Search Results - "Illina, Irina"

Topic segmentation in ASR transcripts using bidirectional RNNS for change detection by Sehikh, Imran, Fohr, Dominique, Illina, Irina

“…Topic segmentation methods are mostly based on the idea of lexical cohesion, in which lexical distributions are analysed across the document and segment…”
Get full text

Training RNN language models on uncertain ASR hypotheses in limited data scenarios by Sheikh, Imran, Vincent, Emmanuel, Illina, Irina

“…Training domain-specific automatic speech recognition (ASR) systems requires a suitable amount of data comprising the target domain. In several scenarios, such…”
Get full text

DNN Uncertainty Propagation Using GMM-Derived Uncertainty Features for Noise Robust ASR by Nathwani, Karan, Vincent, Emmanuel, Illina, Irina

“…The uncertainty decoding framework is known to improve the deep neural network (DNN)-based automatic speech recognition (ASR) performance in noisy…”
Get full text

A combined evaluation of established and new approaches for speech recognition in varied reverberation conditions by Sivasankaran, Sunit, Vincent, Emmanuel, Illina, Irina

“…•A detailed study of various techniques for reverberation robust ASR is conducted.•Performances are evaluated and compared for new as well as established…”
Get full text

Dynamic adjustment of language models for automatic speech recognition using word similarity by Currey, Anna, Illina, Irina, Fohr, Dominique

“…Out-of-vocabulary (OOV) words can pose a particular problem for automatic speech recognition (ASR) of broadcast news. The language models (LMs) of ASR systems…”
Get full text

DNN-Based Mask Estimation for Distributed Speech Enhancement in Spatially Unconstrained Microphone Arrays by Furnon, Nicolas, Serizel, Romain, Essid, Slim, Illina, Irina

“…Deep neural network (DNN)-based speech enhancement algorithms in microphone arrays have now proven to be efficient solutions to speech understanding and speech…”
Get full text

VoiceHome-2, an extended corpus for multichannel speech processing in real homes by Bertin, Nancy, Camberlein, Ewen, Lebarbenchon, Romain, Vincent, Emmanuel, Sivasankaran, Sunit, Illina, Irina, Bimbot, Frédéric

“…We present a new, extended version of the voiceHome corpus for distant-microphone speech processing in domestic environments. This 5-hour corpus includes short…”
Get full text

Distributed Speech Separation in Spatially Unconstrained Microphone Arrays by Furnon, Nicolas, Serizel, Romain, Illina, Irina, Essid, Slim

“…Speech separation with several speakers is a challenging task because of the non-stationarity of the speech and the strong signal similarity between…”
Get full text

DNN-based Distributed Multichannel Mask Estimation for Speech Enhancement in Microphone Arrays by Furnon, Nicolas, Serizel, Romain, Illina, Irina, Essid, Slim

“…Multichannel processing is widely used for speech enhancement but several limitations appear when trying to deploy these solutions in the real world…”
Get full text

Discriminative importance weighting of augmented training data for acoustic model training by Sivasankaran, Sunit, Vincent, Emmanuel, Illina, Irina

“…DNN based acoustic models require a large amount of training data. Parametric data augmentation techniques such as adding noise, reverberation, or changing the…”
Get full text

BERT and fastText Embeddings for Automatic Detection of Toxic Speech by D'Sa, Ashwin Geet, Illina, Irina, Fohr, Dominique

“…With the expansion of Internet usage, catering to the dissemination of thoughts and expressions of an individual, there has been an immense increase in the…”
Get full text

Modelling Semantic Context of OOV Words in Large Vocabulary Continuous Speech Recognition by Sheikh, Imran, Fohr, Dominique, Illina, Irina, Linares, Georges

“…The diachronic nature of broadcast news data leads to the problem of out-of-vocabulary (OOV) words in large vocabulary continuous speech recognition (LVCSR)…”
Get full text

OOV Proper Name retrieval using topic and lexical context models by Sheikh, Imran, Illina, Irina, Fohr, Dominique, Linares, Georges

“…Retrieving Proper Names (PNs) specific to an audio document can be useful for vocabulary selection and OOV recovery in speech recognition, as well as in…”
Get full text

Document level semantic context for retrieving OOV proper names by Sheikh, Imran, Ulina, Irina, Fohr, Dominique, Linares, Georges

“…Recognition of Proper Names (PNs) in speech is important for content based indexing and browsing of audio-video data. However, many PNs are Out-Of-Vocabulary…”
Get full text

A wavelet-based parameterization for speech/music discrimination by Didiot, E., Illina, I., Fohr, D., Mella, O.

“…This paper addresses the problem of parameterization for speech/music discrimination. The current successful parameterization based on cepstral coefficients…”
Get full text

DNN-Based Semantic Model for Rescoring N-best Speech Recognition List by Fohr, Dominique, Illina, Irina

“…The word error rate (WER) of an automatic speech recognition (ASR) system increases when a mismatch occurs between the training and the testing conditions due…”
Get full text

Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection by Bose, Tulika, Illina, Irina, Fohr, Dominique

“…The concerning rise of hateful content on online platforms has increased the attention towards automatic hate speech detection, commonly formulated as a…”
Get full text

Evaluating grapheme-to-phoneme converters in automatic speech recognition context by Jouvet, D., Fohr, D., Illina, I.

“…This paper deals with the evaluation of grapheme-to-phoneme (G2P) converters in a speech recognition context. The precision and recall rates are investigated…”
Get full text

SAMbA: Speech enhancement with Asynchronous ad-hoc Microphone Arrays by Furnon, Nicolas, Serizel, Romain, Essid, Slim, Illina, Irina

“…Speech enhancement in ad-hoc microphone arrays is often hindered by the asynchronization of the devices composing the microphone array. Asynchronization comes…”
Get full text

A Wavelet-Based Parameterization for Speech/Music Discrimination by Didiot, E., Illina, Irina, Fohr, D., Mella, O.

“…This paper addresses the problem of parameterization for speech/music discrimination. The current successful parameterization based on cepstral coefficients…”
Get full text