice

no code implementations9 Oct 2016 Ivan Gonzalez Torre, Bartolo Luque, Lucas Lacasa, Jordi Luque, Antoni Hernandez-Fernandez

This means that inferences of statistical patterns of language in acoustics are biased by the arbitrary, language-dependent segmentation of the signal, and virtually precludes the possibility of making comparative studies between human voice and other animal communication systems.

Speech earthquakes: scaling and universality in human voice

no code implementations5 Aug 2014 Jordi Luque, Bartolo Luque, Lucas Lacasa

We first show that during speech the energy is unevenly released and power-law distributed, reporting a universal robust Gutenberg-Richter-like law in speech.

Speech Synthesis

Cannot find the paper you are looking for? You can Submit a new open access paper.