Publication

End-to-End Acoustic Modeling using Convolutional Neural Networks for HMM-based Automatic Speech Recognition

Related publications (181)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Microphone Array Speech Recognition : Experiments on Overlapping Speech in Meetings

Darren Moore

This paper investigates the use of microphone arrays to acquire and recognise speech in meetings. Meetings pose several interesting problems for speech processing, as they consist of multiple competing speakers within a small space, typically around a tabl ...

IDIAP2002

TODE: A Decoder for Continuous Speech Recognition

Darren Moore

This document describes a new continuous speech decoder, TODE, which is compatible with the Torch machine learning software library. A brief theory of speech recognition is presented followed by a detailed description of the architecture of TODE and the co ...

IDIAP2002

Speech/Music Discrimination using Entropy and Dynamism Features in a HMM Classification Framewor

Hervé Bourlard, Jitendra Ajmera

In this paper, we present a new approach towards high performance speech/music discrimination on realistic tasks related to the automatic transcription of broadcast news. In the approach presented here, the (local) Probability Density Function (PDF) estima ...

IDIAP2001

User Customized HMM/ANN Based Speaker Verification

Hervé Bourlard

In this paper, we describe a new speaker verification approach, using a hybrid HMM/ANN system, and accommodating user customized passwords. This system is exploiting the high phonetic recognition rates usually achieved by HMM/ANN speaker independent system ...

IDIAP2001

Robust Speech Recognition and Feature Extraction Using HMM2

Hervé Bourlard, Samy Bengio, Katrin Weber, Shajith Ikbal

This paper presents the theoretical basis and preliminary experimental results of a new HMM model, referred to as HMM2, which can be considered as a mixture of HMMs. In this new model, the emission probabilities of the temporal (primary) HMM are estimated ...

IDIAP2001

HMM2- Extraction of Formant Features and their Use for Robust ASR

Hervé Bourlard, Samy Bengio, Katrin Weber

As recently introduced, an HMM2 can be considered as a particular case of an HMM mixture in which the HMM emission probabilities (usually estimated through Gaussian mixtures or an artificial neural network) are modeled by state-dependent, feature-based HMM ...

2001

Some applications of a priori knowledge in multi-stream HMM and HMM/ANN based ASR

Multi-band ASR was largely inspired by the extremely high level of redundancy in the spectral signal representation which can be inferred from Fletcher's product-of-errors rule for human speech perception. Indeed, the main aim of the multi-band approach is ...

2000

Audio-Visual Speech Modelling for Continuous Speech Recognition

This paper describes a complete system for audio-visual recognition of continuous speech including robust lip tracking, visual feature extraction, noise-robust acoustic feature extraction, and sensor integration. An appearance based model of the articulato ...

2000

HMM2- Extraction of Formant Features and their Use for Robust ASR

Hervé Bourlard, Samy Bengio, Katrin Weber

IDIAP2000

LPC-based inversion of the DRM articulatory model

Sacha Krstulovic

Articulatory representations are expected to bring better speech recognition results. This requires to estimate the parameters of a speech production model from the speech sound, problem known as acoustico-articulatory inversion. Known methods to solve thi ...

1999