Search Results for author:
Found 20 papers, 5 papers with code
Seeing and Hearing Egocentric Actions: How Much Can We Learn?
Our interaction with the world is an inherently multimodal experience.
Efficient Keyword Spotting by capturing long-range interactions with Temporal Lambda Networks
This work explores the application of Lambda networks, an alternative framework for capturing long-range interactions without attention, for the keyword spotting task.
Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation
The alignments are computed iteratively upon a corpus of broadcast TV.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles
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.
Input complexity and out-of-distribution detection with likelihood-based generative models
Likelihood-based generative models are a promising resource to detect out-of-distribution (OOD) inputs which could compromise the robustness or reliability of a machine learning system.
Ranked #10 on
Anomaly Detection
on Unlabeled CIFAR-10 vs CIFAR-100
Emergence of linguistic laws in human voice
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
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.
How Much Does Audio Matter to Recognize Egocentric Object Interactions?
Sounds are an important source of information on our daily interactions with objects.
Detection of speech events and speaker characteristics through photo-plethysmographic signal neural processing
The use of photoplethysmogram signal (PPG) for heart and sleep monitoring is commonly found nowadays in smartphones and wrist wearables.
Transcription-Enriched Joint Embeddings for Spoken Descriptions of Images and Videos
In this work, we propose an effective approach for training unique embedding representations by combining three simultaneous modalities: image and spoken and textual narratives.
Convolutional Speech Recognition with Pitch and Voice Quality Features
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
Speech Enhancement for Wake-Up-Word detection in Voice Assistants
Keyword spotting and in particular Wake-Up-Word (WUW) detection is a very important task for voice assistants.
BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge
This paper describes joint effort of BUT and Telef\'onica Research on development of Automatic Speech Recognition systems for Albayzin 2020 Challenge.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
English Accent Accuracy Analysis in a State-of-the-Art Automatic Speech Recognition System
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
Influence of ASR and Language Model on Alzheimer's Disease Detection
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.
A unifying framework for modeling acoustic/prosodic entrainment: definition and evaluation on two large corpora
Acoustic/prosodic (a/p) entrainment has been associated with multiple positive social aspects of human-human conversations.
Voice Quality and Pitch Features in Transformer-Based Speech Recognition
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
Data Augmentation for Low-Resource Quechua ASR Improvement
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
Recycle Your Wav2Vec2 Codebook: A Speech Perceiver for Keyword Spotting
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.
Scheduling Inference Workloads on Distributed Edge Clusters with Reinforcement Learning
Many real-time applications (e. g., Augmented/Virtual Reality, cognitive assistance) rely on Deep Neural Networks (DNNs) to process inference tasks.
