Výsledky vyhledávání - "Index Terms: speech recognition"

A Perceptual Study of CV Syllables in both Spoken and Whistled Speech: a Tashlhiyt Berber Perspective

Autor: Julien Meyer, Silvain Gerber, Rachid Ridouane, Laure Dentel

Publikováno v: Interspeech 2019-20th Annual Conference of the International Speech Communication Association
Interspeech 2019-20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria. ⟨10.21437/Interspeech.2019-2251⟩
INTERSPEECH

International audience; The present study compares the perceptual categorization of four CV syllables /ta, da, ka, ga/ in two different speech registers-modal speech and whistled speech-of Tashlhiyt Berber used in the Moroccan High Atlas. Whistled sp

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10826f44ea8a5a115e45bafedecb4a21
https://hal.archives-ouvertes.fr/hal-02371794

Zobrazit plný text záznamu

End-to-End Speech Recognition from the Raw Waveform

Autor: Ronan Collobert, Neil Zeghidour, Gabriel Synnaeve, Nicolas Usunier, Emmanuel Dupoux

Publikováno v: INTERSPEECH
Interspeech 2018
Interspeech 2018, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-2414⟩

State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. In this paper, we study end-to-end systems trained directly from the raw waveform, build

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6b0110af2451c48ed1af41aeaef2cbc
https://doi.org/10.21437/interspeech.2018-2414

Zobrazit plný text záznamu

Belief Hidden Markov Model for speech recognition

Autor: Boutheina Ben Yaghlane, Siwar Jendoubi, Arnaud Martin

Publikováno v: International Conference on Modeling, Simulation and Applied Optimization (ICMSAO)
International Conference on Modeling, Simulation and Applied Optimization (ICMSAO), Apr 2013, Hammamet, Tunisia. pp.1-6, ⟨10.1109/ICMSAO.2013.6552563⟩

International audience; Speech Recognition searches to predict the spoken words automatically. These systems are known to be very expensive because of using several pre-recorded hours of speech. Hence, building a model that minimizes the cost of the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc5117a952061df0e1d19db83e62a253
https://hal.science/hal-01108027/file/articleV05.pdf

Zobrazit plný text záznamu

Bag of n-gram driven decoding for LVCSR system harnessing

Autor: Georges Linarès, Yannick Estève, Fethi Bougares, Paul Deléglise

Publikováno v: ASRU

—This paper focuses on automatic speech recognition systems combination based on driven decoding paradigms. The driven decoding algorithm (DDA) involves the use of a 1-best hypothesis provided by an auxiliary system as another knowledge source in t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bfa4b81569b70d6fff4aed0360c26a35
https://hal.archives-ouvertes.fr/hal-01315538

Zobrazit plný text záznamu

Unsupervised knowledge acquisition for Extracting Named Entities from speech

Autor: Frédéric Béchet, Eric Charton

Publikováno v: ICASSP
IEEE International Conference on Acoustics, Speech and Signal Processing
IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2010, Dallas, United States. ⟨10.1109/ICASSP.2010.5494962⟩

International audience; This paper presents a Named Entity Recognition (NER) method dedicated to process speech transcriptions. The main principle behind this method is to collect in an unsupervised way lexical knowledge for all entries in the ASR le

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::df6b78596703f3d993c426923b787f63
https://doi.org/10.1109/icassp.2010.5494962

Zobrazit plný text záznamu

Fast adaptation of GMM-based compact models

Autor: Jean-François Bonastre, Christophe Lévy, Georges Linarès

Publikováno v: INTERSPEECH

In this paper, a new strategy for a fast adaptation of acoustic models is proposed for embedded speech recognition. It relies on a general GMM, which represents the whole acoustic space, associated with a set of HMM state-dependent probability functi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::21557d50fbeef49dc9ba340bd0fd728a
https://doi.org/10.21437/interspeech.2007-123

Zobrazit plný text záznamu

Information Retrieval Strategies for Accessing African Audio Corpora

Autor: Abdillahi Nimaan, Frédéric Béchet, Jean-François Bonastre, Pascal Nocera

Publikováno v: INTERSPEECH
INTERSPEECH, Aug 2007, Anvers, Belgium

In this paper we present a first approach to access African oral corpora, combining automatic speech recognition and information retrieval. Firstly, we present the principal characteristics of our Somali speech recognizer [8] and the results obtained

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::094eb479d2a25d7990c67de8dcae9cf7
https://hal.archives-ouvertes.fr/hal-01319828

Zobrazit plný text záznamu

Morphosyntactic Processing of N-Best Lists for Improved Recognition and Confidence Measure Computation

Autor: Stéphane Huet, Pascale Sébillot, Guillaume Gravier

Publikováno v: 8th Annual Conference of the International Speech Communication Association (Interspeech)
8th Annual Conference of the International Speech Communication Association (Interspeech), 2007, Antwerp, Belgium. pp.1741-1744
INTERSPEECH

International audience; We study the use of morphosyntactic knowledge to process N-best lists. We propose a new score function that combines the parts of speech (POS), language model, and acoustic scores at the sentence level. Experimental results, o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a220ea8c328400d0a57110b823b2f3d9
https://hal.science/hal-02021878/file/IS07.pdf

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání