Publications by Philip Neil Garner

Related publications (25)

Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks

Understanding cognitive processes in the brain demands sophisticated models capable of replicating neural dynamics at large scales. We present a physiologically inspired speech recognition architecture, compatible and scalable with deep learning frameworks ...

2024

Low-Level Physiological Implications of End-to-End Learning of Speech Recognition

Philip Neil Garner

Current speech recognition architectures perform very well from the point of view of machine learning, hence user interaction. This suggests that they are emulating the human biological system well. We investigate whether the inference can be inverted to p ...

ISCA-INT SPEECH COMMUNICATION ASSOC2022

Incremental Syllable-Context Phonetic Vocoding

Petr Motlicek, Philip Neil Garner

Current very low bit rate speech coders are, due to complexity limitations, designed to work off-line. This paper investigates incremental speech coding that operates real-time and incrementally (i.e., encoded speech depends only on already-uttered speech ...

2015

Spatial Sound Localization via Multipath Euclidean Distance Matrix Recovery

Philip Neil Garner, Hervé Bourlard, Afsaneh Asaei, Mohammadjavad Taghizadeh, Saeid Haghighatshoar

A novel localization approach is proposed in order to find the position of an individual source using recordings of a single microphone in a reverberant enclosure. The multipath propagation is modeled by multiple virtual microphones as images of the actual ...

Ieee-Inst Electrical Electronics Engineers Inc2015

A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers

Philip Neil Garner

Neural Network (NN) classifiers can assign extreme probabilities to samples that have not appeared during training (out-of-distribution samples) resulting in erroneous and unreliable predictions. One of the causes for this unwanted behaviour lies in the us ...

IEEE Institute of Electrical and Electronics Engineers2020

Applying Multi- and Cross-Lingual Stochastic Phone Space Transformations to Non-Native Speech Recognition

Philip Neil Garner, Hervé Bourlard, Mathew Magimai Doss, David Imseng, John David Scott Dines

In the context of hybrid HMM/MLP Automatic Speech Recognition (ASR), this paper describes an investigation into a new type of stochastic phone space transformation, which maps "source" phone (or phone HMM state) posterior probabilities (as obtained at the ...

Ieee-Inst Electrical Electronics Engineers Inc2013

Beamforming with a Maximum Negentropy Criterion

Philip Neil Garner, Weifeng Li

In this paper, we address a beamforming application based on the capture of far-field speech data from a single speaker in a real meeting room. After the position of the speaker is estimated by a speaker tracking system, we construct a subband-domain beamf ...

2009

Training a Filter-Based Model of the Cochlea in the Context of Pre-Trained Acoustic Models

Philip Neil Garner, Louise Clothilde Coppieters De Gibson

Auditory research aims in general to lead to understanding of physiological processes. By contrast, the state of the art in automatic speech processing (notably recognition) is dominated by large pre-trained models that are meant to be used as black-boxes. ...

2024

Cross-lingual Adaptation of a CTC-based multilingual Acoustic Model

Philip Neil Garner, Hervé Bourlard, Sibo Tong

Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from monolingual context-de ...

ELSEVIER SCIENCE BV2018

Current trends in multilingual speech processing

Petr Motlicek, Philip Neil Garner, Hervé Bourlard, Mathew Magimai Doss, Lakshmi Babu Saheer, David Imseng, John David Scott Dines, Hui Liang

In this paper, we describe recent work at Idiap Research Institute in the domain of multilingual speech processing and provide some insights into emerging challenges for the research community. Multilingual speech processing has been a topic of ongoing int ...

2011

Intonation modelling using a muscle model and perceptually weighted matching pursuit

Philip Neil Garner, Pierre-Edouard Jean Charles Honnet

We propose a physiologically based intonation model using perceptual relevance. Motivated by speech synthesis from a speech-to-speech translation (S2ST) point of view, we aim at a language independent way of modelling intonation. The model presented in thi ...

2018

Cepstral normalisation and the signal to noise ratio spectrum in automatic speech recognition

Philip Neil Garner

Cepstral normalisation in automatic speech recognition is investigated in the context of robustness to additive noise. In this paper, it is argued that such normalisation leads naturally to a speech feature based on signal to noise ratio rather than absolu ...

2011

Transcribing meetings with the AMIDA systems

Philip Neil Garner, John David Scott Dines

In this paper we give an overview of the AMIDA systems for transcription of conference and lecture room meetings. The systems were developed for participation in the Rich Transcription evaluations conducted by the National Institute for Standards and Techn ...

2012

Exploiting foreign resources for DNN-based ASR

Petr Motlicek, Philip Neil Garner, David Imseng

Manual transcription of audio databases for the development of automatic speech recognition (ASR) systems is a costly and time-consuming process. In the context of deriving acoustic models adapted to a specific application, or in low-resource scenarios, it ...

2015

Context-Aware Attention Mechanism for Speech Emotion Recognition

Philip Neil Garner

In this work, we study the use of attention mechanisms to enhance the performance of the state-of-the-art deep learning model in Speech Emotion Recognition (SER). We introduce a new Long Short-Term Memory (LSTM)-based neural network attention model which i ...

IEEE2018

Ad Hoc Microphone Array Calibration: Euclidean Distance Matrix Completion Algorithm and Theoretical Guarantees

Hervé Bourlard, Philip Neil Garner, Afsaneh Asaei, Reza Parhizkar, Mohammadjavad Taghizadeh

This paper addresses the problem of ad hoc microphone array calibration where only partial information about the distances between the microphones is available. We construct a matrix consisting of the pairwise distances and propose to estimate the missing ...

2015

Vocal Tract Length Normalization for Statistical Parametric Speech Synthesis

Philip Neil Garner, Lakshmi Babu Saheer, John David Scott Dines

Vocal tract length normalization (VTLN) has been successfully used in automatic speech recognition for improved performance. The same technique can be implemented in statistical parametric speech synthesis for rapid speaker adaptation during synthesis. Thi ...

2012

The SUMMA Platform Prototype

Philip Neil Garner, Hervé Bourlard, Andrei Popescu-Belis, Nikolaos Pappas, Sibo Tong, Yang Wang, Lesly Sadiht Miculicich Werlen

We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring. The platform contains a rich suite of low-level and high-level natural language processing technologies: automatic speech recognition of broadca ...

Association for Computational Linguistics2017

Robust Microphone Placement for Source Localization from Noisy Distance Measurements

Philip Neil Garner, Hervé Bourlard, Afsaneh Asaei, Mohammadjavad Taghizadeh, Saeid Haghighatshoar

We propose a novel algorithm to design an optimum array geometry for source localization inside an enclosure. We assume a square-law decay propagation model for the sound acquisition so that the additive noise on the measured source-microphone distances is ...

2015

Bayesian Recurrent Units and the Forward-Backward Algorithm

Philip Neil Garner

Using Bayes's theorem, we derive a unit-wise recurrence as well as a backward recursion similar to the forward-backward algorithm. The resulting Bayesian recurrent units can be integrated as recurrent neural networks within deep learning frameworks, while ...

ISCA-INT SPEECH COMMUNICATION ASSOC2022